If the function bfq_update_next_in_service is invoked as a consequence
of the activation or requeueing of an entity, say E, and finds out
that E belongs to a higher-priority class than that of the current
next-in-service entity, then it sets next_in_service directly to
E. But this may lead to anomalous schedules, because E may happen not
be eligible for service, because its virtual start time is higher than
the system virtual time for its service tree.
This commit addresses this issue by simply removing this direct
switch.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
To provide a very smooth service, bfq starts to serve a bfq_queue
only if the queue is 'eligible', i.e., if the same queue would
have started to be served in the ideal, perfectly fair system that
bfq simulates internally. This is obtained by associating each
queue with a virtual start time, and by computing a special system
virtual time quantity: a queue is eligible only if the system
virtual time has reached the virtual start time of the
queue. Finally, bfq guarantees that, when a new queue must be set
in service, there is always at least one eligible entity for each
active parent entity in the scheduler. To provide this guarantee,
the function __bfq_lookup_next_entity pushes up, for each parent
entity on which it is invoked, the system virtual time to the
minimum among the virtual start times of the entities in the
active tree for the parent entity (more precisely, the push up
occurs if the system virtual time happens to be lower than all
such virtual start times).
There is however a circumstance in which __bfq_lookup_next_entity
cannot push up the system virtual time for a parent entity, even
if the system virtual time is lower than the virtual start times
of all the child entities in the active tree. It happens if one of
the child entities is in service. In fact, in such a case, there
is already an eligible entity, the in-service one, even if it may
not be not present in the active tree (because in-service entities
may be removed from the active tree).
Unfortunately, in the last re-design of the
hierarchical-scheduling engine, the reset of the pointer to the
in-service entity for a given parent entity--reset to be done as a
consequence of the expiration of the in-service entity--always
happens after the function __bfq_lookup_next_entity has been
invoked. This causes the function to think that there is still an
entity in service for the parent entity, and then that the system
virtual time cannot be pushed up, even if actually such a
no-more-in-service entity has already been properly reinserted
into the active tree (or in some other tree if no more
active). Yet, the system virtual time *had* to be pushed up, to be
ready to correctly choose the next queue to serve. Because of the
lack of this push up, bfq may wrongly set in service a queue that
had been speculatively pre-computed as the possible
next-in-service queue, but that would no more be the one to serve
after the expiration and the reinsertion into the active trees of
the previously in-service entities.
This commit addresses this issue by making
__bfq_lookup_next_entity properly push up the system virtual time
if an expiration is occurring.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The SAS code will need it. Also mark the name argument const to match
bsg_register_queue.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
The block core requests modules with the "-iosched" name suffix, but
mq-deadline does not have that suffix. Add an alias.
Fixes: 945ffb60c1 ("mq-deadline: add blk-mq adaptation of the deadline ...")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The block core requests modules with the "-iosched" name suffix, but
bfq no longer has that suffix. Add an alias.
Fixes: ea25da4808 ("block, bfq: split bfq-iosched.c into multiple ...")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The only caller of this function is blk_start_request() in the same
file. Fix blk_start_request() description accordingly.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
struct call_single_data is used in IPIs to transfer information between
CPUs. Its size is bigger than sizeof(unsigned long) and less than
cache line size. Currently it is not allocated with any explicit alignment
requirements. This makes it possible for allocated call_single_data to
cross two cache lines, which results in double the number of the cache lines
that need to be transferred among CPUs.
This can be fixed by requiring call_single_data to be aligned with the
size of call_single_data. Currently the size of call_single_data is the
power of 2. If we add new fields to call_single_data, we may need to
add padding to make sure the size of new definition is the power of 2
as well.
Fortunately, this is enforced by GCC, which will report bad sizes.
To set alignment requirements of call_single_data to the size of
call_single_data, a struct definition and a typedef is used.
To test the effect of the patch, I used the vm-scalability multiple
thread swap test case (swap-w-seq-mt). The test will create multiple
threads and each thread will eat memory until all RAM and part of swap
is used, so that huge number of IPIs are triggered when unmapping
memory. In the test, the throughput of memory writing improves ~5%
compared with misaligned call_single_data, because of faster IPIs.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Huang, Ying <ying.huang@intel.com>
[ Add call_single_data_t and align with size of call_single_data. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/87bmnqd6lz.fsf@yhuang-mobile.sh.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a race between changing I/O elevator and request_queue removal
which can trigger the warning in kobject_add_internal. A program can
use sysfs to request a change of elevator at the same time another task
is unregistering the request_queue the elevator would be attached to.
The elevator's kobject will then attempt to be connected to the
request_queue in the object tree when the request_queue has just been
removed from sysfs. This triggers the warning in kobject_add_internal
as the request_queue no longer has a sysfs directory:
kobject_add_internal failed for iosched (error: -2 parent: queue)
------------[ cut here ]------------
WARNING: CPU: 3 PID: 14075 at lib/kobject.c:244 kobject_add_internal+0x103/0x2d0
To fix this warning, we can check the QUEUE_FLAG_REGISTERED flag when
changing the elevator and use the request_queue's sysfs_lock to
serialize between clearing the flag and the elevator testing the flag.
Signed-off-by: David Jeffery <djeffery@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The last parameter "count" never be used in xxx_var_store,
convert these functions to void.
Signed-off-by: weiping zhang <zhangweiping@didichuxing.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Normally I wouldn't bother with this, but in my opinion the comments are
the most important part of this whole file since without them no one
would have any clue how this insanity works.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The symbolic constants QUEUE_FLAG_SCSI_PASSTHROUGH, QUEUE_FLAG_QUIESCED
and REQ_NOWAIT are missing from blk-mq-debugfs.c. Add these to
blk-mq-debugfs.c such that these appear as names in debugfs instead of
as numbers.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
put_device(pdev) will call pdev->type->release finally, and blk_free_devt
has been called in part_release(), so remove it.
Signed-off-by: weiping zhang <zhangweiping@didichuxing.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since we split the scsi_request out of struct request bsg fails to
provide a reply-buffer for the drivers. This was done via the pointer
for sense-data, that is not preallocated anymore.
Failing to allocate/assign it results in illegal dereferences because
LLDs use this pointer unquestioned.
An example panic on s390x, using the zFCP driver, looks like this (I had
debugging on, otherwise NULL-pointer dereferences wouldn't even panic on
s390x):
Unable to handle kernel pointer dereference in virtual kernel address space
Failing address: 6b6b6b6b6b6b6000 TEID: 6b6b6b6b6b6b6403
Fault in home space mode while using kernel ASCE.
AS:0000000001590007 R3:0000000000000024
Oops: 0038 ilc:2 [#1] PREEMPT SMP DEBUG_PAGEALLOC
Modules linked in: <Long List>
CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.12.0-bsg-regression+ #3
Hardware name: IBM 2964 N96 702 (z/VM 6.4.0)
task: 0000000065cb0100 task.stack: 0000000065cb4000
Krnl PSW : 0704e00180000000 000003ff801e4156 (zfcp_fc_ct_els_job_handler+0x16/0x58 [zfcp])
R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3
Krnl GPRS: 0000000000000001 000000005fa9d0d0 000000005fa9d078 0000000000e16866
000003ff00000290 6b6b6b6b6b6b6b6b 0000000059f78f00 000000000000000f
00000000593a0958 00000000593a0958 0000000060d88800 000000005ddd4c38
0000000058b50100 07000000659cba08 000003ff801e8556 00000000659cb9a8
Krnl Code: 000003ff801e4146: e31020500004 lg %r1,80(%r2)
000003ff801e414c: 58402040 l %r4,64(%r2)
#000003ff801e4150: e35020200004 lg %r5,32(%r2)
>000003ff801e4156: 50405004 st %r4,4(%r5)
000003ff801e415a: e54c50080000 mvhi 8(%r5),0
000003ff801e4160: e33010280012 lt %r3,40(%r1)
000003ff801e4166: a718fffb lhi %r1,-5
000003ff801e416a: 1803 lr %r0,%r3
Call Trace:
([<000003ff801e8556>] zfcp_fsf_req_complete+0x726/0x768 [zfcp])
[<000003ff801ea82a>] zfcp_fsf_reqid_check+0x102/0x180 [zfcp]
[<000003ff801eb980>] zfcp_qdio_int_resp+0x230/0x278 [zfcp]
[<00000000009b91b6>] qdio_kick_handler+0x2ae/0x2c8
[<00000000009b9e3e>] __tiqdio_inbound_processing+0x406/0xc10
[<00000000001684c2>] tasklet_action+0x15a/0x1d8
[<0000000000bd28ec>] __do_softirq+0x3ec/0x848
[<00000000001675a4>] irq_exit+0x74/0xf8
[<000000000010dd6a>] do_IRQ+0xba/0xf0
[<0000000000bd19e8>] io_int_handler+0x104/0x2d4
[<00000000001033b6>] enabled_wait+0xb6/0x188
([<000000000010339e>] enabled_wait+0x9e/0x188)
[<000000000010396a>] arch_cpu_idle+0x32/0x50
[<0000000000bd0112>] default_idle_call+0x52/0x68
[<00000000001cd0fa>] do_idle+0x102/0x188
[<00000000001cd41e>] cpu_startup_entry+0x3e/0x48
[<0000000000118c64>] smp_start_secondary+0x11c/0x130
[<0000000000bd2016>] restart_int_handler+0x62/0x78
[<0000000000000000>] (null)
INFO: lockdep is turned off.
Last Breaking-Event-Address:
[<000003ff801e41d6>] zfcp_fc_ct_job_handler+0x3e/0x48 [zfcp]
Kernel panic - not syncing: Fatal exception in interrupt
This patch moves bsg-lib to allocate and setup struct bsg_job ahead of
time, including the allocation of a buffer for the reply-data.
This means, struct bsg_job is not allocated separately anymore, but as part
of struct request allocation - similar to struct scsi_cmd. Reflect this in
the function names that used to handle creation/destruction of struct
bsg_job.
Reported-by: Steffen Maier <maier@linux.vnet.ibm.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com>
Fixes: 82ed4db499 ("block: split scsi_request out of struct request")
Cc: <stable@vger.kernel.org> #4.11+
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In dm-integrity target we register integrity profile that have
both generate_fn and verify_fn callbacks set to NULL.
This is used if dm-integrity is stacked under a dm-crypt device
for authenticated encryption (integrity payload contains authentication
tag and IV seed).
In this case the verification is done through own crypto API
processing inside dm-crypt; integrity profile is only holder
of these data. (And memory is owned by dm-crypt as well.)
After the commit (and previous changes)
Commit 7c20f11680
Author: Christoph Hellwig <hch@lst.de>
Date: Mon Jul 3 16:58:43 2017 -0600
bio-integrity: stop abusing bi_end_io
we get this crash:
: BUG: unable to handle kernel NULL pointer dereference at (null)
: IP: (null)
: *pde = 00000000
...
:
: Workqueue: kintegrityd bio_integrity_verify_fn
: task: f48ae180 task.stack: f4b5c000
: EIP: (null)
: EFLAGS: 00210286 CPU: 0
: EAX: f4b5debc EBX: 00001000 ECX: 00000001 EDX: 00000000
: ESI: 00001000 EDI: ed25f000 EBP: f4b5dee8 ESP: f4b5dea4
: DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
: CR0: 80050033 CR2: 00000000 CR3: 32823000 CR4: 001406d0
: Call Trace:
: ? bio_integrity_process+0xe3/0x1e0
: bio_integrity_verify_fn+0xea/0x150
: process_one_work+0x1c7/0x5c0
: worker_thread+0x39/0x380
: kthread+0xd6/0x110
: ? process_one_work+0x5c0/0x5c0
: ? kthread_worker_fn+0x100/0x100
: ? kthread_worker_fn+0x100/0x100
: ret_from_fork+0x19/0x24
: Code: Bad EIP value.
: EIP: (null) SS:ESP: 0068:f4b5dea4
: CR2: 0000000000000000
Patch just skip the whole verify workqueue if verify_fn is set to NULL.
Fixes: 7c20f116 ("bio-integrity: stop abusing bi_end_io")
Signed-off-by: Milan Broz <gmazyland@gmail.com>
[hch: trivial whitespace fix]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
discard request usually is very big and easily use all bandwidth budget
of a cgroup. discard request size doesn't really mean the size of data
written, so it doesn't make sense to account it into bandwidth budget.
Jens pointed out treating the size 0 doesn't make sense too, because
discard request does have cost. But it's not easy to find the actual
cost. This patch simply makes the size one sector.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This way we don't need a block_device structure to submit I/O. The
block_device has different life time rules from the gendisk and
request_queue and is usually only available when the block device node
is open. Other callers need to explicitly create one (e.g. the lightnvm
passthrough code, or the new nvme multipathing code).
For the actual I/O path all that we need is the gendisk, which exists
once per block device. But given that the block layer also does
partition remapping we additionally need a partition index, which is
used for said remapping in generic_make_request.
Note that all the block drivers generally want request_queue or
sometimes the gendisk, so this removes a layer of indirection all
over the stack.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This helper allows looking up a partion under RCU protection without
grabbing a reference to it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The timeout handler set by blk_queue_rq_timed_out() is only used
in single queue mode. Calling this function for blk-mq drivers is
wrong. Hence issue a warning if this function is called by a blk-mq
driver.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Calling blk_start_queue() from interrupt context with the queue
lock held and without disabling IRQs, as the skd driver does, is
safe. This patch avoids that loading the skd driver triggers the
following warning:
WARNING: CPU: 11 PID: 1348 at block/blk-core.c:283 blk_start_queue+0x84/0xa0
RIP: 0010:blk_start_queue+0x84/0xa0
Call Trace:
skd_unquiesce_dev+0x12a/0x1d0 [skd]
skd_complete_internal+0x1e7/0x5a0 [skd]
skd_complete_other+0xc2/0xd0 [skd]
skd_isr_completion_posted.isra.30+0x2a5/0x470 [skd]
skd_isr+0x14f/0x180 [skd]
irq_forced_thread_fn+0x2a/0x70
irq_thread+0x144/0x1a0
kthread+0x125/0x140
ret_from_fork+0x2a/0x40
Fixes: commit a038e25364 ("[PATCH] blk_start_queue() must be called with irq disabled - add warning")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Andrew Morton <akpm@osdl.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Annotate gendisk.part_tbl and disk_part_tbl.part dereferences with
rcu_dereference_protected(). This patch does not change the behavior
of the modified code but ensures that sparse does not complain about
disk->part_tbl manipulations nor about part_tbl->part accesses.
Additionally, improve documentation of the locking requirements of
the modified functions.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This was detected by sparse.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since blk_mq_ops.reinit_request is only called from inside
blk_mq_reinit_tagset(), make this function pointer an argument of
blk_mq_reinit_tagset() instead of a member of struct blk_mq_ops.
This patch does not change any functionality but makes
blk_mq_reinit_tagset() calls easier to read and to analyze.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: James Smart <james.smart@broadcom.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This function is only used inside the block layer core. Hence
unexport it.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since patch "blk-mq: switch .queue_rq return value to blk_status_t"
.queue_rq() returns a BLK_STS_* value instead of a BLK_MQ_RQ_*
value. Hence refer to the former in comments about .queue_rq()
return values.
Fixes: commit 39a70c76b8 ("blk-mq: clarify dispatch may not be drained/blocked by stopping queue")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
While pci_irq_get_affinity should never fail for SMP kernel that
implement the affinity mapping, it will always return NULL in the
UP case, so provide a fallback mapping of all queues to CPU 0 in
that case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_mq_get_request() does not release the callers queue usage counter
when allocation fails. The caller still needs to account for its own
queue usage when it is unable to allocate a request.
Fixes: 1ad43c0078 ("blk-mq: don't leak preempt counter/q_usage_counter when allocating rq failed")
Reported-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In below scenario blkio cgroup does not work as per their assigned
weights :-
1. When the underlying device is nonrotational with a single HW queue
with depth of >= CFQ_HW_QUEUE_MIN
2. When the use case is forming two blkio cgroups cg1(weight 1000) &
cg2(wight 100) and two processes(file1 and file2) doing sync IO in
their respective blkio cgroups.
For above usecase result of fio (without this patch):-
file1: (groupid=0, jobs=1): err= 0: pid=685: Thu Jan 1 19:41:49 1970
write: IOPS=1315, BW=41.1MiB/s (43.1MB/s)(1024MiB/24906msec)
<...>
file2: (groupid=0, jobs=1): err= 0: pid=686: Thu Jan 1 19:41:49 1970
write: IOPS=1295, BW=40.5MiB/s (42.5MB/s)(1024MiB/25293msec)
<...>
// both the process BW is equal even though they belong to diff.
cgroups with weight of 1000(cg1) and 100(cg2)
In above case (for non rotational NCQ devices),
as soon as the request from cg1 is completed and even
though it is provided with higher set_slice=10, because of CFQ
algorithm when the driver tries to fetch the request, CFQ expires
this group without providing any idle time nor weight priority
and schedules another cfq group (in this case cg2).
And thus both cfq groups(cg1 & cg2) keep alternating to get the
disk time and hence loses the cgroup weight based scheduling.
Below patch gives a chance to cfq algorithm (cfq_arm_slice_timer)
to arm the slice timer in case group_idle is enabled.
In case if group_idle is also not required (including for nonrotational
NCQ drives), we need to explicitly set group_idle = 0 from sysfs for
such cases.
With this patch result of fio(for above usecase) :-
file1: (groupid=0, jobs=1): err= 0: pid=690: Thu Jan 1 00:06:08 1970
write: IOPS=1706, BW=53.3MiB/s (55.9MB/s)(1024MiB/19197msec)
<..>
file2: (groupid=0, jobs=1): err= 0: pid=691: Thu Jan 1 00:06:08 1970
write: IOPS=1043, BW=32.6MiB/s (34.2MB/s)(1024MiB/31401msec)
<..>
// In this processes BW is as per their respective cgroups weight.
Signed-off-by: Ritesh Harjani <riteshh@codeaurora.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When a queue associated with a process remains empty, there are cases
where throughput gets boosted if the device is idled to await the
arrival of a new I/O request for that queue. Currently, BFQ assumes
that one of these cases is when the device has no internal queueing
(regardless of the properties of the I/O being served). Unfortunately,
this condition has proved to be too general. So, this commit refines it
as "the device has no internal queueing and is rotational".
This refinement provides a significant throughput boost with random
I/O, on flash-based storage without internal queueing. For example, on
a HiKey board, throughput increases by up to 125%, growing, e.g., from
6.9MB/s to 15.6MB/s with two or three random readers in parallel.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The logic that decides whether to idle the device is scattered across
three functions. Almost all of the logic is in the function
bfq_bfqq_may_idle, but (1) part of the decision is made in
bfq_update_idle_window, and (2) the function bfq_bfqq_must_idle may
switch off idling regardless of the output of bfq_bfqq_may_idle. In
addition, both bfq_update_idle_window and bfq_bfqq_must_idle make
their decisions as a function of parameters that are used, for similar
purposes, also in bfq_bfqq_may_idle. This commit addresses these
issues by moving all the logic into bfq_bfqq_may_idle.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We haven't used these in years, but somehow the definitions still
remained. Kill them, and renumber the QUEUE_FLAG_ space. We had
a hole in the beginning of the space, too.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The blk_mq_delay_kick_requeue_list() function is used by the device
mapper and only by the device mapper to rerun the queue and requeue
list after a delay. This function is called once per request that
gets requeued. Modify this function such that the queue is run once
per path change event instead of once per request that is requeued.
Fixes: commit 2849450ad3 ("blk-mq: introduce blk_mq_delay_kick_requeue_list()")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This gets us back to the behavior in 4.12 and earlier.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Fixes: 7c20f116 ("bio-integrity: stop abusing bi_end_io")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In dm-integrity target we register integrity profile that have
both generate_fn and verify_fn callbacks set to NULL.
This is used if dm-integrity is stacked under a dm-crypt device
for authenticated encryption (integrity payload contains authentication
tag and IV seed).
In this case the verification is done through own crypto API
processing inside dm-crypt; integrity profile is only holder
of these data. (And memory is owned by dm-crypt as well.)
After the commit (and previous changes)
Commit 7c20f11680
Author: Christoph Hellwig <hch@lst.de>
Date: Mon Jul 3 16:58:43 2017 -0600
bio-integrity: stop abusing bi_end_io
we get this crash:
: BUG: unable to handle kernel NULL pointer dereference at (null)
: IP: (null)
: *pde = 00000000
...
:
: Workqueue: kintegrityd bio_integrity_verify_fn
: task: f48ae180 task.stack: f4b5c000
: EIP: (null)
: EFLAGS: 00210286 CPU: 0
: EAX: f4b5debc EBX: 00001000 ECX: 00000001 EDX: 00000000
: ESI: 00001000 EDI: ed25f000 EBP: f4b5dee8 ESP: f4b5dea4
: DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
: CR0: 80050033 CR2: 00000000 CR3: 32823000 CR4: 001406d0
: Call Trace:
: ? bio_integrity_process+0xe3/0x1e0
: bio_integrity_verify_fn+0xea/0x150
: process_one_work+0x1c7/0x5c0
: worker_thread+0x39/0x380
: kthread+0xd6/0x110
: ? process_one_work+0x5c0/0x5c0
: ? kthread_worker_fn+0x100/0x100
: ? kthread_worker_fn+0x100/0x100
: ret_from_fork+0x19/0x24
: Code: Bad EIP value.
: EIP: (null) SS:ESP: 0068:f4b5dea4
: CR2: 0000000000000000
Patch just skip the whole verify workqueue if verify_fn is set to NULL.
Fixes: 7c20f116 ("bio-integrity: stop abusing bi_end_io")
Signed-off-by: Milan Broz <gmazyland@gmail.com>
[hch: trivial whitespace fix]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Modify blk_mq_in_flight() to count both a partition and root at
the same time. Then we only have to call it once, instead of
potentially looping the tags twice.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't have to inc/dec some counter, since we can just
iterate the tags. That makes inc/dec a noop, but means we
have to iterate busy tags to get an in-flight count.
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of returning the count that matches the partition, pass
in an array of two ints. Index 0 will be filled with the inflight
count for the partition in question, and index 1 will filled
with the root inflight count, if the partition passed in is not the
root.
This is in preparation for being able to calculate both in one
go.
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No functional change in this patch, just in preparation for
basing the inflight mechanism on the queue in question.
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since we introduced blk-mq-sched, the tags->rqs[] array has been
dynamically assigned. So we need to check for NULL when iterating,
since there's a window of time where the bit is set, but we haven't
dynamically assigned the tags->rqs[] array position yet.
This is perfectly safe, since the memory backing of the request is
never going away while the device is alive.
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This makes the code more obvious, and moves the most likely branch first
in the function.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Like pci and virtio, we add a rdma helper for affinity
spreading. This achieves optimal mq affinity assignments
according to the underlying rdma device affinity maps.
Reviewed-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>
submit_bio_wait() does not consume bio reference. Add comment about
that.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When blk_mq_get_request() failed, preempt counter isn't
released, and blk_mq_make_request() doesn't release the counter
too.
This patch fixes the issue, and makes sure that preempt counter
is only held if rq is allocated successfully. The same policy is
applied on .q_usage_counter too.
Signed-off-by: Ming Lei <minlei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We recently had a bug in the IPR SCSI driver, where it would end up
making the SCSI mid layer run the mq hardware queue with interrupts
disabled. This isn't legal, since the software queue locking relies
on never being grabbed from interrupt context. Additionally, drivers
that set BLK_MQ_F_BLOCKING may schedule from this context.
Add a WARN_ON_ONCE() to catch bad users up front.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Groups of BFQ queues are represented by generic entities in BFQ. When
a queue belonging to a parent entity is deactivated, the parent entity
may need to be deactivated too, in case the deactivated queue was the
only active queue for the parent entity. This deactivation may need to
be propagated upwards if the entity belongs, in its turn, to a further
higher-level entity, and so on. In particular, the upward propagation
of deactivation stops at the first parent entity that remains active
even if one of its child entities has been deactivated.
To decide whether the last non-deactivation condition holds for a
parent entity, BFQ checks whether the field next_in_service is still
not NULL for the parent entity, after the deactivation of one of its
child entity. If it is not NULL, then there are certainly other active
entities in the parent entity, and deactivations can stop.
Unfortunately, this check misses a corner case: if in_service_entity
is not NULL, then next_in_service may happen to be NULL, although the
parent entity is evidently active. This happens if: 1) the entity
pointed by in_service_entity is the only active entity in the parent
entity, and 2) according to the definition of next_in_service, the
in_service_entity cannot be considered as next_in_service. See the
comments on the definition of next_in_service for details on this
second point.
Hitting the above corner case causes crashes.
To address this issue, this commit:
1) Extends the above check on only next_in_service to controlling both
next_in_service and in_service_entity (if any of them is not NULL,
then no further deactivation is performed)
2) Improves the (important) comments on how next_in_service is defined
and updated; in particular it fixes a few rather obscure paragraphs
Reported-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Reported-by: Rick Yiu <rick_yiu@htc.com>
Reported-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Tested-by: Rick Yiu <rick_yiu@htc.com>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
Tested-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
BFQ implements hierarchical scheduling by representing each group of
queues with a generic parent entity. For each parent entity, BFQ
maintains an in_service_entity pointer: if one of the child entities
happens to be in service, in_service_entity points to it. The
resetting of these pointers happens only on queue expirations: when
the in-service queue is expired, i.e., stops to be the queue in
service, BFQ resets all in_service_entity pointers along the
parent-entity path from this queue to the root entity.
Functions handling the scheduling of entities assume, naturally, that
in-service entities are active, i.e., have pending I/O requests (or,
as a special case, even if they have no pending requests, they are
expected to receive a new request very soon, with the scheduler idling
the storage device while waiting for such an event). Unfortunately,
the above resetting scheme of the in_service_entity pointers may cause
this assumption to be violated. For example, the in-service queue may
happen to remain without requests because of a request merge. In this
case the queue does become idle, and all related data structures are
updated accordingly. But in_service_entity still points to the queue
in the parent entity. This inconsistency may even propagate to
higher-level parent entities, if they happen to become idle as well,
as a consequence of the leaf queue becoming idle. For this queue and
parent entities, scheduling functions have an undefined behaviour,
and, as reported, may easily lead to kernel crashes or hangs.
This commit addresses this issue by simply resetting the
in_service_entity field also when it is detected to point to an entity
becoming idle (regardless of why the entity becomes idle).
Reported-by: Laurentiu Nicola <lnicola@dend.ro>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently cfq/bfq/blk-throttle output cgroup info in trace in their own
way. Now we have standard blktrace API for this, so convert them to use
it.
Note, this changes the behavior a little bit. cgroup info isn't output
by default, we only do this with 'blk_cgroup' option enabled. cgroup
info isn't output as a string by default too, we only do this with
'blk_cgname' option enabled. Also cgroup info is output in different
position of the note string. I think these behavior changes aren't a big
issue (actually we make trace data shorter which is good), since the
blktrace note is solely for debugging.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blkcg_bio_issue_check() already gets blkcg for a BIO.
bio_associate_blkcg() uses a percpu refcounter, so it's a very cheap
operation. There is no point we don't attach the cgroup info into bio at
blkcg_bio_issue_check. This also makes blktrace outputs correct cgroup
info.
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We already do this for PCI mappings, and the higher level code now
expects that CPU on/offlining doesn't have an affect on the queue
mappings.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The blk-mq code lacks support for looking at the rpm_status field, tracking
active requests and the RQF_PM flag.
Due to the default switch to blk-mq for scsi people start to run into
suspend / resume issue due to this fact, so make sure we disable the runtime
PM functionality until it is properly implemented.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Presently, the order of the block devices listed in /proc/devices is not
entirely sequential. If a block device has a major number greater than
BLKDEV_MAJOR_HASH_SIZE (255), it will be ordered as if its major were
module 255. For example, 511 appears after 1.
This patch cleans that up and prints each major number in the correct
order, regardless of where they are stored in the hash table.
In order to do this, we introduce BLKDEV_MAJOR_MAX as an artificial
limit (chosen to be 512). It will then print all devices in major
order number from 0 to the maximum.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jeff Layton <jlayton@poochiereds.net>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There are mq devices (eg., virtio-blk, nbd and loopback) which don't
invoke blk_mq_run_hw_queues() after the completion of a request.
If bfq is enabled on these devices and the slice_idle attribute or
strict_guarantees attribute is set as zero, it is possible that
after a request completion the remaining requests of busy bfq queue
will stalled in the bfq schedule until a new request arrives.
To fix the scheduler latency problem, we need to check whether or not
all issued requests have completed and dispatch more requests to driver
if there is no request in driver.
The problem can be reproduced by running the following script
on a virtio-blk device with nr_hw_queues as 1:
#!/bin/sh
dev=vdb
# mount point for dev
mp=/tmp/mnt
cd $mp
job=strict.job
cat <<EOF > $job
[global]
direct=1
bs=4k
size=256M
rw=write
ioengine=libaio
iodepth=128
runtime=5
time_based
[1]
filename=1.data
[2]
new_group
filename=2.data
EOF
echo bfq > /sys/block/$dev/queue/scheduler
echo 1 > /sys/block/$dev/queue/iosched/strict_guarantees
fio $job
Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The start time of eligible entity should be less than or equal to
the current virtual time, and the entity in idle tree has a finish
time being greater than the current virtual time.
Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull more block updates from Jens Axboe:
"This is a followup for block changes, that didn't make the initial
pull request. It's a bit of a mixed bag, this contains:
- A followup pull request from Sagi for NVMe. Outside of fixups for
NVMe, it also includes a series for ensuring that we properly
quiesce hardware queues when browsing live tags.
- Set of integrity fixes from Dmitry (mostly), fixing various issues
for folks using DIF/DIX.
- Fix for a bug introduced in cciss, with the req init changes. From
Christoph.
- Fix for a bug in BFQ, from Paolo.
- Two followup fixes for lightnvm/pblk from Javier.
- Depth fix from Ming for blk-mq-sched.
- Also from Ming, performance fix for mtip32xx that was introduced
with the dynamic initialization of commands"
* 'for-linus' of git://git.kernel.dk/linux-block: (44 commits)
block: call bio_uninit in bio_endio
nvmet: avoid unneeded assignment of submit_bio return value
nvme-pci: add module parameter for io queue depth
nvme-pci: compile warnings in nvme_alloc_host_mem()
nvmet_fc: Accept variable pad lengths on Create Association LS
nvme_fc/nvmet_fc: revise Create Association descriptor length
lightnvm: pblk: remove unnecessary checks
lightnvm: pblk: control I/O flow also on tear down
cciss: initialize struct scsi_req
null_blk: fix error flow for shared tags during module_init
block: Fix __blkdev_issue_zeroout loop
nvme-rdma: unconditionally recycle the request mr
nvme: split nvme_uninit_ctrl into stop and uninit
virtio_blk: quiesce/unquiesce live IO when entering PM states
mtip32xx: quiesce request queues to make sure no submissions are inflight
nbd: quiesce request queues to make sure no submissions are inflight
nvme: kick requeue list when requeueing a request instead of when starting the queues
nvme-pci: quiesce/unquiesce admin_q instead of start/stop its hw queues
nvme-loop: quiesce/unquiesce admin_q instead of start/stop its hw queues
nvme-fc: quiesce/unquiesce admin_q instead of start/stop its hw queues
...
bio_free isn't a good place to free cgroup info. There are a
lot of cases bio is allocated in special way (for example, in stack) and
never gets called by bio_put hence bio_free, we are leaking memory. This
patch moves the free to bio endio, which should be called anyway. The
bio_uninit call in bio_free is kept, in case the bio never gets called
bio endio.
This assumes ->bi_end_io() doesn't access cgroup info, which seems true
in my audit.
This along with Christoph's integrity patch should fix the memory leak
issue.
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull misc compat stuff updates from Al Viro:
"This part is basically untangling various compat stuff. Compat
syscalls moved to their native counterparts, getting rid of quite a
bit of double-copying and/or set_fs() uses. A lot of field-by-field
copyin/copyout killed off.
- kernel/compat.c is much closer to containing just the
copyin/copyout of compat structs. Not all compat syscalls are gone
from it yet, but it's getting there.
- ipc/compat_mq.c killed off completely.
- block/compat_ioctl.c cleaned up; floppy compat ioctls moved to
drivers/block/floppy.c where they belong. Yes, there are several
drivers that implement some of the same ioctls. Some are m68k and
one is 32bit-only pmac. drivers/block/floppy.c is the only one in
that bunch that can be built on biarch"
* 'misc.compat' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
mqueue: move compat syscalls to native ones
usbdevfs: get rid of field-by-field copyin
compat_hdio_ioctl: get rid of set_fs()
take floppy compat ioctls to sodding floppy.c
ipmi: get rid of field-by-field __get_user()
ipmi: get COMPAT_IPMICTL_RECEIVE_MSG in sync with the native one
rt_sigtimedwait(): move compat to native
select: switch compat_{get,put}_fd_set() to compat_{get,put}_bitmap()
put_compat_rusage(): switch to copy_to_user()
sigpending(): move compat to native
getrlimit()/setrlimit(): move compat to native
times(2): move compat to native
compat_{get,put}_bitmap(): use unsafe_{get,put}_user()
fb_get_fscreeninfo(): don't bother with do_fb_ioctl()
do_sigaltstack(): lift copying to/from userland into callers
take compat_sys_old_getrlimit() to native syscall
trim __ARCH_WANT_SYS_OLD_GETRLIMIT
The BIO issuing loop in __blkdev_issue_zeroout() is allocating BIOs
with a maximum number of bvec (pages) equal to
min(nr_sects, (sector_t)BIO_MAX_PAGES)
This works since the requested number of bvecs will always be limited
to the absolute maximum number supported (BIO_MAX_PAGES), but this is
ineficient as too many bvec entries may be requested due to the
different units being used in the min() operation (number of sectors vs
number of pages).
To fix this, introduce the helper __blkdev_sectors_to_bio_pages() to
correctly calculate the number of bvecs for zeroout BIOs as the issuing
loop progresses. The calculation is done using consistent units and
makes sure that the number of pages return is at least 1 (for cases
where the number of sectors is less that the number of sectors in
a page).
Also remove a trailing space after the bit shift in the internal loop
min() call.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
block/bio-integrity.c:318:10-11: WARNING: return of 0/1 in function 'bio_integrity_prep' with return type bool
Return statements in functions returning bool should use
true/false instead of 1/0.
Generated by: scripts/coccinelle/misc/boolreturn.cocci
Fixes: e23947bd76 ("bio-integrity: fold bio_integrity_enabled to bio_integrity_prep")
CC: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull irq updates from Thomas Gleixner:
"The irq department delivers:
- Expand the generic infrastructure handling the irq migration on CPU
hotplug and convert X86 over to it. (Thomas Gleixner)
Aside of consolidating code this is a preparatory change for:
- Finalizing the affinity management for multi-queue devices. The
main change here is to shut down interrupts which are affine to a
outgoing CPU and reenabling them when the CPU comes online again.
That avoids moving interrupts pointlessly around and breaking and
reestablishing affinities for no value. (Christoph Hellwig)
Note: This contains also the BLOCK-MQ and NVME changes which depend
on the rework of the irq core infrastructure. Jens acked them and
agreed that they should go with the irq changes.
- Consolidation of irq domain code (Marc Zyngier)
- State tracking consolidation in the core code (Jeffy Chen)
- Add debug infrastructure for hierarchical irq domains (Thomas
Gleixner)
- Infrastructure enhancement for managing generic interrupt chips via
devmem (Bartosz Golaszewski)
- Constification work all over the place (Tobias Klauser)
- Two new interrupt controller drivers for MVEBU (Thomas Petazzoni)
- The usual set of fixes, updates and enhancements all over the
place"
* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (112 commits)
irqchip/or1k-pic: Fix interrupt acknowledgement
irqchip/irq-mvebu-gicp: Allocate enough memory for spi_bitmap
irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity
nvme: Allocate queues for all possible CPUs
blk-mq: Create hctx for each present CPU
blk-mq: Include all present CPUs in the default queue mapping
genirq: Avoid unnecessary low level irq function calls
genirq: Set irq masked state when initializing irq_desc
genirq/timings: Add infrastructure for estimating the next interrupt arrival time
genirq/timings: Add infrastructure to track the interrupt timings
genirq/debugfs: Remove pointless NULL pointer check
irqchip/gic-v3-its: Don't assume GICv3 hardware supports 16bit INTID
irqchip/gic-v3-its: Add ACPI NUMA node mapping
irqchip/gic-v3-its-platform-msi: Make of_device_ids const
irqchip/gic-v3-its: Make of_device_ids const
irqchip/irq-mvebu-icu: Add new driver for Marvell ICU
irqchip/irq-mvebu-gicp: Add new driver for Marvell GICP
dt-bindings/interrupt-controller: Add DT binding for the Marvell ICU
genirq/irqdomain: Remove auto-recursive hierarchy support
irqchip/MSI: Use irq_domain_update_bus_token instead of an open coded access
...
And instead call directly into the integrity code from bio_end_io.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently ->verify_fn not woks at all because at the moment it is called
bio->bi_iter.bi_size == 0, so we do not iterate integrity bvecs at all.
In order to perform verification we need to know original data vector,
with new bvec rewind API this is trivial.
testcase: 3c6509eaa8
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
[hch: adopted for new status values]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently all integrity prep hooks are open-coded, and if prepare fails
we ignore it's code and fail bio with EIO. Let's return real error to
upper layer, so later caller may react accordingly.
In fact no one want to use bio_integrity_prep() w/o bio_integrity_enabled,
so it is reasonable to fold it in to one function.
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
[hch: merged with the latest block tree,
return bool from bio_integrity_prep]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
bio_integrity_trim inherent it's interface from bio_trim and accept
offset and size, but this API is error prone because data offset
must always be insync with bio's data offset. That is why we have
integrity update hook in bio_advance()
So only meaningful values are: offset == 0, sectors == bio_sectors(bio)
Let's just remove them completely.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
SCSI drivers do care about bip_seed so we must update it accordingly.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When mq-deadline is taken, IOPS of sequential read and
seqential write is observed more than 20% drop on sata(scsi-mq)
devices, compared with using 'none' scheduler.
The reason is that the default nr_requests for scheduler is
too big for small queuedepth devices, and latency is increased
much.
Since the principle of taking 256 requests for mq scheduler
is based on 128 queue depth, this patch changes into
double size of min(hw queue_depth, 128).
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
On each deactivation or re-scheduling (after being served) of a
bfq_queue, BFQ invokes the function __bfq_entity_update_weight_prio(),
to perform pending updates of ioprio, weight and ioprio class for the
bfq_queue. BFQ also invokes this function on I/O-request dispatches,
to raise or lower weights more quickly when needed, thereby improving
latency. However, the entity representing the bfq_queue may be on the
active (sub)tree of a service tree when this happens, and, although
with a very low probability, the bfq_queue may happen to also have a
pending change of its ioprio class. If both conditions hold when
__bfq_entity_update_weight_prio() is invoked, then the entity moves to
a sort of hybrid state: the new service tree for the entity, as
returned by bfq_entity_service_tree(), differs from service tree on
which the entity still is. The functions that handle activations and
deactivations of entities do not cope with such a hybrid state (and
would need to become more complex to cope).
This commit addresses this issue by just making
__bfq_entity_update_weight_prio() not perform also a possible pending
change of ioprio class, when invoked on an I/O-request dispatch for a
bfq_queue. Such a change is thus postponed to when
__bfq_entity_update_weight_prio() is invoked on deactivation or
re-scheduling of the bfq_queue.
Reported-by: Marco Piazza <mpiazza@gmail.com>
Reported-by: Laurentiu Nicola <lnicola@dend.ro>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle were:
- Add the SYSTEM_SCHEDULING bootup state to move various scheduler
debug checks earlier into the bootup. This turns silent and
sporadically deadly bugs into nice, deterministic splats. Fix some
of the splats that triggered. (Thomas Gleixner)
- A round of restructuring and refactoring of the load-balancing and
topology code (Peter Zijlstra)
- Another round of consolidating ~20 of incremental scheduler code
history: this time in terms of wait-queue nomenclature. (I didn't
get much feedback on these renaming patches, and we can still
easily change any names I might have misplaced, so if anyone hates
a new name, please holler and I'll fix it.) (Ingo Molnar)
- sched/numa improvements, fixes and updates (Rik van Riel)
- Another round of x86/tsc scheduler clock code improvements, in hope
of making it more robust (Peter Zijlstra)
- Improve NOHZ behavior (Frederic Weisbecker)
- Deadline scheduler improvements and fixes (Luca Abeni, Daniel
Bristot de Oliveira)
- Simplify and optimize the topology setup code (Lauro Ramos
Venancio)
- Debloat and decouple scheduler code some more (Nicolas Pitre)
- Simplify code by making better use of llist primitives (Byungchul
Park)
- ... plus other fixes and improvements"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
sched/cputime: Refactor the cputime_adjust() code
sched/debug: Expose the number of RT/DL tasks that can migrate
sched/numa: Hide numa_wake_affine() from UP build
sched/fair: Remove effective_load()
sched/numa: Implement NUMA node level wake_affine()
sched/fair: Simplify wake_affine() for the single socket case
sched/numa: Override part of migrate_degrades_locality() when idle balancing
sched/rt: Move RT related code from sched/core.c to sched/rt.c
sched/deadline: Move DL related code from sched/core.c to sched/deadline.c
sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled
sched/fair: Spare idle load balancing on nohz_full CPUs
nohz: Move idle balancer registration to the idle path
sched/loadavg: Generalize "_idle" naming to "_nohz"
sched/core: Drop the unused try_get_task_struct() helper function
sched/fair: WARN() and refuse to set buddy when !se->on_rq
sched/debug: Fix SCHED_WARN_ON() to return a value on !CONFIG_SCHED_DEBUG as well
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
sched/wait: Move bit_wait_table[] and related functionality from sched/core.c to sched/wait_bit.c
sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>
sched/wait: Re-adjust macro line continuation backslashes in <linux/wait.h>
...
Pull core block/IO updates from Jens Axboe:
"This is the main pull request for the block layer for 4.13. Not a huge
round in terms of features, but there's a lot of churn related to some
core cleanups.
Note this depends on the UUID tree pull request, that Christoph
already sent out.
This pull request contains:
- A series from Christoph, unifying the error/stats codes in the
block layer. We now use blk_status_t everywhere, instead of using
different schemes for different places.
- Also from Christoph, some cleanups around request allocation and IO
scheduler interactions in blk-mq.
- And yet another series from Christoph, cleaning up how we handle
and do bounce buffering in the block layer.
- A blk-mq debugfs series from Bart, further improving on the support
we have for exporting internal information to aid debugging IO
hangs or stalls.
- Also from Bart, a series that cleans up the request initialization
differences across types of devices.
- A series from Goldwyn Rodrigues, allowing the block layer to return
failure if we will block and the user asked for non-blocking.
- Patch from Hannes for supporting setting loop devices block size to
that of the underlying device.
- Two series of patches from Javier, fixing various issues with
lightnvm, particular around pblk.
- A series from me, adding support for write hints. This comes with
NVMe support as well, so applications can help guide data placement
on flash to improve performance, latencies, and write
amplification.
- A series from Ming, improving and hardening blk-mq support for
stopping/starting and quiescing hardware queues.
- Two pull requests for NVMe updates. Nothing major on the feature
side, but lots of cleanups and bug fixes. From the usual crew.
- A series from Neil Brown, greatly improving the bio rescue set
support. Most notably, this kills the bio rescue work queues, if we
don't really need them.
- Lots of other little bug fixes that are all over the place"
* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
lightnvm: pblk: set line bitmap check under debug
lightnvm: pblk: verify that cache read is still valid
lightnvm: pblk: add initialization check
lightnvm: pblk: remove target using async. I/Os
lightnvm: pblk: use vmalloc for GC data buffer
lightnvm: pblk: use right metadata buffer for recovery
lightnvm: pblk: schedule if data is not ready
lightnvm: pblk: remove unused return variable
lightnvm: pblk: fix double-free on pblk init
lightnvm: pblk: fix bad le64 assignations
nvme: Makefile: remove dead build rule
blk-mq: map all HWQ also in hyperthreaded system
nvmet-rdma: register ib_client to not deadlock in device removal
nvme_fc: fix error recovery on link down.
nvmet_fc: fix crashes on bad opcodes
nvme_fc: Fix crash when nvme controller connection fails.
nvme_fc: replace ioabort msleep loop with completion
nvme_fc: fix double calls to nvme_cleanup_cmd()
nvme-fabrics: verify that a controller returns the correct NQN
nvme: simplify nvme_dev_attrs_are_visible
...
- introduce the new uuid_t/guid_t types that are going to replace
the somewhat confusing uuid_be/uuid_le types and make the terminology
fit the various specs, as well as the userspace libuuid library.
(me, based on a previous version from Amir)
- consolidated generic uuid/guid helper functions lifted from XFS
and libnvdimm (Amir and me)
- conversions to the new types and helpers (Amir, Andy and me)
-----BEGIN PGP SIGNATURE-----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=J/4P
-----END PGP SIGNATURE-----
Merge tag 'uuid-for-4.13' of git://git.infradead.org/users/hch/uuid
Pull uuid subsystem from Christoph Hellwig:
"This is the new uuid subsystem, in which Amir, Andy and I have started
consolidating our uuid/guid helpers and improving the types used for
them. Note that various other subsystems have pulled in this tree, so
I'd like it to go in early.
UUID/GUID summary:
- introduce the new uuid_t/guid_t types that are going to replace the
somewhat confusing uuid_be/uuid_le types and make the terminology
fit the various specs, as well as the userspace libuuid library.
(me, based on a previous version from Amir)
- consolidated generic uuid/guid helper functions lifted from XFS and
libnvdimm (Amir and me)
- conversions to the new types and helpers (Amir, Andy and me)"
* tag 'uuid-for-4.13' of git://git.infradead.org/users/hch/uuid: (34 commits)
ACPI: hns_dsaf_acpi_dsm_guid can be static
mmc: sdhci-pci: make guid intel_dsm_guid static
uuid: Take const on input of uuid_is_null() and guid_is_null()
thermal: int340x_thermal: fix compile after the UUID API switch
thermal: int340x_thermal: Switch to use new generic UUID API
acpi: always include uuid.h
ACPI: Switch to use generic guid_t in acpi_evaluate_dsm()
ACPI / extlog: Switch to use new generic UUID API
ACPI / bus: Switch to use new generic UUID API
ACPI / APEI: Switch to use new generic UUID API
acpi, nfit: Switch to use new generic UUID API
MAINTAINERS: add uuid entry
tmpfs: generate random sb->s_uuid
scsi_debug: switch to uuid_t
nvme: switch to uuid_t
sysctl: switch to use uuid_t
partitions/ldm: switch to use uuid_t
overlayfs: use uuid_t instead of uuid_be
fs: switch ->s_uuid to uuid_t
ima/policy: switch to use uuid_t
...
This patch performs sequential mapping between CPUs and queues.
In case the system has more CPUs than HWQs then there are still
CPUs to map to HWQs. In hyperthreaded system, map the unmapped CPUs
and their siblings to the same HWQ.
This actually fixes a bug that found unmapped HWQs in a system with
2 sockets, 18 cores per socket, 2 threads per core (total 72 CPUs)
running NVMEoF (opens upto maximum of 64 HWQs).
Performance results running fio (72 jobs, 128 iodepth)
using null_blk (w/w.o patch):
bs IOPS(read submit_queues=72) IOPS(write submit_queues=72) IOPS(read submit_queues=24) IOPS(write submit_queues=24)
----- ---------------------------- ------------------------------ ---------------------------- -----------------------------
512 4890.4K/4723.5K 4524.7K/4324.2K 4280.2K/4264.3K 3902.4K/3909.5K
1k 4910.1K/4715.2K 4535.8K/4309.6K 4296.7K/4269.1K 3906.8K/3914.9K
2k 4906.3K/4739.7K 4526.7K/4330.6K 4301.1K/4262.4K 3890.8K/3900.1K
4k 4918.6K/4730.7K 4556.1K/4343.6K 4297.6K/4264.5K 3886.9K/3893.9K
8k 4906.4K/4748.9K 4550.9K/4346.7K 4283.2K/4268.8K 3863.4K/3858.2K
16k 4903.8K/4782.6K 4501.5K/4233.9K 4292.3K/4282.3K 3773.1K/3773.5K
32k 4885.8K/4782.4K 4365.9K/4184.2K 4307.5K/4289.4K 3780.3K/3687.3K
64k 4822.5K/4762.7K 2752.8K/2675.1K 4308.8K/4312.3K 2651.5K/2655.7K
128k 2388.5K/2313.8K 1391.9K/1375.7K 2142.8K/2152.2K 1395.5K/1374.2K
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Wen reports significant memory leaks with DIF and O_DIRECT:
"With nvme devive + T10 enabled, On a system it has 256GB and started
logging /proc/meminfo & /proc/slabinfo for every minute and in an hour
it increased by 15968128 kB or ~15+GB.. Approximately 256 MB / minute
leaking.
/proc/meminfo | grep SUnreclaim...
SUnreclaim: 6752128 kB
SUnreclaim: 6874880 kB
SUnreclaim: 7238080 kB
....
SUnreclaim: 22307264 kB
SUnreclaim: 22485888 kB
SUnreclaim: 22720256 kB
When testcases with T10 enabled call into __blkdev_direct_IO_simple,
code doesn't free memory allocated by bio_integrity_alloc. The patch
fixes the issue. HTX has been run with +60 hours without failure."
Since __blkdev_direct_IO_simple() allocates the bio on the stack, it
doesn't go through the regular bio free. This means that any ancillary
data allocated with the bio through the stack is not freed. Hence, we
can leak the integrity data associated with the bio, if the device is
using DIF/DIX.
Fix this by providing a bio_uninit() and export it, so that we can use
it to free this data. Note that this is a minimal fix for this issue.
Any current user of bio's that are allocated outside of
bio_alloc_bioset() suffers from this issue, most notably some drivers.
We will fix those in a more comprehensive patch for 4.13. This also
means that the commit marked as being fixed by this isn't the real
culprit, it's just the most obvious one out there.
Fixes: 542ff7bf18 ("block: new direct I/O implementation")
Reported-by: Wen Xiong <wenxiong@linux.vnet.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we only create hctx for online CPUs, which can lead to a lot
of churn due to frequent soft offline / online operations. Instead
allocate one for each present CPU to avoid this and dramatically simplify
the code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: Keith Busch <keith.busch@intel.com>
Cc: linux-block@vger.kernel.org
Cc: linux-nvme@lists.infradead.org
Link: http://lkml.kernel.org/r/20170626102058.10200-3-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This commit fixes a bug triggered by a non-trivial sequence of
events. These events are briefly described in the next two
paragraphs. The impatiens, or those who are familiar with queue
merging and splitting, can jump directly to the last paragraph.
On each I/O-request arrival for a shared bfq_queue, i.e., for a
bfq_queue that is the result of the merge of two or more bfq_queues,
BFQ checks whether the shared bfq_queue has become seeky (i.e., if too
many random I/O requests have arrived for the bfq_queue; if the device
is non rotational, then random requests must be also small for the
bfq_queue to be tagged as seeky). If the shared bfq_queue is actually
detected as seeky, then a split occurs: the bfq I/O context of the
process that has issued the request is redirected from the shared
bfq_queue to a new non-shared bfq_queue. As a degenerate case, if the
shared bfq_queue actually happens to be shared only by one process
(because of previous splits), then no new bfq_queue is created: the
state of the shared bfq_queue is just changed from shared to non
shared.
Regardless of whether a brand new non-shared bfq_queue is created, or
the pre-existing shared bfq_queue is just turned into a non-shared
bfq_queue, several parameters of the non-shared bfq_queue are set
(restored) to the original values they had when the bfq_queue
associated with the bfq I/O context of the process (that has just
issued an I/O request) was merged with the shared bfq_queue. One of
these parameters is the weight-raising state.
If, on the split of a shared bfq_queue,
1) a pre-existing shared bfq_queue is turned into a non-shared
bfq_queue;
2) the previously shared bfq_queue happens to be busy;
3) the weight-raising state of the previously shared bfq_queue happens
to change;
the number of weight-raised busy queues changes. The field
wr_busy_queues must then be updated accordingly, but such an update
was missing. This commit adds the missing update.
Reported-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead move it to the callers. Those that either don't use bio_data() or
page_address() or are specific to architectures that do not support highmem
are skipped.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
And just move it into scsi_transport_sas which needs it due to low-level
drivers directly derferencing bio_data, and into blk_init_queue_node,
which will need a further push into the callers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For historical reasons we default to bouncing highmem pages for all block
queues. But the blk-mq drivers are easy to audit to ensure that we don't
need this - scsi and mtip32xx set explicit limits and everyone else doesn't
have any particular ones.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We only call blk_queue_bounce for request-based drivers, so stop messing
with it for make_request based drivers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Only used inside the bounce code, and opencoding it makes it more obvious
what is going on.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This makes moves the knowledge about bouncing out of the callers into the
block core (just like we do for the normal I/O path), and allows to unexport
blk_queue_bounce.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Useful to verify that things are working the way they should.
Reading the file will return number of kb written with each
write hint. Writing the file will reset the statistics. No care
is taken to ensure that we don't race on updates.
Drivers will write to q->write_hints[] if they handle a given
write hint.
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No functional changes in this patch, we just use up some holes
in the bio and request structures to define a write hint that
we psas down the stack.
Ensure that we don't merge requests that have different life time
hints assigned to them, and that we inherit the write hint when
cloning a bio.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull in the fix for shared tags, as it conflicts with the pending
changes in for-4.13/block. We already pulled in v4.12-rc5 to solve
other conflicts or get fixes that went into 4.12, so not a lot
of changes in this merge.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
hwctx's queue_num has been set prior call blk_mq_init_hctx, so no need
set it again.
Signed-off-by: weiping <zhangweiping@didichuxing.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since blk_mq_quiesce_queue_nowait() can be called from interrupt
context, make this safe. Since this function is not in the hot
path, uninline it.
Fixes: commit f4560ffe8c ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This was detected by the smatch static analyzer.
Fixes: commit 2a842acab1 ("block: introduce new block status code type")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Avoid that building with W=1 causes the compiler to complain that
a declaration for bounce_bio_set and bounce_bio_split is missing.
References: commit a8821f3f32 ("block: Improvements to bounce-buffer handling")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Neil Brown <neilb@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch suppresses gcc 7 warnings about falling through in switch
statements when building with W=1. From the gcc documentation: The
-Wimplicit-fallthrough=3 warning is enabled by -Wextra. See also
https://gcc.gnu.org/onlinedocs/gcc-7.1.0/gcc/Warning-Options.html.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we have shared tags enabled, then every IO completion will trigger
a full loop of every queue belonging to a tag set, and every hardware
queue for each of those queues, even if nothing needs to be done.
This causes a massive performance regression if you have a lot of
shared devices.
Instead of doing this huge full scan on every IO, add an atomic
counter to the main queue that tracks how many hardware queues have
been marked as needing a restart. With that, we can avoid looking for
restartable queues, if we don't have to.
Max reports that this restores performance. Before this patch, 4K
IOPS was limited to 22-23K IOPS. With the patch, we are running at
950-970K IOPS.
Fixes: 6d8c6c0f97 ("blk-mq: Restart a single queue if tag sets are shared")
Reported-by: Max Gurtovoy <maxg@mellanox.com>
Tested-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Tested-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A queue must be frozen while the mapped state of a hardware queue
is changed. Additionally, any change of the mapped state is
followed by a call to blk_mq_map_swqueue() (see also
blk_mq_init_allocated_queue() and blk_mq_update_nr_hw_queues()).
Since blk_mq_map_swqueue() does not map any unmapped hardware
queue onto any software queue, no attempt will be made to run
an unmapped hardware queue. Hence issue a warning upon attempts
to run an unmapped hardware queue.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The variable 'disk_type' is never modified so constify it.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Document the locking assumptions in functions that modify
blk_mq_ctx.rq_list to make it easier for humans to verify
this code.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some functions in block/blk-core.c must only be used on blk-sq queues
while others are safe to use against any queue type. Document which
functions are intended for blk-sq queues and issue a warning if the
blk-sq API is misused. This does not only help block driver authors
but will also make it easier to remove the blk-sq code once that code
is declared obsolete.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of documenting the locking assumptions of most block layer
functions as a comment, use lockdep_assert_held() to verify locking
assumptions at runtime.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Initialization of blk-mq requests is a bit weird: blk_mq_rq_ctx_init()
is called after a value has been assigned to .rq_flags and .rq_flags
is initialized in __blk_mq_finish_request(). Initialize .rq_flags in
blk_mq_rq_ctx_init() instead of relying on __blk_mq_finish_request().
Moving the initialization of .rq_flags is fine because all changes
and tests of .rq_flags occur between blk_get_request() and finishing
a request.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since scsi_req_init() works on a struct scsi_request, change the
argument type into struct scsi_request *.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of explicitly calling scsi_req_init() after blk_get_request(),
call that function from inside blk_get_request(). Add an
.initialize_rq_fn() callback function to the block drivers that need
it. Merge the IDE .init_rq_fn() function into .initialize_rq_fn()
because it is too small to keep it as a separate function. Keep the
scsi_req_init() call in ide_prep_sense() because it follows a
blk_rq_init() call.
References: commit 82ed4db499 ("block: split scsi_request out of struct request")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Several block drivers need to initialize the driver-private request
data after having called blk_get_request() and before .prep_rq_fn()
is called, e.g. when submitting a REQ_OP_SCSI_* request. Avoid that
that initialization code has to be repeated after every
blk_get_request() call by adding new callback functions to struct
request_queue and to struct blk_mq_ops.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of declaring the second argument of blk_*_get_request()
as int and passing it to functions that expect an unsigned int,
declare that second argument as unsigned int. Also because of
consistency, rename that second argument from 'rw' into 'op'.
This patch does not change any functionality.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since the srcu structure is rather large (184 bytes on an x86-64
system with kernel debugging disabled), only allocate it if needed.
Reported-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A new bio operation flag REQ_NOWAIT is introduced to identify bio's
orignating from iocb with IOCB_NOWAIT. This flag indicates
to return immediately if a request cannot be made instead
of retrying.
Stacked devices such as md (the ones with make_request_fn hooks)
currently are not supported because it may block for housekeeping.
For example, an md can have a part of the device suspended.
For this reason, only request based devices are supported.
In the future, this feature will be expanded to stacked devices
by teaching them how to handle the REQ_NOWAIT flags.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Rename:
wait_queue_t => wait_queue_entry_t
'wait_queue_t' was always a slight misnomer: its name implies that it's a "queue",
but in reality it's a queue *entry*. The 'real' queue is the wait queue head,
which had to carry the name.
Start sorting this out by renaming it to 'wait_queue_entry_t'.
This also allows the real structure name 'struct __wait_queue' to
lose its double underscore and become 'struct wait_queue_entry',
which is the more canonical nomenclature for such data types.
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch reverts commit 2719aa217e0d02(blk-mq: don't use
sync workqueue flushing from drivers) because only
blk_mq_quiesce_queue() need the sync flush, and now
we don't need to stop queue any more, so revert it.
Also changes to cancel_delayed_work() in blk_mq_stop_hw_queue().
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
BLK_MQ_S_STOPPED may not be observed in other concurrent I/O paths,
we can't guarantee that dispatching won't happen after returning
from the APIs of stopping queue.
So clarify the fact and avoid potential misuse.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Queue can be started by other blk-mq APIs and can be used in
different cases, this limits uses of blk_mq_quiesce_queue()
if it is based on stopping queue, and make its usage very
difficult, especially users have to use the stop queue APIs
carefully for avoiding to break blk_mq_quiesce_queue().
We have applied the QUIESCED flag for draining and blocking
dispatch, so it isn't necessary to stop queue any more.
After stopping queue is removed, blk_mq_quiesce_queue() can
be used safely and easily, then users won't worry about queue
restarting during quiescing at all.
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Actually what we want to get from blk_mq_quiesce_queue()
isn't only to wait for completion of all ongoing .queue_rq().
In the typical context of canceling requests, we need to
make sure that the following is done in the dispatch path
before starting to cancel requests:
- failed dispatched request is finished
- busy dispatched request is requeued, and the STARTED
flag is cleared
So update comment to keep code, doc and our expection consistent.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It is required that no dispatch can happen any more once
blk_mq_quiesce_queue() returns, and we don't have such requirement
on APIs of stopping queue.
But blk_mq_quiesce_queue() still may not block/drain dispatch in the
the case of BLK_MQ_S_START_ON_RUN, so use the new introduced flag of
QUEUE_FLAG_QUIESCED and evaluate it inside RCU read-side critical
sections for fixing this issue.
Also blk_mq_quiesce_queue() is implemented via stopping queue, which
limits its uses, and easy to cause race, because any queue restart in
other paths may break blk_mq_quiesce_queue(). With the introduced
flag of QUEUE_FLAG_QUIESCED, we don't need to depend on stopping queue
for quiescing any more.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_mq_start_stopped_hw_queues() is used implictly
as counterpart of blk_mq_quiesce_queue() for unquiescing queue,
so we introduce blk_mq_unquiesce_queue() and make it
as counterpart of blk_mq_quiesce_queue() explicitly.
This function is for improving the current quiescing mechanism
in the following patches.
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_bio_segment_split() makes sure bios have no more than
BIO_MAX_PAGES entries in the bi_io_vec.
This was done because bio_clone_bioset() (when given a
mempool bioset) could not handle larger io_vecs.
No driver uses bio_clone_bioset() any more, they all
use bio_clone_fast() if anything, and bio_clone_fast()
doesn't clone the bi_io_vec.
The main user of of bio_clone_bioset() at this level
is bounce.c, and bouncing now happens before blk_bio_segment_split(),
so that is not of concern.
So remove the big helpful comment and the code.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
bio_clone() is no longer used.
Only bio_clone_bioset() or bio_clone_fast().
This is for the best, as bio_clone() used fs_bio_set,
and filesystems are unlikely to want to use bio_clone().
So remove bio_clone() and all references.
This includes a fix to some incorrect documentation.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since commit 23688bf4f8 ("block: ensure to split after potentially
bouncing a bio") blk_queue_bounce() is called *before*
blk_queue_split().
This means that:
1/ the comments blk_queue_split() about bounce buffers are
irrelevant, and
2/ a very large bio (more than BIO_MAX_PAGES) will no longer be
split before it arrives at blk_queue_bounce(), leading to the
possibility that bio_clone_bioset() will fail and a NULL
will be dereferenced.
Separately, blk_queue_bounce() shouldn't use fs_bio_set as the bio
being copied could be from the same set, and this could lead to a
deadlock.
So:
- allocate 2 private biosets for blk_queue_bounce, one for
splitting enormous bios and one for cloning bios.
- add code to split a bio that exceeds BIO_MAX_PAGES.
- Fix up the comments in blk_queue_split()
Credit-to: Ming Lei <tom.leiming@gmail.com> (suggested using single bio_for_each_segment loop)
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A rescuing bioset is only useful if there might be bios from
that same bioset on the bio_list_on_stack queue at a time
when bio_alloc_bioset() is called. This never applies to
q->bio_split.
Allocations from q->bio_split are only ever made from
blk_queue_split() which is only ever called early in each of
various make_request_fn()s. The original bio (call this A)
is then passed to generic_make_request() and is placed on
the bio_list_on_stack queue, and the bio that was allocated
from q->bio_split (B) is processed.
The processing of this may cause other bios to be passed to
generic_make_request() or may even cause the bio B itself to
be passed, possible after some prefix has been split off
(using some other bioset).
generic_make_request() now guarantees that all of these bios
(B and dependants) will be fully processed before the tail
of the original bio A gets handled. None of these early bios
can possible trigger an allocation from the original
q->bio_split as they are either too small to require
splitting or (more likely) are destined for a different queue.
The next time that the original q->bio_split might be used
by this thread is when A is processed again, as it might
still be too big to handle directly. By this time there
cannot be any other bios allocated from q->bio_split in the
generic_make_request() queue. So no rescuing will ever be
needed.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch converts bioset_create() to not create a workqueue by
default, so alloctions will never trigger punt_bios_to_rescuer(). It
also introduces a new flag BIOSET_NEED_RESCUER which tells
bioset_create() to preserve the old behavior.
All callers of bioset_create() that are inside block device drivers,
are given the BIOSET_NEED_RESCUER flag.
biosets used by filesystems or other top-level users do not
need rescuing as the bio can never be queued behind other
bios. This includes fs_bio_set, blkdev_dio_pool,
btrfs_bioset, xfs_ioend_bioset, and one allocated by
target_core_iblock.c.
biosets used by md/raid do not need rescuing as
their usage was recently audited and revised to never
risk deadlock.
It is hoped that most, if not all, of the remaining biosets
can end up being the non-rescued version.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Credit-to: Ming Lei <ming.lei@redhat.com> (minor fixes)
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
"flags" arguments are often seen as good API design as they allow
easy extensibility.
bioset_create_nobvec() is implemented internally as a variation in
flags passed to __bioset_create().
To support future extension, make the internal structure part of the
API.
i.e. add a 'flags' argument to bioset_create() and discard
bioset_create_nobvec().
Note that the bio_split allocations in drivers/md/raid* do not need
the bvec mempool - they should have used bioset_create_nobvec().
Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_queue_split() is always called with the last arg being q->bio_split,
where 'q' is the first arg.
Also blk_queue_split() sometimes uses the passed-in 'bs' and sometimes uses
q->bio_split.
This is inconsistent and unnecessary. Remove the last arg and always use
q->bio_split inside blk_queue_split()
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Credit-to: Javier González <jg@lightnvm.io> (Noticed that lightnvm was missed)
Reviewed-by: Javier González <javier@cnexlabs.com>
Tested-by: Javier González <javier@cnexlabs.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Move most code into blk_mq_rq_ctx_init, and the rest into
blk_mq_get_request.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch makes sure we always allocate requests in the core blk-mq
code and use a common prepare_request method to initialize them for
both mq I/O schedulers. For Kyber and additional limit_depth method
is added that is called before allocating the request.
Also because none of the intializations can really fail the new method
does not return an error - instead the bfq finish method is hardened
to deal with the no-IOC case.
Last but not least this removes the abuse of RQF_QUEUE by the blk-mq
scheduling code as RQF_ELFPRIV is all that is needed now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_mq_sched_assign_ioc now only handles the assigned of the ioc if
the schedule needs it (bfq only at the moment). The caller to the
per-request initializer is moved out so that it can be merged with
a similar call for the kyber I/O scheduler.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
icq_to_bic is a container_of operation, so we need to check for NULL
before it. Also move the check outside the spinlock while we're at
it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Merge three functions only tail-called by blk_mq_free_request into
blk_mq_free_request.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Having these as separate helpers in a header really does not help
readability, or my chances to refactor this code sanely.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Having them out of line in blk-mq-sched.c just makes the code flow
unnecessarily complicated.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull NVMe changes for 4.13 from Christoph:
Highlights:
- UUID identifier support from Johannes
- Lots of cleanups from Sagi
- Host Memory Buffer support from me
And lots of cleanups and smaller fixes of course.
Note that the UUID identifier changes are based on top of the uuid tree.
I am the maintainer of that tree and will send it to Linus as soon as
4.12 is released as various other trees depend on it as well (and the
diffstat includes those changes unfortunately)
This patch fixes two sparse warnings introduced by the "dedicated
error codes for the block layer V3" patch series. These changes
have not been tested.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Avoid that the following complaint is reported:
BUG: sleeping function called from invalid context at kernel/workqueue.c:2790
in_atomic(): 1, irqs_disabled(): 0, pid: 41, name: rcuop/3
1 lock held by rcuop/3/41:
#0: (rcu_callback){......}, at: [<ffffffff8111f9a2>] rcu_nocb_kthread+0x282/0x500
Call Trace:
dump_stack+0x86/0xcf
___might_sleep+0x174/0x260
__might_sleep+0x4a/0x80
flush_work+0x7e/0x2e0
__cancel_work_timer+0x143/0x1c0
cancel_work_sync+0x10/0x20
blk_throtl_exit+0x25/0x60
blkcg_exit_queue+0x35/0x40
blk_release_queue+0x42/0x130
kobject_put+0xa9/0x190
This happens since we invoke callbacks that need to block from the
queue release handler. Fix this by pushing the final release to
a workqueue.
Reported-by: Ross Zwisler <zwisler@gmail.com>
Fixes: commit b425e50492 ("block: Avoid that blk_exit_rl() triggers a use-after-free")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Tested-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Updated changelog
Signed-off-by: Jens Axboe <axboe@fb.com>
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJZPdbLAAoJEHm+PkMAQRiGx4wH/1nCjfnl6fE8oJ24/1gEAOUh
biFdqJkYZmlLYHVtYfLm4Ueg4adJdg0wx6qM/4RaAzmQVvLfDV34bc1qBf1+P95G
kVF+osWyXrZo5cTwkwapHW/KNu4VJwAx2D1wrlxKDVG5AOrULH1pYOYGOpApEkZU
4N+q5+M0ce0GJpqtUZX+UnI33ygjdDbBxXoFKsr24B7eA0ouGbAJ7dC88WcaETL+
2/7tT01SvDMo0jBSV0WIqlgXwZ5gp3yPGnklC3F4159Yze6VFrzHMKS/UpPF8o8E
W9EbuzwxsKyXUifX2GY348L1f+47glen/1sedbuKnFhP6E9aqUQQJXvEO7ueQl4=
=m2Gx
-----END PGP SIGNATURE-----
Merge tag 'v4.12-rc5' into for-4.13/block
We've already got a few conflicts and upcoming work depends on some of the
changes that have gone into mainline as regression fixes for this series.
Pull in 4.12-rc5 to resolve these conflicts and make it easier on down stream
trees to continue working on 4.13 changes.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Replace bi_error with a new bi_status to allow for a clear conversion.
Note that device mapper overloaded bi_error with a private value, which
we'll have to keep arround at least for now and thus propagate to a
proper blk_status_t value.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Use the same values for use for request completion errors as the return
value from ->queue_rq. BLK_STS_RESOURCE is special cased to cause
a requeue, and all the others are completed as-is.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Currently we use nornal Linux errno values in the block layer, and while
we accept any error a few have overloaded magic meanings. This patch
instead introduces a new blk_status_t value that holds block layer specific
status codes and explicitly explains their meaning. Helpers to convert from
and to the previous special meanings are provided for now, but I suspect
we want to get rid of them in the long run - those drivers that have a
errno input (e.g. networking) usually get errnos that don't know about
the special block layer overloads, and similarly returning them to userspace
will usually return somethings that strictly speaking isn't correct
for file system operations, but that's left as an exercise for later.
For now the set of errors is a very limited set that closely corresponds
to the previous overloaded errno values, but there is some low hanging
fruite to improve it.
blk_status_t (ab)uses the sparse __bitwise annotations to allow for sparse
typechecking, so that we can easily catch places passing the wrong values.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
In blk-cgroup, operations on blkg objects are protected with the
request_queue lock. This is no more the lock that protects
I/O-scheduler operations in blk-mq. In fact, the latter are now
protected with a finer-grained per-scheduler-instance lock. As a
consequence, although blkg lookups are also rcu-protected, blk-mq I/O
schedulers may see inconsistent data when they access blkg and
blkg-related objects. BFQ does access these objects, and does incur
this problem, in the following case.
The blkg_lookup performed in bfq_get_queue, being protected (only)
through rcu, may happen to return the address of a copy of the
original blkg. If this is the case, then the blkg_get performed in
bfq_get_queue, to pin down the blkg, is useless: it does not prevent
blk-cgroup code from destroying both the original blkg and all objects
directly or indirectly referred by the copy of the blkg. BFQ accesses
these objects, which typically causes a crash for NULL-pointer
dereference of memory-protection violation.
Some additional protection mechanism should be added to blk-cgroup to
address this issue. In the meantime, this commit provides a quick
temporary fix for BFQ: cache (when safe) blkg data that might
disappear right after a blkg_lookup.
In particular, this commit exploits the following facts to achieve its
goal without introducing further locks. Destroy operations on a blkg
invoke, as a first step, hooks of the scheduler associated with the
blkg. And these hooks are executed with bfqd->lock held for BFQ. As a
consequence, for any blkg associated with the request queue an
instance of BFQ is attached to, we are guaranteed that such a blkg is
not destroyed, and that all the pointers it contains are consistent,
while that instance is holding its bfqd->lock. A blkg_lookup performed
with bfqd->lock held then returns a fully consistent blkg, which
remains consistent until this lock is held. In more detail, this holds
even if the returned blkg is a copy of the original one.
Finally, also the object describing a group inside BFQ needs to be
protected from destruction on the blkg_free of the original blkg
(which invokes bfq_pd_free). This commit adds private refcounting for
this object, to let it disappear only after no bfq_queue refers to it
any longer.
This commit also removes or updates some stale comments on locking
issues related to blk-cgroup operations.
Reported-by: Tomas Konir <tomas.konir@gmail.com>
Reported-by: Lee Tibbert <lee.tibbert@gmail.com>
Reported-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Tomas Konir <tomas.konir@gmail.com>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
hard disk IO latency varies a lot depending on spindle move. The latency
range could be from several microseconds to several milliseconds. It's
pretty hard to get the baseline latency used by io.low.
We will use a different stragety here. The idea is only using IO with
spindle move to determine if cgroup IO is in good state. For HD, if io
latency is small (< 1ms), we ignore the IO. Such IO is likely from
sequential IO, and is helpless to help determine if a cgroup's IO is
impacted by other cgroups. With this, we only account IO with big
latency. Then we can choose a hardcoded baseline latency for HD (4ms,
which is typical IO latency with seek). With all these settings, the
io.low latency works for both HD and SSD.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
I have encountered a NULL pointer dereference in
throtl_schedule_pending_timer:
[ 413.735396] BUG: unable to handle kernel NULL pointer dereference at 0000000000000038
[ 413.735535] IP: [<ffffffff812ebbbf>] throtl_schedule_pending_timer+0x3f/0x210
[ 413.735643] PGD 22c8cf067 PUD 22cb34067 PMD 0
[ 413.735713] Oops: 0000 [#1] SMP
......
This is caused by the following case:
blk_throtl_bio
throtl_schedule_next_dispatch <= sq is top level one without parent
throtl_schedule_pending_timer
sq_to_tg(sq)->td->throtl_slice <= sq_to_tg(sq) returns NULL
Fix it by using sq_to_td instead of sq_to_tg(sq)->td, which will always
return a valid td.
Fixes: 297e3d8547 ("blk-throttle: make throtl_slice tunable")
Signed-off-by: Joseph Qi <qijiang.qj@alibaba-inc.com>
Reviewed-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When direct issue is done on request picked up from plug list,
the hctx need to be updated with the actual hw queue, otherwise
wrong hctx is used and may hurt performance, especially when
wrong SRCU readlock is acquired/released
Reported-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
And the uuid helpers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Since BSG only supports request queues for which struct scsi_request
is the first member of their private request data, refuse to register
block layer queues for which struct scsi_request is not the first
member of their private data.
References: commit bd1599d931 ("scsi_transport_sas: fix BSG ioctl memory corruption")
References: commit 82ed4db499 ("block: split scsi_request out of struct request")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
From the context where a SCSI command is submitted it is not always
possible to figure out whether or not the queue the command is
submitted to has struct scsi_request as the first member of its
private data. Hence introduce the flag QUEUE_FLAG_SCSI_PASSTHROUGH.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Don Brace <don.brace@microsemi.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Running a queue causes the block layer to examine the per-CPU and
hw queues but not the requeue list. Hence add a 'kick' operation
that also examines the requeue list.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Eduardo Valentin <eduval@amazon.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Requests that got stuck in a block driver are neither on
blk_mq_ctx.rq_list nor on any hw dispatch queue. Make these
visible in debugfs through the "busy" attribute.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Eduardo Valentin <eduval@amazon.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When verifying whether or not a blk-mq driver forgot to kick the
requeue list after having requeued a request it is important to
be able to verify the contents of the requeue list. Hence export
that list through debugfs.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Eduardo Valentin <eduval@amazon.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When analyzing e.g. queue lockups it is important to know whether
or not a request has already been started. Hence also show the
atomic request flags.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Eduardo Valentin <eduval@amazon.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
When adding a cfq_group into the cfq service tree, we use CFQ_IDLE_DELAY
as the delay of cfq_group's vdisktime if there have been other cfq_groups
already.
When cfq is under iops mode, commit 9a7f38c42c ("cfq-iosched: Convert
from jiffies to nanoseconds") could result in a large iops delay and
lead to an abnormal io schedule delay for the added cfq_group. To fix
it, we just need to revert to the old CFQ_IDLE_DELAY value: HZ / 5
when iops mode is enabled.
Despite having the same value, the delay of a cfq_queue in idle class
and the delay of cfq_group are different things, so I define two new
macros for the delay of a cfq_group under time-slice mode and iops mode.
Fixes: 9a7f38c42c ("cfq-iosched: Convert from jiffies to nanoseconds")
Cc: <stable@vger.kernel.org> # 4.8+
Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
The tagset lock needs to be held when iterating the tag_list, so a
lockdep assert was added when updating number of hardware queues. The
drivers calling this API, however, were unaware of the new requirement,
so are failing the assertion.
This patch takes the lock within the blk-mq function so the drivers do
not have to be modified in order to be safe.
Fixes: 705cda97e ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list")
Reported-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This fixes the following warning when building with clang:
block/cfq-iosched.c:970:19: error: unused function 'min_vdisktime'
[-Werror,-Wunused-function]
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
Because what the per-sw-queue bio merge does is basically same with
scheduler's .bio_merge(), this patch makes per-sw-queue bio merge
as the default .bio_merge if no scheduler is used or io scheduler
doesn't provide .bio_merge().
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Before blk-mq is introduced, I/O is merged to elevator
before being putted into plug queue, but blk-mq changed the
order and makes merging to sw queue basically impossible.
Then it is observed that throughput of sequential I/O is degraded
about 10%~20% on virtio-blk in the test[1] if mq-deadline isn't used.
This patch moves the bio merging per sw queue before plugging,
like what blk_queue_bio() does, and the performance regression is
fixed under this situation.
[1]. test script:
sudo fio --direct=1 --size=128G --bsrange=4k-4k --runtime=40 --numjobs=16 --ioengine=libaio --iodepth=64 --group_reporting=1 --filename=/dev/vdb --name=virtio_blk-test-$RW --rw=$RW --output-format=json
RW=read or write
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Christoph writes:
"A couple of fixes for the next rc on the nvme front. Various FC fixes
from James, controller removal fixes from Ming (including a block layer
patch), a APST related device quirk from Andy, a RDMA fix for small
queue depth device from Marta, as well as fixes for the lack of
metadata support in non-PCIe drivers and the printk logging format from
me."
The code in blk-mq-debugfs.c assumes that it is working on a blk-mq
queue and is not intended to work on a blk-sq queue. Hence only
register blk-mq debugfs attributes for blk-mq queues.
Fixes: commit 9c1051aacd ("blk-mq: untangle debugfs and sysfs")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The code in block/partitions/msdos.c recognizes FreeBSD, OpenBSD
and NetBSD partitions and does a reasonable job picking out OpenBSD
and NetBSD UFS subpartitions.
But for FreeBSD the subpartitions are always "bad".
Kernel: <bsd:bad subpartition - ignored
Though all 3 of these BSD systems use UFS as a file system, only
FreeBSD uses relative start addresses in the subpartition
declarations.
The following patch fixes this for FreeBSD partitions and leaves
the code for OpenBSD and NetBSD intact:
Signed-off-by: Richard Narron <comet.berkeley@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
We don't set an error code on this path. It means that we return NULL
instead of an error pointer and the caller does a NULL dereference.
Fixes: 6d1d8050b4 ("block, partition: add partition_meta_info to hd_struct")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Default value of io.low limit is 0. If user doesn't configure the limit,
last patch makes cgroup be throttled to very tiny bps/iops, which could
stall the system. A cgroup with default settings of io.low limit really
means nothing, so we force user to configure all settings, otherwise
io.low limit doesn't take effect. With this stragety, default setting of
latency/idle isn't important, so just set them to very conservative and
safe value.
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
If a cgroup with low limit 0 for both bps/iops, the cgroup's low limit
is ignored and we throttle the cgroup with its max limit. In this way,
other cgroups with a low limit will not get protected. To fix this, we
don't do the exception any more. cgroup will be throttled to a limit 0
if it uese default setting. To avoid completed stall, we give such
cgroup tiny IO resources.
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
These info are important to understand what's happening and help debug.
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
For idle time, children's setting should not be bigger than parent's.
For latency target, children's setting should not be smaller than
parent's. The leaf nodes will adjust their settings according to the
hierarchy and compare their IO with the settings and do
upgrade/downgrade. parents nodes don't need to track their IO
latency/idle time.
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
No one uses it any more, so remove it.
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Pull libnvdimm fixes from Dan Williams:
"Incremental fixes and a small feature addition on top of the main
libnvdimm 4.12 pull request:
- Geert noticed that tinyconfig was bloated by BLOCK selecting DAX.
The size regression is fixed by moving all dax helpers into the
dax-core and only specifying "select DAX" for FS_DAX and
dax-capable drivers. He also asked for clarification of the
NR_DEV_DAX config option which, on closer look, does not need to be
a config option at all. Mike also throws in a DEV_DAX_PMEM fixup
for good measure.
- Ben's attention to detail on -stable patch submissions caught a
case where the recent fixes to arch_copy_from_iter_pmem() missed a
condition where we strand dirty data in the cache. This is tagged
for -stable and will also be included in the rework of the pmem api
to a proposed {memcpy,copy_user}_flushcache() interface for 4.13.
- Vishal adds a feature that missed the initial pull due to pending
review feedback. It allows the kernel to clear media errors when
initializing a BTT (atomic sector update driver) instance on a pmem
namespace.
- Ross noticed that the dax_device + dax_operations conversion broke
__dax_zero_page_range(). The nvdimm unit tests fail to check this
path, but xfstests immediately trips over it. No excuse for missing
this before submitting the 4.12 pull request.
These all pass the nvdimm unit tests and an xfstests spot check. The
set has received a build success notification from the kbuild robot"
* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
filesystem-dax: fix broken __dax_zero_page_range() conversion
libnvdimm, btt: ensure that initializing metadata clears poison
libnvdimm: add an atomic vs process context flag to rw_bytes
x86, pmem: Fix cache flushing for iovec write < 8 bytes
device-dax: kill NR_DEV_DAX
block, dax: move "select DAX" from BLOCK to FS_DAX
device-dax: Tell kbuild DEV_DAX_PMEM depends on DEV_DAX
SCSI devices can return short writes on Write Same just like for normal
writes, so we need to handle this case for our special payload requests
as well.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Tested-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When formatting NVMe to 512B/4K + T10 DIf/DIX, dd with split op returns
"Input/output error". Looks block layer split the bio after calling
bio_integrity_prep(bio). This patch fixes the issue.
Below is how we debug this issue:
(1)format nvme to 4K block # size with type 2 DIF
(2)dd with block size bigger than 1024k.
oflag=direct
dd: error writing '/dev/nvme0n1': Input/output error
We added some debug code in nvme device driver. It showed us the first
op and the second op have the same bi and pi address. This is not
correct.
1st op: nvme0n1 Op:Wr slba 0x505 length 0x100, PI ctrl=0x1400,
dsmgmt=0x0, AT=0x0 & RT=0x505
Guard 0x00b1, AT 0x0000, RT physical 0x00000505 RT virtual 0x00002828
2nd op: nvme0n1 Op:Wr slba 0x605 length 0x1, PI ctrl=0x1400, dsmgmt=0x0,
AT=0x0 & RT=0x605 ==> This op fails and subsequent 5 retires..
Guard 0x00b1, AT 0x0000, RT physical 0x00000605 RT virtual 0x00002828
With the fix, It showed us both of the first op and the second op have
correct bi and pi address.
1st op: nvme2n1 Op:Wr slba 0x505 length 0x100, PI ctrl=0x1400,
dsmgmt=0x0, AT=0x0 & RT=0x505
Guard 0x5ccb, AT 0x0000, RT physical 0x00000505 RT virtual
0x00002828
2nd op: nvme2n1 Op:Wr slba 0x605 length 0x1, PI ctrl=0x1400, dsmgmt=0x0,
AT=0x0 & RT=0x605
Guard 0xab4c, AT 0x0000, RT physical 0x00000605 RT virtual
0x00003028
Signed-off-by: Wen Xiong <wenxiong@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If PREEMPT_RCU is enabled, rcu_read_lock() isn't strong enough
for us to use this_cpu_ptr() in that section. Use the safer
get/put_cpu_ptr() variants instead.
Reported-by: Mike Galbraith <efault@gmx.de>
Fixes: 34dbad5d26 ("blk-stat: convert to callback-based statistics reporting")
Signed-off-by: Jens Axboe <axboe@fb.com>
We warn twice for switching to a scheduler, if that switch fails.
As we also report the failure in the return value to the
sysfs write, remove the dmesg induced failures.
Keep the failure print for warning to switch to the kconfig
selected IO scheduler, as we can't report errors for that in
any other way.
Signed-off-by: Jens Axboe <axboe@fb.com>
The introduction of the BFQ and Kyber I/O schedulers has triggered a
new wave of I/O benchmarks. Unfortunately, comments and discussions on
these benchmarks confirm that there is still little awareness that it
is very hard to achieve, at the same time, a low latency and a high
throughput. In particular, virtually all benchmarks measure
throughput, or throughput-related figures of merit, but, for BFQ, they
use the scheduler in its default configuration. This configuration is
geared, instead, toward a low latency. This is evidently a sign that
BFQ documentation is still too unclear on this important aspect. This
commit addresses this issue by stressing how BFQ configuration must be
(easily) changed if the only goal is maximum throughput.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
In the function __bfq_deactivate_entity, the pointer
entity->sched_data could happen to be used before being properly
initialized. This led to a NULL pointer dereference. This commit fixes
this bug by just using this pointer only where it is safe to do so.
Reported-by: Tom Harrison <l12436.tw@gmail.com>
Tested-by: Tom Harrison <l12436.tw@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
For configurations that do not enable DAX filesystems or drivers, do not
require the DAX core to be built.
Given that the 'direct_access' method has been removed from
'block_device_operations', we can also go ahead and remove the
block-related dax helper functions from fs/block_dev.c to
drivers/dax/super.c. This keeps dax details out of the block layer and
lets the DAX core be built as a module in the FS_DAX=n case.
Filesystems need to include dax.h to call bdev_dax_supported().
Cc: linux-xfs@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Darrick J. Wong" <darrick.wong@oracle.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.com>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Making __blk_mq_stop_hw_queues static fixes sparse warning:
block/blk-mq.c:6: warning: symbol '__blk_mq_stop_hw_queues' was not
declared. Should it be static?
Fixes: 2719aa217e ("blk-mq: don't use sync workqueue flushing from drivers")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This can be triggered by hot-unplug one cpu.
======================================================
[ INFO: possible circular locking dependency detected ]
4.11.0+ #17 Not tainted
-------------------------------------------------------
step_after_susp/2640 is trying to acquire lock:
(all_q_mutex){+.+...}, at: [<ffffffffb33f95b8>] blk_mq_queue_reinit_work+0x18/0x110
but task is already holding lock:
(cpu_hotplug.lock){+.+.+.}, at: [<ffffffffb306d04f>] cpu_hotplug_begin+0x7f/0xe0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (cpu_hotplug.lock){+.+.+.}:
lock_acquire+0x11c/0x230
__mutex_lock+0x92/0x990
mutex_lock_nested+0x1b/0x20
get_online_cpus+0x64/0x80
blk_mq_init_allocated_queue+0x3a0/0x4e0
blk_mq_init_queue+0x3a/0x60
loop_add+0xe5/0x280
loop_init+0x124/0x177
do_one_initcall+0x53/0x1c0
kernel_init_freeable+0x1e3/0x27f
kernel_init+0xe/0x100
ret_from_fork+0x31/0x40
-> #0 (all_q_mutex){+.+...}:
__lock_acquire+0x189a/0x18a0
lock_acquire+0x11c/0x230
__mutex_lock+0x92/0x990
mutex_lock_nested+0x1b/0x20
blk_mq_queue_reinit_work+0x18/0x110
blk_mq_queue_reinit_dead+0x1c/0x20
cpuhp_invoke_callback+0x1f2/0x810
cpuhp_down_callbacks+0x42/0x80
_cpu_down+0xb2/0xe0
freeze_secondary_cpus+0xb6/0x390
suspend_devices_and_enter+0x3b3/0xa40
pm_suspend+0x129/0x490
state_store+0x82/0xf0
kobj_attr_store+0xf/0x20
sysfs_kf_write+0x45/0x60
kernfs_fop_write+0x135/0x1c0
__vfs_write+0x37/0x160
vfs_write+0xcd/0x1d0
SyS_write+0x58/0xc0
do_syscall_64+0x8f/0x710
return_from_SYSCALL_64+0x0/0x7a
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(cpu_hotplug.lock);
lock(all_q_mutex);
lock(cpu_hotplug.lock);
lock(all_q_mutex);
*** DEADLOCK ***
8 locks held by step_after_susp/2640:
#0: (sb_writers#6){.+.+.+}, at: [<ffffffffb3244aed>] vfs_write+0x1ad/0x1d0
#1: (&of->mutex){+.+.+.}, at: [<ffffffffb32d3a51>] kernfs_fop_write+0x101/0x1c0
#2: (s_active#166){.+.+.+}, at: [<ffffffffb32d3a59>] kernfs_fop_write+0x109/0x1c0
#3: (pm_mutex){+.+...}, at: [<ffffffffb30d2ecd>] pm_suspend+0x21d/0x490
#4: (acpi_scan_lock){+.+.+.}, at: [<ffffffffb34dc3d7>] acpi_scan_lock_acquire+0x17/0x20
#5: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffffb306d6d7>] freeze_secondary_cpus+0x27/0x390
#6: (cpu_hotplug.dep_map){++++++}, at: [<ffffffffb306cfd5>] cpu_hotplug_begin+0x5/0xe0
#7: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffffb306d04f>] cpu_hotplug_begin+0x7f/0xe0
stack backtrace:
CPU: 3 PID: 2640 Comm: step_after_susp Not tainted 4.11.0+ #17
Hardware name: Dell Inc. OptiPlex 7040/0JCTF8, BIOS 1.4.9 09/12/2016
Call Trace:
dump_stack+0x99/0xce
print_circular_bug+0x1fa/0x270
__lock_acquire+0x189a/0x18a0
lock_acquire+0x11c/0x230
? lock_acquire+0x11c/0x230
? blk_mq_queue_reinit_work+0x18/0x110
? blk_mq_queue_reinit_work+0x18/0x110
__mutex_lock+0x92/0x990
? blk_mq_queue_reinit_work+0x18/0x110
? kmem_cache_free+0x2cb/0x330
? anon_transport_class_unregister+0x20/0x20
? blk_mq_queue_reinit_work+0x110/0x110
mutex_lock_nested+0x1b/0x20
? mutex_lock_nested+0x1b/0x20
blk_mq_queue_reinit_work+0x18/0x110
blk_mq_queue_reinit_dead+0x1c/0x20
cpuhp_invoke_callback+0x1f2/0x810
? __flow_cache_shrink+0x160/0x160
cpuhp_down_callbacks+0x42/0x80
_cpu_down+0xb2/0xe0
freeze_secondary_cpus+0xb6/0x390
suspend_devices_and_enter+0x3b3/0xa40
? rcu_read_lock_sched_held+0x79/0x80
pm_suspend+0x129/0x490
state_store+0x82/0xf0
kobj_attr_store+0xf/0x20
sysfs_kf_write+0x45/0x60
kernfs_fop_write+0x135/0x1c0
__vfs_write+0x37/0x160
? rcu_read_lock_sched_held+0x79/0x80
? rcu_sync_lockdep_assert+0x2f/0x60
? __sb_start_write+0xd9/0x1c0
? vfs_write+0x1ad/0x1d0
vfs_write+0xcd/0x1d0
SyS_write+0x58/0xc0
? rcu_read_lock_sched_held+0x79/0x80
do_syscall_64+0x8f/0x710
? trace_hardirqs_on_thunk+0x1a/0x1c
entry_SYSCALL64_slow_path+0x25/0x25
The cpu hotplug path will hold cpu_hotplug.lock and then reinit all exiting
queues for blk mq w/ all_q_mutex, however, blk_mq_init_allocated_queue() will
contend these two locks in the inversion order. This is due to commit eabe06595d
(blk/mq: Cure cpu hotplug lock inversion), it fixes a cpu hotplug lock inversion
issue because of hotplug rework, however the hotplug rework is still work-in-progress
and lives in a -tip branch and mainline cannot yet trigger that splat. The commit
breaks the linus's tree in the merge window, so this patch reverts the lock order
and avoids to splat linus's tree.
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull block fixes and updates from Jens Axboe:
"Some fixes and followup features/changes that should go in, in this
merge window. This contains:
- Two fixes for lightnvm from Javier, fixing problems in the new code
merge previously in this merge window.
- A fix from Jan for the backing device changes, fixing an issue in
NFS that causes a failure to mount on certain setups.
- A change from Christoph, cleaning up the blk-mq init and exit
request paths.
- Remove elevator_change(), which is now unused. From Bart.
- A fix for queue operation invocation on a dead queue, from Bart.
- A series fixing up mtip32xx for blk-mq scheduling, removing a
bandaid we previously had in place for this. From me.
- A regression fix for this series, fixing a case where we wait on
workqueue flushing from an invalid (non-blocking) context. From me.
- A fix/optimization from Ming, ensuring that we don't both quiesce
and freeze a queue at the same time.
- A fix from Peter on lock ordering for CPU hotplug. Not a real
problem right now, but will be once the CPU hotplug rework goes in.
- A series from Omar, cleaning up out blk-mq debugfs support, and
adding support for exporting info from schedulers in debugfs as
well. This is really useful in debugging stalls or livelocks. From
Omar"
* 'for-linus' of git://git.kernel.dk/linux-block: (28 commits)
mq-deadline: add debugfs attributes
kyber: add debugfs attributes
blk-mq-debugfs: allow schedulers to register debugfs attributes
blk-mq: untangle debugfs and sysfs
blk-mq: move debugfs declarations to a separate header file
blk-mq: Do not invoke queue operations on a dead queue
blk-mq-debugfs: get rid of a bunch of boilerplate
blk-mq-debugfs: rename hw queue directories from <n> to hctx<n>
blk-mq-debugfs: don't open code strstrip()
blk-mq-debugfs: error on long write to queue "state" file
blk-mq-debugfs: clean up flag definitions
blk-mq-debugfs: separate flags with |
nfs: Fix bdi handling for cloned superblocks
block/mq: Cure cpu hotplug lock inversion
lightnvm: fix bad back free on error path
lightnvm: create cmd before allocating request
blk-mq: don't use sync workqueue flushing from drivers
mtip32xx: convert internal commands to regular block infrastructure
mtip32xx: cleanup internal tag assumptions
block: don't call blk_mq_quiesce_queue() after queue is frozen
...
* Region media error reporting: A libnvdimm region device is the parent
to one or more namespaces. To date, media errors have been reported via
the "badblocks" attribute attached to pmem block devices for namespaces
in "raw" or "memory" mode. Given that namespaces can be in "device-dax"
or "btt-sector" mode this new interface reports media errors
generically, i.e. independent of namespace modes or state. This
subsequently allows userspace tooling to craft "ACPI 6.1 Section
9.20.7.6 Function Index 4 - Clear Uncorrectable Error" requests and
submit them via the ioctl path for NVDIMM root bus devices.
* Introduce 'struct dax_device' and 'struct dax_operations': Prompted by
a request from Linus and feedback from Christoph this allows for dax
capable drivers to publish their own custom dax operations. This fixes
the broken assumption that all dax operations are related to a
persistent memory device, and makes it easier for other architectures
and platforms to add customized persistent memory support.
* 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
available for storage appliance applications to manually trigger memory
controllers to drain write-pending buffers that would otherwise be
flushed automatically by the platform ADR (asynchronous-DRAM-refresh)
mechanism at a power loss event. Support for "locked" DIMMs is included
to prevent namespaces from surfacing when the namespace label data area
is locked. Finally, fixes for various reported deadlocks and crashes,
also tagged for -stable.
* ACPI / nfit driver updates: General updates of the nfit driver to add
DSM command overrides, ACPI 6.1 health state flags support, DSM payload
debug available by default, and various fixes.
Acknowledgements that came after the branch was pushed:
commmit 565851c972 "device-dax: fix sysfs attribute deadlock"
Tested-by: Yi Zhang <yizhan@redhat.com>
commit 23f4984483 "libnvdimm: rework region badblocks clearing"
Tested-by: Toshi Kani <toshi.kani@hpe.com>
-----BEGIN PGP SIGNATURE-----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=Ox0s
-----END PGP SIGNATURE-----
Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams:
"The bulk of this has been in multiple -next releases. There were a few
late breaking fixes and small features that got added in the last
couple days, but the whole set has received a build success
notification from the kbuild robot.
Change summary:
- Region media error reporting: A libnvdimm region device is the
parent to one or more namespaces. To date, media errors have been
reported via the "badblocks" attribute attached to pmem block
devices for namespaces in "raw" or "memory" mode. Given that
namespaces can be in "device-dax" or "btt-sector" mode this new
interface reports media errors generically, i.e. independent of
namespace modes or state.
This subsequently allows userspace tooling to craft "ACPI 6.1
Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error"
requests and submit them via the ioctl path for NVDIMM root bus
devices.
- Introduce 'struct dax_device' and 'struct dax_operations': Prompted
by a request from Linus and feedback from Christoph this allows for
dax capable drivers to publish their own custom dax operations.
This fixes the broken assumption that all dax operations are
related to a persistent memory device, and makes it easier for
other architectures and platforms to add customized persistent
memory support.
- 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
available for storage appliance applications to manually trigger
memory controllers to drain write-pending buffers that would
otherwise be flushed automatically by the platform ADR
(asynchronous-DRAM-refresh) mechanism at a power loss event.
Support for "locked" DIMMs is included to prevent namespaces from
surfacing when the namespace label data area is locked. Finally,
fixes for various reported deadlocks and crashes, also tagged for
-stable.
- ACPI / nfit driver updates: General updates of the nfit driver to
add DSM command overrides, ACPI 6.1 health state flags support, DSM
payload debug available by default, and various fixes.
Acknowledgements that came after the branch was pushed:
- commmit 565851c972 "device-dax: fix sysfs attribute deadlock":
Tested-by: Yi Zhang <yizhan@redhat.com>
- commit 23f4984483 "libnvdimm: rework region badblocks clearing"
Tested-by: Toshi Kani <toshi.kani@hpe.com>"
* tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits)
libnvdimm, pfn: fix 'npfns' vs section alignment
libnvdimm: handle locked label storage areas
libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED
brd: fix uninitialized use of brd->dax_dev
block, dax: use correct format string in bdev_dax_supported
device-dax: fix sysfs attribute deadlock
libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking"
libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering
libnvdimm: rework region badblocks clearing
acpi, nfit: kill ACPI_NFIT_DEBUG
libnvdimm: fix clear length of nvdimm_forget_poison()
libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify
libnvdimm, region: sysfs trigger for nvdimm_flush()
libnvdimm: fix phys_addr for nvdimm_clear_poison
x86, dax, pmem: remove indirection around memcpy_from_pmem()
block: remove block_device_operations ->direct_access()
block, dax: convert bdev_dax_supported() to dax_direct_access()
filesystem-dax: convert to dax_direct_access()
Revert "block: use DAX for partition table reads"
ext2, ext4, xfs: retrieve dax_device for iomap operations
...
Expose the fifo lists, cached next requests, batching state, and
dispatch list. It'd also be possible to add the sorted lists, but there
aren't already seq_file helpers for rbtrees.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This provides the infrastructure for schedulers to expose their internal
state through debugfs. We add a list of queue attributes and a list of
hctx attributes to struct elevator_type and wire them up when switching
schedulers.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Add missing seq_file.h header in blk-mq-debugfs.h
Signed-off-by: Jens Axboe <axboe@fb.com>
Originally, I tied debugfs registration/unregistration together with
sysfs. There's no reason to do this, and it's getting in the way of
letting schedulers define their own debugfs attributes. Instead, tie the
debugfs registration to the lifetime of the structures themselves.
The saner lifetimes mean we can also get rid of the extra mq directory
and move everything one level up. I.e., nvme0n1/mq/hctx0/tags is now
just nvme0n1/hctx0/tags.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
In commit e869b5462f ("blk-mq: Unregister debugfs attributes
earlier"), we shuffled the debugfs cleanup around so that the "state"
attribute was removed before we freed the blk-mq data structures.
However, later changes are going to undo that, so we need to explicitly
disallow running a dead queue.
[Omar: rebased and updated commit message]
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A large part of blk-mq-debugfs.c is file_operations and seq_file
boilerplate. This sucks as is but will suck even more when schedulers
can define their own debugfs entries. Factor it all out into a single
blk_mq_debugfs_fops which multiplexes as needed. We store the
request_queue, blk_mq_hw_ctx, or blk_mq_ctx in the parent directory
dentry, which is kind of hacky, but it works.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
It's not clear what these numbered directories represent unless you
consult the code. We're about to get rid of the intermediate "mq"
directory, so these would be even more confusing without that context.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Slightly more readable, plus we also strip leading spaces.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_queue_flags_store() currently truncates and returns a short write if
the operation being written is too long. This can give us weird results,
like here:
$ echo "run bar"
echo: write error: invalid argument
$ dmesg
[ 1103.075435] blk_queue_flags_store: unsupported operation bar. Use either 'run' or 'start'
Instead, return an error if the user does this. While we're here, make
the argument names consistent with everywhere else in this file.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Make sure the spelled out flag names match the definition. This also
adds a missing hctx state, BLK_MQ_S_START_ON_RUN, and a missing
cmd_flag, __REQ_NOUNMAP.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This reads more naturally than spaces.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A previous commit introduced the sync flush, which we need from
internal callers like blk_mq_quiesce_queue(). However, we also
call the stop helpers from drivers, particularly from ->queue_rq()
when we have to stop processing for a bit. We can't block from
those locations, and we don't have to guarantee that we're
fully flushed.
Fixes: 9f99373790 ("blk-mq: unify hctx delayed_run_work and run_work")
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull MD updates from Shaohua Li:
- Add Partial Parity Log (ppl) feature found in Intel IMSM raid array
by Artur Paszkiewicz. This feature is another way to close RAID5
writehole. The Linux implementation is also available for normal
RAID5 array if specific superblock bit is set.
- A number of md-cluser fixes and enabling md-cluster array resize from
Guoqing Jiang
- A bunch of patches from Ming Lei and Neil Brown to rewrite MD bio
handling related code. Now MD doesn't directly access bio bvec,
bi_phys_segments and uses modern bio API for bio split.
- Improve RAID5 IO pattern to improve performance for hard disk based
RAID5/6 from me.
- Several patches from Song Liu to speed up raid5-cache recovery and
allow raid5 cache feature disabling in runtime.
- Fix a performance regression in raid1 resync from Xiao Ni.
- Other cleanup and fixes from various people.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (84 commits)
md/raid10: skip spare disk as 'first' disk
md/raid1: Use a new variable to count flighting sync requests
md: clear WantReplacement once disk is removed
md/raid1/10: remove unused queue
md: handle read-only member devices better.
md/raid10: wait up frozen array in handle_write_completed
uapi: fix linux/raid/md_p.h userspace compilation error
md-cluster: Fix a memleak in an error handling path
md: support disabling of create-on-open semantics.
md: allow creation of mdNNN arrays via md_mod/parameters/new_array
raid5-ppl: use a single mempool for ppl_io_unit and header_page
md/raid0: fix up bio splitting.
md/linear: improve bio splitting.
md/raid5: make chunk_aligned_read() split bios more cleanly.
md/raid10: simplify handle_read_error()
md/raid10: simplify the splitting of requests.
md/raid1: factor out flush_bio_list()
md/raid1: simplify handle_read_error().
Revert "block: introduce bio_copy_data_partial"
md/raid1: simplify alloc_behind_master_bio()
...
After queue is frozen, no request in this queue can be in use at all, so
there can't be any .queue_rq() running on this queue. It isn't
necessary to call blk_mq_quiesce_queue() any more, so remove it in both
elevator_switch_mq() and blk_mq_update_nr_requests().
Cc: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Fixed up the description a bit.
Signed-off-by: Jens Axboe <axboe@fb.com>
guide for user-space API documents, rather sparsely populated at the
moment, but it's a start. Markus improved the infrastructure for
converting diagrams. Mauro has converted much of the USB documentation
over to RST. Plus the usual set of fixes, improvements, and tweaks.
There's a bit more than the usual amount of reaching out of Documentation/
to fix comments elsewhere in the tree; I have acks for those where I could
get them.
-----BEGIN PGP SIGNATURE-----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=41m+
-----END PGP SIGNATURE-----
Merge tag 'docs-4.12' of git://git.lwn.net/linux
Pull documentation update from Jonathan Corbet:
"A reasonably busy cycle for documentation this time around. There is a
new guide for user-space API documents, rather sparsely populated at
the moment, but it's a start. Markus improved the infrastructure for
converting diagrams. Mauro has converted much of the USB documentation
over to RST. Plus the usual set of fixes, improvements, and tweaks.
There's a bit more than the usual amount of reaching out of
Documentation/ to fix comments elsewhere in the tree; I have acks for
those where I could get them"
* tag 'docs-4.12' of git://git.lwn.net/linux: (74 commits)
docs: Fix a couple typos
docs: Fix a spelling error in vfio-mediated-device.txt
docs: Fix a spelling error in ioctl-number.txt
MAINTAINERS: update file entry for HSI subsystem
Documentation: allow installing man pages to a user defined directory
Doc/PM: Sync with intel_powerclamp code behavior
zr364xx.rst: usb/devices is now at /sys/kernel/debug/
usb.rst: move documentation from proc_usb_info.txt to USB ReST book
convert philips.txt to ReST and add to media docs
docs-rst: usb: update old usbfs-related documentation
arm: Documentation: update a path name
docs: process/4.Coding.rst: Fix a couple of document refs
docs-rst: fix usb cross-references
usb: gadget.h: be consistent at kernel doc macros
usb: composite.h: fix two warnings when building docs
usb: get rid of some ReST doc build errors
usb.rst: get rid of some Sphinx errors
usb/URB.txt: convert to ReST and update it
usb/persist.txt: convert to ReST and add to driver-api book
usb/hotplug.txt: convert to ReST and add to driver-api book
...
Remove the request_idx parameter, which can't be used safely now that we
support I/O schedulers with blk-mq. Except for a superflous check in
mtip32xx it was unused anyway.
Also pass the tag_set instead of just the driver data - this allows drivers
to avoid some code duplication in a follow on cleanup.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
We have update the troublesome driver (mtip32xx) to deal with this
appropriately. So kill the hack that bypassed scheduler allocation
and insertion for reserved requests.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Since commit 8425339492 ("remove the mg_disk driver") removed the
only caller of elevator_change(), also remove the elevator_change()
function itself.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Markus Trippelsdorf <markus@trippelsdorf.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull uaccess unification updates from Al Viro:
"This is the uaccess unification pile. It's _not_ the end of uaccess
work, but the next batch of that will go into the next cycle. This one
mostly takes copy_from_user() and friends out of arch/* and gets the
zero-padding behaviour in sync for all architectures.
Dealing with the nocache/writethrough mess is for the next cycle;
fortunately, that's x86-only. Same for cleanups in iov_iter.c (I am
sold on access_ok() in there, BTW; just not in this pile), same for
reducing __copy_... callsites, strn*... stuff, etc. - there will be a
pile about as large as this one in the next merge window.
This one sat in -next for weeks. -3KLoC"
* 'work.uaccess' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (96 commits)
HAVE_ARCH_HARDENED_USERCOPY is unconditional now
CONFIG_ARCH_HAS_RAW_COPY_USER is unconditional now
m32r: switch to RAW_COPY_USER
hexagon: switch to RAW_COPY_USER
microblaze: switch to RAW_COPY_USER
get rid of padding, switch to RAW_COPY_USER
ia64: get rid of copy_in_user()
ia64: sanitize __access_ok()
ia64: get rid of 'segment' argument of __do_{get,put}_user()
ia64: get rid of 'segment' argument of __{get,put}_user_check()
ia64: add extable.h
powerpc: get rid of zeroing, switch to RAW_COPY_USER
esas2r: don't open-code memdup_user()
alpha: fix stack smashing in old_adjtimex(2)
don't open-code kernel_setsockopt()
mips: switch to RAW_COPY_USER
mips: get rid of tail-zeroing in primitives
mips: make copy_from_user() zero tail explicitly
mips: clean and reorder the forest of macros...
mips: consolidate __invoke_... wrappers
...
Pull block layer updates from Jens Axboe:
- Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
was initially a fork of CFQ, but subsequently changed to implement
fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
to be used on desktop type single drives, providing good fairness.
From Paolo.
- Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
using a scalable token based algorithm that throttles IO based on
live completion IO stats, similary to blk-wbt. From Omar.
- A series from Jan, moving users to separately allocated backing
devices. This continues the work of separating backing device life
times, solving various problems with hot removal.
- A series of updates for lightnvm, mostly from Javier. Includes a
'pblk' target that exposes an open channel SSD as a physical block
device.
- A series of fixes and improvements for nbd from Josef.
- A series from Omar, removing queue sharing between devices on mostly
legacy drivers. This helps us clean up other bits, if we know that a
queue only has a single device backing. This has been overdue for
more than a decade.
- Fixes for the blk-stats, and improvements to unify the stats and user
windows. This both improves blk-wbt, and enables other users to
register a need to receive IO stats for a device. From Omar.
- blk-throttle improvements from Shaohua. This provides a scalable
framework for implementing scalable priotization - particularly for
blk-mq, but applicable to any type of block device. The interface is
marked experimental for now.
- Bucketized IO stats for IO polling from Stephen Bates. This improves
efficiency of polled workloads in the presence of mixed block size
IO.
- A few fixes for opal, from Scott.
- A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
From a variety of folks, mostly Sagi and James Smart.
- A series from Bart, improving our exposed info and capabilities from
the blk-mq debugfs support.
- A series from Christoph, cleaning up how handle WRITE_ZEROES.
- A series from Christoph, cleaning up the block layer handling of how
we track errors in a request. On top of being a nice cleanup, it also
shrinks the size of struct request a bit.
- Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
never used by platforms, and the latter has outlived it's usefulness.
- Various little bug fixes and cleanups from a wide variety of folks.
* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
block: hide badblocks attribute by default
blk-mq: unify hctx delay_work and run_work
block: add kblock_mod_delayed_work_on()
blk-mq: unify hctx delayed_run_work and run_work
nbd: fix use after free on module unload
MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
blk-mq-sched: alloate reserved tags out of normal pool
mtip32xx: use runtime tag to initialize command header
scsi: Implement blk_mq_ops.show_rq()
blk-mq: Add blk_mq_ops.show_rq()
blk-mq: Show operation, cmd_flags and rq_flags names
blk-mq: Make blk_flags_show() callers append a newline character
blk-mq: Move the "state" debugfs attribute one level down
blk-mq: Unregister debugfs attributes earlier
blk-mq: Only unregister hctxs for which registration succeeded
blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
blk-mq: Let blk_mq_debugfs_register() look up the queue name
blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
ide-pm: always pass 0 error to __blk_end_request_all
..
Commit 99e6608c9e "block: Add badblock management for gendisks"
allowed for drivers like pmem and software-raid to advertise a list of
bad media areas. However, it inadvertently added a 'badblocks' to all
block devices. Lets clean this up by having the 'badblocks' attribute
not be visible when the driver has not populated a 'struct badblocks'
instance in the gendisk.
Cc: Jens Axboe <axboe@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The only difference between ->run_work and ->delay_work, is that
the latter is used to defer running a queue. This is done by
marking the queue stopped, and scheduling ->delay_work to run
sometime in the future. While the queue is stopped, direct runs
or runs through ->run_work will not run the queue.
If we combine the handlers, then we need to handle two things:
1) If a delayed/stopped run is scheduled, then we should not run
the queue before that has been completed.
2) If a queue is delayed/stopped, the handler needs to restart
the queue. Normally a run of a queue with the stopped bit set
would be a no-op.
Case 1 is handled by modifying a currently pending queue run
to the deadline set by the caller of blk_mq_delay_queue().
Subsequent attempts to queue a queue run will find the work
item already pending, and direct runs will see a stopped queue
as before.
Case 2 is handled by adding a new bit, BLK_MQ_S_START_ON_RUN,
that tells the work handler that it should clear a stopped
queue and run the handler.
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This modifies (or adds, if not currently pending) an existing
delayed work item.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
They serve the exact same purpose. Get rid of the non-delayed
work variant, and just run it without delay for the normal case.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
At least one driver, mtip32xx, has a hard coded dependency on
the value of the reserved tag used for internal commands. While
that should really be fixed up, for now let's ensure that we just
bypass the scheduler tags an allocation marked as reserved. They
are used for house keeping or error handling, so we can safely
ignore them in the scheduler.
Tested-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This new callback function will be used in the next patch to show
more information about SCSI requests.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Show the operation name, .cmd_flags and .rq_flags as names instead
of numbers.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch does not change any functionality but makes it possible
to produce a single line of output with multiple flag-to-name
translations.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Move the "state" attribute from the top level to the "mq" directory
as requested by Omar.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We currently call blk_mq_free_queue() from blk_cleanup_queue()
before we unregister the debugfs attributes for that queue in
blk_release_queue(). This leaves a window open during which
accessing most of the mq debugfs attributes would cause a
use-after-free. Additionally, the "state" attribute allows
running the queue, which we should not do after the queue has
entered the "dead" state. Fix both cases by unregistering the
debugfs attributes before freeing queue resources starts.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Hctx unregistration involves calling kobject_del(). kobject_del()
must not be called if kobject_add() has not been called. Hence in
the error path only unregister hctxs for which registration succeeded.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Since the blk_mq_debugfs_*register_hctxs() functions register and
unregister all attributes under the "mq" directory, rename these
into blk_mq_debugfs_*register_mq().
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A later patch will move the call of blk_mq_debugfs_register() to
a function to which the queue name is not passed as an argument.
To avoid having to add a 'name' argument to multiple callers, let
blk_mq_debugfs_register() look up the queue name.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A later patch in this series will modify blk_mq_debugfs_register()
such that it uses q->kobj.parent to determine the name of a
request queue. Hence make sure that that pointer is initialized
before blk_mq_debugfs_register() is called. To avoid lock inversion,
protect sysfs / debugfs registration with the queue sysfs_lock
instead of the global mutex all_q_mutex.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
commit d1a5f2b4d8 ("block: use DAX for partition table reads") was
part of a stalled effort to allow dax mappings of block devices. Since
then the device-dax mechanism has filled the role of dax-mapping static
device ranges.
Now that we are moving ->direct_access() from a block_device operation
to a dax_inode operation we would need block devices to map and carry
their own dax_inode reference.
Unless / until we decide to revive dax mapping of raw block devices
through the dax_inode scheme, there is no need to carry
read_dax_sector(). Its removal in turn allows for the removal of
bdev_direct_access() and should have been included in commit
2237570168 ("block_dev: remove DAX leftovers").
Cc: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
When registering an integrity profile: if the template's interval_exp is
not 0 use it, otherwise use the ilog2() of logical block size of the
provided gendisk.
This fixes a long-standing DM linear target bug where it cannot pass
integrity data to the underlying device if its logical block size
conflicts with the underlying device's logical block size.
Cc: stable@vger.kernel.org
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Commit 25520d55cd ("block: Inline blk_integrity in struct gendisk")
introduced blk_integrity_revalidate(), which seems to assume ownership
of the stable pages flag and unilaterally clears it if no blk_integrity
profile is registered:
if (bi->profile)
disk->queue->backing_dev_info->capabilities |=
BDI_CAP_STABLE_WRITES;
else
disk->queue->backing_dev_info->capabilities &=
~BDI_CAP_STABLE_WRITES;
It's called from revalidate_disk() and rescan_partitions(), making it
impossible to enable stable pages for drivers that support partitions
and don't use blk_integrity: while the call in revalidate_disk() can be
trivially worked around (see zram, which doesn't support partitions and
hence gets away with zram_revalidate_disk()), rescan_partitions() can
be triggered from userspace at any time. This breaks rbd, where the
ceph messenger is responsible for generating/verifying CRCs.
Since blk_integrity_{un,}register() "must" be used for (un)registering
the integrity profile with the block layer, move BDI_CAP_STABLE_WRITES
setting there. This way drivers that call blk_integrity_register() and
use integrity infrastructure won't interfere with drivers that don't
but still want stable pages.
Fixes: 25520d55cd ("block: Inline blk_integrity in struct gendisk")
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 4.4+, needs backporting
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Avoid that the following kernel bug gets triggered:
BUG: sleeping function called from invalid context at ./include/linux/buffer_head.h:349
in_atomic(): 1, irqs_disabled(): 0, pid: 8019, name: find
CPU: 10 PID: 8019 Comm: find Tainted: G W I 4.11.0-rc4-dbg+ #2
Call Trace:
dump_stack+0x68/0x93
___might_sleep+0x16e/0x230
__might_sleep+0x4a/0x80
__ext4_get_inode_loc+0x1e0/0x4e0
ext4_iget+0x70/0xbc0
ext4_iget_normal+0x2f/0x40
ext4_lookup+0xb6/0x1f0
lookup_slow+0x104/0x1e0
walk_component+0x19a/0x330
path_lookupat+0x4b/0x100
filename_lookup+0x9a/0x110
user_path_at_empty+0x36/0x40
vfs_statx+0x67/0xc0
SYSC_newfstatat+0x20/0x40
SyS_newfstatat+0xe/0x10
entry_SYSCALL_64_fastpath+0x18/0xad
This happens since the big if/else in blk_mq_make_request() doesn't
have final else section that also drops the ctx. Add that.
Fixes: b00c53e8f4 ("blk-mq: fix schedule-while-atomic with scheduler attached")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Added a bit more to the commit log.
Signed-off-by: Jens Axboe <axboe@fb.com>
No point in providing and exporting this helper. There's just
one (real) user of it, just use rq_data_dir().
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
commit c13660a08c ("blk-mq-sched: change ->dispatch_requests()
to ->dispatch_request()") removed the last user of this function.
Hence also remove the function itself.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If the caller passes in wait=true, it has to be able to block
for a driver tag. We just had a bug where flush insertion
would block on tag allocation, while we had preempt disabled.
Ensure that we catch cases like that earlier next time.
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Fixes an issue where the size of the poll_stat array in request_queue
does not match the size expected by the new size based bucketing for
IO completion polling.
Fixes: 720b8ccc45 ("blk-mq: Add a polling specific stats function")
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Rather than bucketing IO statisics based on direction only we also
bucket based on the IO size. This leads to improved polling
performance. Update the bucket callback function and use it in the
polling latency estimation.
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
In order to allow for filtering of IO based on some other properties
of the request than direction we allow the bucket function to return
an int.
If the bucket callback returns a negative do no count it in the stats
accumulation.
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Fixed up Kyber scheduler stat callback.
Signed-off-by: Jens Axboe <axboe@fb.com>
If we have a scheduler attached, blk_mq_tag_to_rq() on the
scheduled tags will return NULL if a request is no longer
in flight. This is different than using the normal tags,
where it will always return the fixed request. Check for
this condition for polling, in case we happen to enter
polling for a completed request.
The request address remains valid, so this check and return
should be perfectly safe.
Fixes: bd166ef183 ("blk-mq-sched: add framework for MQ capable IO schedulers")
Tested-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Replace bdev_direct_access() with dax_direct_access() that uses
dax_device and dax_operations instead of a block_device and
block_device_operations for dax. Once all consumers of the old api have
been converted bdev_direct_access() will be deleted.
Given that block device partitioning decisions can cause dax page
alignment constraints to be violated this also introduces the
bdev_dax_pgoff() helper. It handles calculating a logical pgoff relative
to the dax_device and also checks for page alignment.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Merge blk_mq_ipi_complete_request and blk_mq_stat_add into their only
caller.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Now that all drivers that call blk_mq_complete_requests have a
->complete callback we can remove the direct call to blk_mq_end_request,
as well as the error argument to blk_mq_complete_request.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This passes on the scsi_cmnd result field to users of passthrough
requests. Currently we abuse req->errors for this purpose, but that
field will go away in its current form.
Note that the old IDE code abuses the errors field in very creative
ways and stores all kinds of different values in it. I didn't dare
to touch this magic, so the abuses are brought forward 1:1.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The function only returns -EIO if rq->errors is non-zero, which is not
very useful and lets a large number of callers ignore the return value.
Just let the callers figure out their error themselves.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We trigger this warning:
block/blk-throttle.c: In function ‘blk_throtl_bio’:
block/blk-throttle.c:2042:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable]
int ret;
^~~
since we only assign 'ret' if BLK_DEV_THROTTLING_LOW is off, we never
check it.
Reported-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If we don't have CGROUPS enabled, the compile ends in the
following misery:
In file included from ../block/bfq-iosched.c:105:0:
../block/bfq-iosched.h:819:22: error: array type has incomplete element type
extern struct cftype bfq_blkcg_legacy_files[];
^
../block/bfq-iosched.h:820:22: error: array type has incomplete element type
extern struct cftype bfq_blkg_files[];
^
Move the declarations under the right ifdef.
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
The call to bfq_check_ioprio_change will dereference bic, however,
the null check for bic is after this call. Move the the null
check on bic to before the call to avoid any potential null
pointer dereference issues.
Detected by CoverityScan, CID#1430138 ("Dereference before null check")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Since ioprio_best() translates IOPRIO_CLASS_NONE into IOPRIO_CLASS_BE
and since lower numerical priority values represent a higher priority
a simple numerical comparison is sufficient.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Adam Manzanares <adam.manzanares@wdc.com>
Tested-by: Adam Manzanares <adam.manzanares@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
Since only a single caller remains, inline blk_rq_set_prio(). Initialize
req->ioprio even if no I/O priority has been set in the bio nor in the
I/O context.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Adam Manzanares <adam.manzanares@wdc.com>
Tested-by: Adam Manzanares <adam.manzanares@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
Export this function such that it becomes available to block
drivers.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Cc: Adam Manzanares <adam.manzanares@wdc.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If one driver claims that it doesn't support io scheduler via
BLK_MQ_F_NO_SCHED, we should not allow to change and show the
availabe io schedulers.
This patch adds check to enhance this behaviour.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_insert_flush should be using __blk_end_request to start with.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
This function is not used anywhere in the kernel.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Both functions are entirely unused.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
When CFQ is used as an elevator, it disables writeback throttling
because they don't play well together. Later when a different elevator
is chosen for the device, writeback throttling doesn't get enabled
again as it should. Make sure CFQ enables writeback throttling (if it
should be enabled by default) when we switch from it to another IO
scheduler.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
The BFQ I/O scheduler features an optimal fair-queuing
(proportional-share) scheduling algorithm, enriched with several
mechanisms to boost throughput and reduce latency for interactive and
real-time applications. This makes BFQ a large and complex piece of
code. This commit addresses this issue by splitting BFQ into three
main, independent components, and by moving each component into a
separate source file:
1. Main algorithm: handles the interaction with the kernel, and
decides which requests to dispatch; it uses the following two further
components to achieve its goals.
2. Scheduling engine (Hierarchical B-WF2Q+ scheduling algorithm):
computes the schedule, using weights and budgets provided by the above
component.
3. cgroups support: handles group operations (creation, destruction,
move, ...).
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
When a bfq queue is set in service and when it is merged, a reference
to the I/O context associated with the queue is taken. This reference
is then released when the queue is deselected from service or
split. More precisely, the release of the reference is postponed to
when the scheduler lock is released, to avoid nesting between the
scheduler and the I/O-context lock. In fact, such nesting would lead
to deadlocks, because of other code paths that take the same locks in
the opposite order. This postponing of I/O-context releases does
complicate code.
This commit addresses these issue by modifying involved operations in
such a way to not need to get the above I/O-context references any
more. Then it also removes any get and release of these references.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
Many popular I/O-intensive services or applications spawn or
reactivate many parallel threads/processes during short time
intervals. Examples are systemd during boot or git grep. These
services or applications benefit mostly from a high throughput: the
quicker the I/O generated by their processes is cumulatively served,
the sooner the target job of these services or applications gets
completed. As a consequence, it is almost always counterproductive to
weight-raise any of the queues associated to the processes of these
services or applications: in most cases it would just lower the
throughput, mainly because weight-raising also implies device idling.
To address this issue, an I/O scheduler needs, first, to detect which
queues are associated with these services or applications. In this
respect, we have that, from the I/O-scheduler standpoint, these
services or applications cause bursts of activations, i.e.,
activations of different queues occurring shortly after each
other. However, a shorter burst of activations may be caused also by
the start of an application that does not consist in a lot of parallel
I/O-bound threads (see the comments on the function bfq_handle_burst
for details).
In view of these facts, this commit introduces:
1) an heuristic to detect (only) bursts of queue activations caused by
services or applications consisting in many parallel I/O-bound
threads;
2) the prevention of device idling and weight-raising for the queues
belonging to these bursts.
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch is basically the counterpart, for NCQ-capable rotational
devices, of the previous patch. Exactly as the previous patch does on
flash-based devices and for any workload, this patch disables device
idling on rotational devices, but only for random I/O. In fact, only
with these queues disabling idling boosts the throughput on
NCQ-capable rotational devices. To not break service guarantees,
idling is disabled for NCQ-enabled rotational devices only when the
same symmetry conditions considered in the previous patches hold.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch boosts the throughput on NCQ-capable flash-based devices,
while still preserving latency guarantees for interactive and soft
real-time applications. The throughput is boosted by just not idling
the device when the in-service queue remains empty, even if the queue
is sync and has a non-null idle window. This helps to keep the drive's
internal queue full, which is necessary to achieve maximum
performance. This solution to boost the throughput is a port of
commits a68bbdd and f7d7b7a for CFQ.
As already highlighted in a previous patch, allowing the device to
prefetch and internally reorder requests trivially causes loss of
control on the request service order, and hence on service guarantees.
Fortunately, as discussed in detail in the comments on the function
bfq_bfqq_may_idle(), if every process has to receive the same
fraction of the throughput, then the service order enforced by the
internal scheduler of a flash-based device is relatively close to that
enforced by BFQ. In particular, it is close enough to let service
guarantees be substantially preserved.
Things change in an asymmetric scenario, i.e., if not every process
has to receive the same fraction of the throughput. In this case, to
guarantee the desired throughput distribution, the device must be
prevented from prefetching requests. This is exactly what this patch
does in asymmetric scenarios.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A seeky queue (i..e, a queue containing random requests) is assigned a
very small device-idling slice, for throughput issues. Unfortunately,
given the process associated with a seeky queue, this behavior causes
the following problem: if the process, say P, performs sync I/O and
has a higher weight than some other processes doing I/O and associated
with non-seeky queues, then BFQ may fail to guarantee to P its
reserved share of the throughput. The reason is that idling is key
for providing service guarantees to processes doing sync I/O [1].
This commit addresses this issue by allowing the device-idling slice
to be reduced for a seeky queue only if the scenario happens to be
symmetric, i.e., if all the queues are to receive the same share of
the throughput.
[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
Scheduler", Proceedings of the First Workshop on Mobile System
Technologies (MST-2015), May 2015.
http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Riccardo Pizzetti <riccardo.pizzetti@gmail.com>
Signed-off-by: Samuele Zecchini <samuele.zecchini92@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
A set of processes may happen to perform interleaved reads, i.e.,
read requests whose union would give rise to a sequential read pattern.
There are two typical cases: first, processes reading fixed-size chunks
of data at a fixed distance from each other; second, processes reading
variable-size chunks at variable distances. The latter case occurs for
example with QEMU, which splits the I/O generated by a guest into
multiple chunks, and lets these chunks be served by a pool of I/O
threads, iteratively assigning the next chunk of I/O to the first
available thread. CFQ denotes as 'cooperating' a set of processes that
are doing interleaved I/O, and when it detects cooperating processes,
it merges their queues to obtain a sequential I/O pattern from the union
of their I/O requests, and hence boost the throughput.
Unfortunately, in the following frequent case, the mechanism
implemented in CFQ for detecting cooperating processes and merging
their queues is not responsive enough to handle also the fluctuating
I/O pattern of the second type of processes. Suppose that one process
of the second type issues a request close to the next request to serve
of another process of the same type. At that time the two processes
would be considered as cooperating. But, if the request issued by the
first process is to be merged with some other already-queued request,
then, from the moment at which this request arrives, to the moment
when CFQ controls whether the two processes are cooperating, the two
processes are likely to be already doing I/O in distant zones of the
disk surface or device memory.
CFQ uses however preemption to get a sequential read pattern out of
the read requests performed by the second type of processes too. As a
consequence, CFQ uses two different mechanisms to achieve the same
goal: boosting the throughput with interleaved I/O.
This patch introduces Early Queue Merge (EQM), a unified mechanism to
get a sequential read pattern with both types of processes. The main
idea is to immediately check whether a newly-arrived request lets some
pair of processes become cooperating, both in the case of actual
request insertion and, to be responsive with the second type of
processes, in the case of request merge. Both types of processes are
then handled by just merging their queues.
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Mauro Andreolini <mauro.andreolini@unimore.it>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch introduces an heuristic that reduces latency when the
I/O-request pool is saturated. This goal is achieved by disabling
device idling, for non-weight-raised queues, when there are weight-
raised queues with pending or in-flight requests. In fact, as
explained in more detail in the comment on the function
bfq_bfqq_may_idle(), this reduces the rate at which processes
associated with non-weight-raised queues grab requests from the pool,
thereby increasing the probability that processes associated with
weight-raised queues get a request immediately (or at least soon) when
they need one. Along the same line, if there are weight-raised queues,
then this patch halves the service rate of async (write) requests for
non-weight-raised queues.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
I/O schedulers typically allow NCQ-capable drives to prefetch I/O
requests, as NCQ boosts the throughput exactly by prefetching and
internally reordering requests.
Unfortunately, as discussed in detail and shown experimentally in [1],
this may cause fairness and latency guarantees to be violated. The
main problem is that the internal scheduler of an NCQ-capable drive
may postpone the service of some unlucky (prefetched) requests as long
as it deems serving other requests more appropriate to boost the
throughput.
This patch addresses this issue by not disabling device idling for
weight-raised queues, even if the device supports NCQ. This allows BFQ
to start serving a new queue, and therefore allows the drive to
prefetch new requests, only after the idling timeout expires. At that
time, all the outstanding requests of the expired queue have been most
certainly served.
[1] P. Valente and M. Andreolini, "Improving Application
Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
the 5th Annual International Systems and Storage Conference
(SYSTOR '12), June 2012.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
To guarantee a low latency also to the I/O requests issued by soft
real-time applications, this patch introduces a further heuristic,
which weight-raises (in the sense explained in the previous patch)
also the queues associated to applications deemed as soft real-time.
To be deemed as soft real-time, an application must meet two
requirements. First, the application must not require an average
bandwidth higher than the approximate bandwidth required to playback
or record a compressed high-definition video. Second, the request
pattern of the application must be isochronous, i.e., after issuing a
request or a batch of requests, the application must stop issuing new
requests until all its pending requests have been completed. After
that, the application may issue a new batch, and so on.
As for the second requirement, it is critical to require also that,
after all the pending requests of the application have been completed,
an adequate minimum amount of time elapses before the application
starts issuing new requests. This prevents also greedy (i.e.,
I/O-bound) applications from being incorrectly deemed, occasionally,
as soft real-time. In fact, if *any amount of time* is fine, then even
a greedy application may, paradoxically, meet both the above
requirements, if: (1) the application performs random I/O and/or the
device is slow, and (2) the CPU load is high. The reason is the
following. First, if condition (1) is true, then, during the service
of the application, the throughput may be low enough to let the
application meet the bandwidth requirement. Second, if condition (2)
is true as well, then the application may occasionally behave in an
apparently isochronous way, because it may simply stop issuing
requests while the CPUs are busy serving other processes.
To address this issue, the heuristic leverages the simple fact that
greedy applications issue *all* their requests as quickly as they can,
whereas soft real-time applications spend some time processing data
after each batch of requests is completed. In particular, the
heuristic works as follows. First, according to the above isochrony
requirement, the heuristic checks whether an application may be soft
real-time, thereby giving to the application the opportunity to be
deemed as such, only when both the following two conditions happen to
hold: 1) the queue associated with the application has expired and is
empty, 2) there is no outstanding request of the application.
Suppose that both conditions hold at time, say, t_c and that the
application issues its next request at time, say, t_i. At time t_c the
heuristic computes the next time instant, called soft_rt_next_start in
the code, such that, only if t_i >= soft_rt_next_start, then both the
next conditions will hold when the application issues its next
request: 1) the application will meet the above bandwidth requirement,
2) a given minimum time interval, say Delta, will have elapsed from
time t_c (so as to filter out greedy application).
The current value of Delta is a little bit higher than the value that
we have found, experimentally, to be adequate on a real,
general-purpose machine. In particular we had to increase Delta to
make the filter quite precise also in slower, embedded systems, and in
KVM/QEMU virtual machines (details in the comments on the code).
If the application actually issues its next request after time
soft_rt_next_start, then its associated queue will be weight-raised
for a relatively short time interval. If, during this time interval,
the application proves again to meet the bandwidth and isochrony
requirements, then the end of the weight-raising period for the queue
is moved forward, and so on. Note that an application whose associated
queue never happens to be empty when it expires will never have the
opportunity to be deemed as soft real-time.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch introduces a simple heuristic to load applications quickly,
and to perform the I/O requested by interactive applications just as
quickly. To this purpose, both a newly-created queue and a queue
associated with an interactive application (we explain in a moment how
BFQ decides whether the associated application is interactive),
receive the following two special treatments:
1) The weight of the queue is raised.
2) The queue unconditionally enjoys device idling when it empties; in
fact, if the requests of a queue are sync, then performing device
idling for the queue is a necessary condition to guarantee that the
queue receives a fraction of the throughput proportional to its weight
(see [1] for details).
For brevity, we call just weight-raising the combination of these
two preferential treatments. For a newly-created queue,
weight-raising starts immediately and lasts for a time interval that:
1) depends on the device speed and type (rotational or
non-rotational), and 2) is equal to the time needed to load (start up)
a large-size application on that device, with cold caches and with no
additional workload.
Finally, as for guaranteeing a fast execution to interactive,
I/O-related tasks (such as opening a file), consider that any
interactive application blocks and waits for user input both after
starting up and after executing some task. After a while, the user may
trigger new operations, after which the application stops again, and
so on. Accordingly, the low-latency heuristic weight-raises again a
queue in case it becomes backlogged after being idle for a
sufficiently long (configurable) time. The weight-raising then lasts
for the same time as for a just-created queue.
According to our experiments, the combination of this low-latency
heuristic and of the improvements described in the previous patch
allows BFQ to guarantee a high application responsiveness.
[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
Scheduler", Proceedings of the First Workshop on Mobile System
Technologies (MST-2015), May 2015.
http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch deals with two sources of unfairness, which can also cause
high latencies and throughput loss. The first source is related to
write requests. Write requests tend to starve read requests, basically
because, on one side, writes are slower than reads, whereas, on the
other side, storage devices confuse schedulers by deceptively
signaling the completion of write requests immediately after receiving
them. This patch addresses this issue by just throttling writes. In
particular, after a write request is dispatched for a queue, the
budget of the queue is decremented by the number of sectors to write,
multiplied by an (over)charge coefficient. The value of the
coefficient is the result of our tuning with different devices.
The second source of unfairness has to do with slowness detection:
when the in-service queue is expired, BFQ also controls whether the
queue has been "too slow", i.e., has consumed its last-assigned budget
at such a low rate that it would have been impossible to consume all
of this budget within the maximum time slice T_max (Subsec. 3.5 in
[1]). In this case, the queue is always (over)charged the whole
budget, to reduce its utilization of the device. Both this overcharge
and the slowness-detection criterion may cause unfairness.
First, always charging a full budget to a slow queue is too coarse. It
is much more accurate, and this patch lets BFQ do so, to charge an
amount of service 'equivalent' to the amount of time during which the
queue has been in service. As explained in more detail in the comments
on the code, this enables BFQ to provide time fairness among slow
queues.
Secondly, because of ZBR, a queue may be deemed as slow when its
associated process is performing I/O on the slowest zones of a
disk. However, unless the process is truly too slow, not reducing the
disk utilization of the queue is more profitable in terms of disk
throughput than the opposite. A similar problem is caused by logical
block mapping on non-rotational devices. For this reason, this patch
lets a queue be charged time, and not budget, only if the queue has
consumed less than 2/3 of its assigned budget. As an additional,
important benefit, this tolerance allows BFQ to preserve enough
elasticity to still perform bandwidth, and not time, distribution with
little unlucky or quasi-sequential processes.
Finally, for the same reasons as above, this patch makes slowness
detection itself much less harsh: a queue is deemed slow only if it
has consumed its budget at less than half of the peak rate.
[1] P. Valente and M. Andreolini, "Improving Application
Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
the 5th Annual International Systems and Storage Conference
(SYSTOR '12), June 2012.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Unless the maximum budget B_max that BFQ can assign to a queue is set
explicitly by the user, BFQ automatically updates B_max. In
particular, BFQ dynamically sets B_max to the number of sectors that
can be read, at the current estimated peak rate, during the maximum
time, T_max, allowed before a budget timeout occurs. In formulas, if
we denote as R_est the estimated peak rate, then B_max = T_max ∗
R_est. Hence, the higher R_est is with respect to the actual device
peak rate, the higher the probability that processes incur budget
timeouts unjustly is. Besides, a too high value of B_max unnecessarily
increases the deviation from an ideal, smooth service.
Unfortunately, it is not trivial to estimate the peak rate correctly:
because of the presence of sw and hw queues between the scheduler and
the device components that finally serve I/O requests, it is hard to
say exactly when a given dispatched request is served inside the
device, and for how long. As a consequence, it is hard to know
precisely at what rate a given set of requests is actually served by
the device.
On the opposite end, the dispatch time of any request is trivially
available, and, from this piece of information, the "dispatch rate"
of requests can be immediately computed. So, the idea in the next
function is to use what is known, namely request dispatch times
(plus, when useful, request completion times), to estimate what is
unknown, namely in-device request service rate.
The main issue is that, because of the above facts, the rate at
which a certain set of requests is dispatched over a certain time
interval can vary greatly with respect to the rate at which the
same requests are then served. But, since the size of any
intermediate queue is limited, and the service scheme is lossless
(no request is silently dropped), the following obvious convergence
property holds: the number of requests dispatched MUST become
closer and closer to the number of requests completed as the
observation interval grows. This is the key property used in
this new version of the peak-rate estimator.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The feedback-loop algorithm used by BFQ to compute queue (process)
budgets is basically a set of three update rules, one for each of the
main reasons why a queue may be expired. If many processes suddenly
switch from sporadic I/O to greedy and sequential I/O, then these
rules are quite slow to assign large budgets to these processes, and
hence to achieve a high throughput. On the opposite side, BFQ assigns
the maximum possible budget B_max to a just-created queue. This allows
a high throughput to be achieved immediately if the associated process
is I/O-bound and performs sequential I/O from the beginning. But it
also increases the worst-case latency experienced by the first
requests issued by the process, because the larger the budget of a
queue waiting for service is, the later the queue will be served by
B-WF2Q+ (Subsec 3.3 in [1]). This is detrimental for an interactive or
soft real-time application.
To tackle these throughput and latency problems, on one hand this
patch changes the initial budget value to B_max/2. On the other hand,
it re-tunes the three rules, adopting a more aggressive,
multiplicative increase/linear decrease scheme. This scheme trades
latency for throughput more than before, and tends to assign large
budgets quickly to processes that are or become I/O-bound. For two of
the expiration reasons, the new version of the rules also contains
some more little improvements, briefly described below.
*No more backlog.* In this case, the budget was larger than the number
of sectors actually read/written by the process before it stopped
doing I/O. Hence, to reduce latency for the possible future I/O
requests of the process, the old rule simply set the next budget to
the number of sectors actually consumed by the process. However, if
there are still outstanding requests, then the process may have not
yet issued its next request just because it is still waiting for the
completion of some of the still outstanding ones. If this sub-case
holds true, then the new rule, instead of decreasing the budget,
doubles it, proactively, in the hope that: 1) a larger budget will fit
the actual needs of the process, and 2) the process is sequential and
hence a higher throughput will be achieved by serving the process
longer after granting it access to the device.
*Budget timeout*. The original rule set the new budget to the maximum
value B_max, to maximize throughput and let all processes experiencing
budget timeouts receive the same share of the device time. In our
experiments we verified that this sudden jump to B_max did not provide
sensible benefits; rather it increased the latency of processes
performing sporadic and short I/O. The new rule only doubles the
budget.
[1] P. Valente and M. Andreolini, "Improving Application
Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
the 5th Annual International Systems and Storage Conference
(SYSTOR '12), June 2012.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Add complete support for full hierarchical scheduling, with a cgroups
interface. Full hierarchical scheduling is implemented through the
'entity' abstraction: both bfq_queues, i.e., the internal BFQ queues
associated with processes, and groups are represented in general by
entities. Given the bfq_queues associated with the processes belonging
to a given group, the entities representing these queues are sons of
the entity representing the group. At higher levels, if a group, say
G, contains other groups, then the entity representing G is the parent
entity of the entities representing the groups in G.
Hierarchical scheduling is performed as follows: if the timestamps of
a leaf entity (i.e., of a bfq_queue) change, and such a change lets
the entity become the next-to-serve entity for its parent entity, then
the timestamps of the parent entity are recomputed as a function of
the budget of its new next-to-serve leaf entity. If the parent entity
belongs, in its turn, to a group, and its new timestamps let it become
the next-to-serve for its parent entity, then the timestamps of the
latter parent entity are recomputed as well, and so on. When a new
bfq_queue must be set in service, the reverse path is followed: the
next-to-serve highest-level entity is chosen, then its next-to-serve
child entity, and so on, until the next-to-serve leaf entity is
reached, and the bfq_queue that this entity represents is set in
service.
Writeback is accounted for on a per-group basis, i.e., for each group,
the async I/O requests of the processes of the group are enqueued in a
distinct bfq_queue, and the entity associated with this queue is a
child of the entity associated with the group.
Weights can be assigned explicitly to groups and processes through the
cgroups interface, differently from what happens, for single
processes, if the cgroups interface is not used (as explained in the
description of the previous patch). In particular, since each node has
a full scheduler, each group can be assigned its own weight.
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We tag as v0 the version of BFQ containing only BFQ's engine plus
hierarchical support. BFQ's engine is introduced by this commit, while
hierarchical support is added by next commit. We use the v0 tag to
distinguish this minimal version of BFQ from the versions containing
also the features and the improvements added by next commits. BFQ-v0
coincides with the version of BFQ submitted a few years ago [1], apart
from the introduction of preemption, described below.
BFQ is a proportional-share I/O scheduler, whose general structure,
plus a lot of code, are borrowed from CFQ.
- Each process doing I/O on a device is associated with a weight and a
(bfq_)queue.
- BFQ grants exclusive access to the device, for a while, to one queue
(process) at a time, and implements this service model by
associating every queue with a budget, measured in number of
sectors.
- After a queue is granted access to the device, the budget of the
queue is decremented, on each request dispatch, by the size of the
request.
- The in-service queue is expired, i.e., its service is suspended,
only if one of the following events occurs: 1) the queue finishes
its budget, 2) the queue empties, 3) a "budget timeout" fires.
- The budget timeout prevents processes doing random I/O from
holding the device for too long and dramatically reducing
throughput.
- Actually, as in CFQ, a queue associated with a process issuing
sync requests may not be expired immediately when it empties. In
contrast, BFQ may idle the device for a short time interval,
giving the process the chance to go on being served if it issues
a new request in time. Device idling typically boosts the
throughput on rotational devices, if processes do synchronous
and sequential I/O. In addition, under BFQ, device idling is
also instrumental in guaranteeing the desired throughput
fraction to processes issuing sync requests (see [2] for
details).
- With respect to idling for service guarantees, if several
processes are competing for the device at the same time, but
all processes (and groups, after the following commit) have
the same weight, then BFQ guarantees the expected throughput
distribution without ever idling the device. Throughput is
thus as high as possible in this common scenario.
- Queues are scheduled according to a variant of WF2Q+, named
B-WF2Q+, and implemented using an augmented rb-tree to preserve an
O(log N) overall complexity. See [2] for more details. B-WF2Q+ is
also ready for hierarchical scheduling. However, for a cleaner
logical breakdown, the code that enables and completes
hierarchical support is provided in the next commit, which focuses
exactly on this feature.
- B-WF2Q+ guarantees a tight deviation with respect to an ideal,
perfectly fair, and smooth service. In particular, B-WF2Q+
guarantees that each queue receives a fraction of the device
throughput proportional to its weight, even if the throughput
fluctuates, and regardless of: the device parameters, the current
workload and the budgets assigned to the queue.
- The last, budget-independence, property (although probably
counterintuitive in the first place) is definitely beneficial, for
the following reasons:
- First, with any proportional-share scheduler, the maximum
deviation with respect to an ideal service is proportional to
the maximum budget (slice) assigned to queues. As a consequence,
BFQ can keep this deviation tight not only because of the
accurate service of B-WF2Q+, but also because BFQ *does not*
need to assign a larger budget to a queue to let the queue
receive a higher fraction of the device throughput.
- Second, BFQ is free to choose, for every process (queue), the
budget that best fits the needs of the process, or best
leverages the I/O pattern of the process. In particular, BFQ
updates queue budgets with a simple feedback-loop algorithm that
allows a high throughput to be achieved, while still providing
tight latency guarantees to time-sensitive applications. When
the in-service queue expires, this algorithm computes the next
budget of the queue so as to:
- Let large budgets be eventually assigned to the queues
associated with I/O-bound applications performing sequential
I/O: in fact, the longer these applications are served once
got access to the device, the higher the throughput is.
- Let small budgets be eventually assigned to the queues
associated with time-sensitive applications (which typically
perform sporadic and short I/O), because, the smaller the
budget assigned to a queue waiting for service is, the sooner
B-WF2Q+ will serve that queue (Subsec 3.3 in [2]).
- Weights can be assigned to processes only indirectly, through I/O
priorities, and according to the relation:
weight = 10 * (IOPRIO_BE_NR - ioprio).
The next patch provides, instead, a cgroups interface through which
weights can be assigned explicitly.
- If several processes are competing for the device at the same time,
but all processes and groups have the same weight, then BFQ
guarantees the expected throughput distribution without ever idling
the device. It uses preemption instead. Throughput is then much
higher in this common scenario.
- ioprio classes are served in strict priority order, i.e.,
lower-priority queues are not served as long as there are
higher-priority queues. Among queues in the same class, the
bandwidth is distributed in proportion to the weight of each
queue. A very thin extra bandwidth is however guaranteed to the Idle
class, to prevent it from starving.
- If the strict_guarantees parameter is set (default: unset), then BFQ
- always performs idling when the in-service queue becomes empty;
- forces the device to serve one I/O request at a time, by
dispatching a new request only if there is no outstanding
request.
In the presence of differentiated weights or I/O-request sizes,
both the above conditions are needed to guarantee that every
queue receives its allotted share of the bandwidth (see
Documentation/block/bfq-iosched.txt for more details). Setting
strict_guarantees may evidently affect throughput.
[1] https://lkml.org/lkml/2008/4/1/234https://lkml.org/lkml/2008/11/11/148
[2] P. Valente and M. Andreolini, "Improving Application
Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
the 5th Annual International Systems and Storage Conference
(SYSTOR '12), June 2012.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The Kyber I/O scheduler is an I/O scheduler for fast devices designed to
scale to multiple queues. Users configure only two knobs, the target
read and synchronous write latencies, and the scheduler tunes itself to
achieve that latency goal.
The implementation is based on "tokens", built on top of the scalable
bitmap library. Tokens serve as a mechanism for limiting requests. There
are two tiers of tokens: queueing tokens and dispatch tokens.
A queueing token is required to allocate a request. In fact, these
tokens are actually the blk-mq internal scheduler tags, but the
scheduler manages the allocation directly in order to implement its
policy.
Dispatch tokens are device-wide and split up into two scheduling
domains: reads vs. writes. Each hardware queue dispatches batches
round-robin between the scheduling domains as long as tokens are
available for that domain.
These tokens can be used as the mechanism to enable various policies.
The policy Kyber uses is inspired by active queue management techniques
for network routing, similar to blk-wbt. The scheduler monitors
latencies and scales the number of dispatch tokens accordingly. Queueing
tokens are used to prevent starvation of synchronous requests by
asynchronous requests.
Various extensions are possible, including better heuristics and ionice
support. The new scheduler isn't set as the default yet.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Currently, this callback is called right after put_request() and has no
distinguishable purpose. Instead, let's call it before put_request() as
soon as I/O has completed on the request, before we account it in
blk-stat. With this, Kyber can enable stats when it sees a latency
outlier and make sure the outlier gets accounted.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_mq_finish_request() is required for schedulers that define their own
put_request(). blk_mq_run_hw_queue() is required for schedulers that
hold back requests to be run later.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Wire up the sbitmap_get_shallow() operation to the tag code so that a
caller can limit the number of tags available to it.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This reverts commit 6f8802852f.
bio_copy_data_partial() is no longer needed.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
When CFQ calls wbt_disable_default(), it will call
blk_stat_remove_callback() to stop gathering IO statistics for the
purposes of writeback throttling. Later, when request_queue is
unregistered, wbt_exit() will call blk_stat_remove_callback() again
which will try to delete callback from the list again and possibly cause
list corruption.
Fix the problem by making wbt_disable_default() called wbt_exit() which
is properly guarded against being called multiple times.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
Instead of showing the hctx state and flags as numbers, show the
names of the flags.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Make it possible to check whether or not a block layer queue has
been stopped. Make it possible to start and to run a blk-mq queue
from user space.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Now that we use the proper REQ_OP_WRITE_ZEROES operation everywhere we can
kill this hack.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Now that we have REQ_OP_WRITE_ZEROES implemented for all devices that
support efficient zeroing, we can remove the call to blkdev_issue_discard.
This means we only have two ways of zeroing left and can simplify the
code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This avoids fallbacks to explicit zeroing in (__)blkdev_issue_zeroout if
the caller doesn't want them.
Also clean up the convoluted check for the return condition that this
new flag is added to.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If this flag is set logical provisioning capable device should
release space for the zeroed blocks if possible, if it is not set
devices should keep the blocks anchored.
Also remove an out of sync kerneldoc comment for a static function
that would have become even more out of data with this change.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Turn the existing discard flag into a new BLKDEV_ZERO_UNMAP flag with
similar semantics, but without referring to diѕcard.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We'll always use the WRITE ZEROES code for zeroing now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Copy and past the REQ_OP_WRITE_SAME code to prepare to implementations
that limit the write zeroes size.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Lets not flood the kernel log with messages unless
the user requests so.
Signed-off-by: Scott Bauer <scott.bauer@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The blk_mq_dispatch_rq_list() implementation got modified several
times but the comments in that function were not updated every
time. Since it is nontrivial what is going on, update the comments
in blk_mq_dispatch_rq_list().
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Since the next patch in this series will use RCU to iterate over
tag_list, make this safe. Add lockdep_assert_held() statements
in functions that iterate over tag_list to make clear that using
list_for_each_entry() instead of list_for_each_entry_rcu() is
fine in these functions.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Minor cleanup that makes it easier to figure out what's going on in the
driver tag allocation failure path of blk_mq_dispatch_rq_list().
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Schedulers need to be informed when a hardware queue is added or removed
at runtime so they can allocate/free per-hardware queue data. So,
replace the blk_mq_sched_init_hctx_data() helper, which only makes sense
at init time, with .init_hctx() and .exit_hctx() hooks.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We've added a considerable amount of fixes for stalls and issues
with the blk-mq scheduling in the 4.11 series since forking
off the for-4.12/block branch. We need to do improvements on
top of that for 4.12, so pull in the previous fixes to make
our lives easier going forward.
Signed-off-by: Jens Axboe <axboe@fb.com>
To improve scalability, if hardware queues are shared, restart
a single hardware queue in round-robin fashion. Rename
blk_mq_sched_restart_queues() to reflect the new semantics.
Remove blk_mq_sched_mark_restart_queue() because this function
has no callers. Remove flag QUEUE_FLAG_RESTART because this
patch removes the code that uses this flag.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Introduce a function that runs a hardware queue unconditionally
after a delay. Note: there is already a function that stops and
restarts a hardware queue after a delay, namely blk_mq_delay_queue().
This function will be used in the next patch in this series.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Long Li <longli@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Currently only dm and md/raid5 bios trigger
trace_block_bio_complete(). Now that we have bio_chain() and
bio_inc_remaining(), it is not possible, in general, for a driver to
know when the bio is really complete. Only bio_endio() knows that.
So move the trace_block_bio_complete() call to bio_endio().
Now trace_block_bio_complete() pairs with trace_block_bio_queue().
Any bio for which a 'queue' event is traced, will subsequently
generate a 'complete' event.
There are a few cases where completion tracing is not wanted.
1/ If blk_update_request() has already generated a completion
trace event at the 'request' level, there is no point generating
one at the bio level too. In this case the bi_sector and bi_size
will have changed, so the bio level event would be wrong
2/ If the bio hasn't actually been queued yet, but is being aborted
early, then a trace event could be confusing. Some filesystems
call bio_endio() but do not want tracing.
3/ The bio_integrity code interposes itself by replacing bi_end_io,
then restoring it and calling bio_endio() again. This would produce
two identical trace events if left like that.
To handle these, we introduce a flag BIO_TRACE_COMPLETION and only
produce the trace event when this is set.
We address point 1 above by clearing the flag in blk_update_request().
We address point 2 above by only setting the flag when
generic_make_request() is called.
We address point 3 above by clearing the flag after generating a
completion event.
When bio_split() is used on a bio, particularly in blk_queue_split(),
there is an extra complication. A new bio is split off the front, and
may be handle directly without going through generic_make_request().
The old bio, which has been advanced, is passed to
generic_make_request(), so it will trigger a trace event a second
time.
Probably the best result when a split happens is to see a single
'queue' event for the whole bio, then multiple 'complete' events - one
for each component. To achieve this was can:
- copy the BIO_TRACE_COMPLETION flag to the new bio in bio_split()
- avoid generating a 'queue' event if BIO_TRACE_COMPLETION is already set.
This way, the split-off bio won't create a queue event, the original
won't either even if it re-submitted to generic_make_request(),
but both will produce completion events, each for their own range.
So if generic_make_request() is called (which generates a QUEUED
event), then bi_endio() will create a single COMPLETE event for each
range that the bio is split into, unless the driver has explicitly
requested it not to.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_mq_update_nr_hw_queues() used to remap hardware queues, which is the
behavior that drivers expect. However, commit 4e68a01142 changed
blk_mq_queue_reinit() to not remap queues for the case of CPU
hotplugging, inadvertently making blk_mq_update_nr_hw_queues() not remap
queues as well. This breaks, for example, NBD's multi-connection mode,
leaving the added hardware queues unused. Fix it by making
blk_mq_update_nr_hw_queues() explicitly remap the queues.
Fixes: 4e68a01142 ("blk-mq: don't redistribute hardware queues on a CPU hotplug event")
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
In elevator_switch(), if blk_mq_init_sched() fails, we attempt to fall
back to the original scheduler. However, at this point, we've already
torn down the original scheduler's tags, so this causes a crash. Doing
the fallback like the legacy elevator path is much harder for mq, so fix
it by just falling back to none, instead.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If a new hardware queue is added at runtime, we don't allocate scheduler
tags for it, leading to a crash. This hooks up the scheduler framework
to blk_mq_{init,exit}_hctx() to make sure everything gets properly
initialized/freed.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Preparation cleanup for the next couple of fixes, push
blk_mq_sched_setup() and e->ops.mq.init_sched() into a helper.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
While dispatching requests, if we fail to get a driver tag, we mark the
hardware queue as waiting for a tag and put the requests on a
hctx->dispatch list to be run later when a driver tag is freed. However,
blk_mq_dispatch_rq_list() may dispatch requests from multiple hardware
queues if using a single-queue scheduler with a multiqueue device. If
blk_mq_get_driver_tag() fails, it doesn't update the hardware queue we
are processing. This means we end up using the hardware queue of the
previous request, which may or may not be the same as that of the
current request. If it isn't, the wrong hardware queue will end up
waiting for a tag, and the requests will be on the wrong dispatch list,
leading to a hang.
The fix is twofold:
1. Make sure we save which hardware queue we were trying to get a
request for in blk_mq_get_driver_tag() regardless of whether it
succeeds or not.
2. Make blk_mq_dispatch_rq_list() take a request_queue instead of a
blk_mq_hw_queue to make it clear that it must handle multiple
hardware queues, since I've already messed this up on a couple of
occasions.
This didn't appear in testing with nvme and mq-deadline because nvme has
more driver tags than the default number of scheduler tags. However,
with the blk_mq_update_nr_hw_queues() fix, it showed up with nbd.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Instead of bloating the generic struct request with it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
The block layer core sets blk_mq_queue_data.list but no block
drivers read that member. Hence remove it and also the code that
is used to set this member.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
Writeback throttling does not play well with CFQ since that also tries
to throttle async writes. As a result async writeback can get starved in
presence of readers. As an example take a benchmark simulating
postgreSQL database running over a standard rotating SATA drive. There
are 16 processes doing random reads from a huge file (2*machine memory),
1 process doing random writes to the huge file and calling fsync once
per 50000 writes and 1 process doing sequential 8k writes to a
relatively small file wrapping around at the end of the file and calling
fsync every 5 writes. Under this load read latency easily exceeds the
target latency of 75 ms (just because there are so many reads happening
against a relatively slow disk) and thus writeback is throttled to a
point where only 1 write request is allowed at a time. Blktrace data
then looks like:
8,0 1 0 8.347751764 0 m N cfq workload slice:40000000
8,0 1 0 8.347755256 0 m N cfq293A / set_active wl_class: 0 wl_type:0
8,0 1 0 8.347784100 0 m N cfq293A / Not idling. st->count:1
8,0 1 3814 8.347763916 5839 UT N [kworker/u9:2] 1
8,0 0 0 8.347777605 0 m N cfq293A / Not idling. st->count:1
8,0 1 0 8.347784100 0 m N cfq293A / Not idling. st->count:1
8,0 3 1596 8.354364057 0 C R 156109528 + 8 (6906954) [0]
8,0 3 0 8.354383193 0 m N cfq6196SN / complete rqnoidle 0
8,0 3 0 8.354386476 0 m N cfq schedule dispatch
8,0 3 0 8.354399397 0 m N cfq293A / Not idling. st->count:1
8,0 3 0 8.354404705 0 m N cfq293A / dispatch_insert
8,0 3 0 8.354409454 0 m N cfq293A / dispatched a request
8,0 3 0 8.354412527 0 m N cfq293A / activate rq, drv=1
8,0 3 1597 8.354414692 0 D W 145961400 + 24 (6718452) [swapper/0]
8,0 3 0 8.354484184 0 m N cfq293A / Not idling. st->count:1
8,0 3 0 8.354487536 0 m N cfq293A / slice expired t=0
8,0 3 0 8.354498013 0 m N / served: vt=5888102466265088 min_vt=5888074869387264
8,0 3 0 8.354502692 0 m N cfq293A / sl_used=6737519 disp=1 charge=6737519 iops=0 sect=24
8,0 3 0 8.354505695 0 m N cfq293A / del_from_rr
...
8,0 0 1810 8.354728768 0 C W 145961400 + 24 (314076) [0]
8,0 0 0 8.354746927 0 m N cfq293A / complete rqnoidle 0
...
8,0 1 3829 8.389886102 5839 G W 145962968 + 24 [kworker/u9:2]
8,0 1 3830 8.389888127 5839 P N [kworker/u9:2]
8,0 1 3831 8.389908102 5839 A W 145978336 + 24 <- (8,4) 44000
8,0 1 3832 8.389910477 5839 Q W 145978336 + 24 [kworker/u9:2]
8,0 1 3833 8.389914248 5839 I W 145962968 + 24 (28146) [kworker/u9:2]
8,0 1 0 8.389919137 0 m N cfq293A / insert_request
8,0 1 0 8.389924305 0 m N cfq293A / add_to_rr
8,0 1 3834 8.389933175 5839 UT N [kworker/u9:2] 1
...
8,0 0 0 9.455290997 0 m N cfq workload slice:40000000
8,0 0 0 9.455294769 0 m N cfq293A / set_active wl_class:0 wl_type:0
8,0 0 0 9.455303499 0 m N cfq293A / fifo=ffff880003166090
8,0 0 0 9.455306851 0 m N cfq293A / dispatch_insert
8,0 0 0 9.455311251 0 m N cfq293A / dispatched a request
8,0 0 0 9.455314324 0 m N cfq293A / activate rq, drv=1
8,0 0 2043 9.455316210 6204 D W 145962968 + 24 (1065401962) [pgioperf]
8,0 0 0 9.455392407 0 m N cfq293A / Not idling. st->count:1
8,0 0 0 9.455395969 0 m N cfq293A / slice expired t=0
8,0 0 0 9.455404210 0 m N / served: vt=5888958194597888 min_vt=5888941810597888
8,0 0 0 9.455410077 0 m N cfq293A / sl_used=4000000 disp=1 charge=4000000 iops=0 sect=24
8,0 0 0 9.455416851 0 m N cfq293A / del_from_rr
...
8,0 0 2045 9.455648515 0 C W 145962968 + 24 (332305) [0]
8,0 0 0 9.455668350 0 m N cfq293A / complete rqnoidle 0
...
8,0 1 4371 9.455710115 5839 G W 145978336 + 24 [kworker/u9:2]
8,0 1 4372 9.455712350 5839 P N [kworker/u9:2]
8,0 1 4373 9.455730159 5839 A W 145986616 + 24 <- (8,4) 52280
8,0 1 4374 9.455732674 5839 Q W 145986616 + 24 [kworker/u9:2]
8,0 1 4375 9.455737563 5839 I W 145978336 + 24 (27448) [kworker/u9:2]
8,0 1 0 9.455742871 0 m N cfq293A / insert_request
8,0 1 0 9.455747550 0 m N cfq293A / add_to_rr
8,0 1 4376 9.455756629 5839 UT N [kworker/u9:2] 1
So we can see a Q event for a write request, then IO is blocked by
writeback throttling and G and I events for the request happen only once
other writeback IO is completed. Thus CFQ always sees only one write
request. When it sees it, it queues the async queue behind all the read
queues and the async queue gets scheduled after about one second. When
it is scheduled, that one request gets dispatched and async queue is
expired as it has no more requests to submit. Overall we submit about
one write request per second.
Although this scheduling is beneficial for read latency, writes are
heavily starved and this causes large delays all over the system (due to
processes blocking on page lock, transaction starts, etc.). When
writeback throttling is disabled, write throughput is about one fifth of
a read throughput which roughly matches readers/writers ratio and
overall the system stalls are much shorter.
Mixing writeback throttling logic with CFQ throttling logic is always a
recipe for surprises as CFQ assumes it sees the big part of the picture
which is not necessarily true when writeback throttling is blocking
requests. So disable writeback throttling logic by default when CFQ is
used as an IO scheduler.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
In 4.10 I introduced a patch that associates the ioc priority with
each request in the block layer. This work was done in the single queue
block layer code. This patch unifies ioc priority to request mapping across
the single/multi queue block layers.
I have tested this patch with the null block device driver with the following
parameters.
null_blk queue_mode=2 irqmode=0 use_per_node_hctx=1 nr_devices=1
I have not seen a performance regression with this patch and I would appreciate
any feedback or additional testing.
I have also verified that io priorities are passed to the device when using
the SQ and MQ path to a SATA HDD that supports io priorities.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Adam Manzanares <adam.manzanares@wdc.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Commit a4d907b6a3 unified the single and multi queue request handlers,
but in the process, it also screwed up the locking balance and calls
blk_mq_try_issue_directly() with the ctx preempt lock held. This is a
problem for drivers that have set BLK_MQ_F_BLOCKING, since now they
can't reliably sleep.
While in there, protect against similar issues in the future, by adding
a might_sleep() trigger in the BLOCKING path for direct issue or queue
run.
Reported-by: Josef Bacik <josef@toxicpanda.com>
Tested-by: Josef Bacik <josef@toxicpanda.com>
Fixes: a4d907b6a3 ("blk-mq: streamline blk_mq_make_request")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
trivial fix to spelling mistake in pr_err error message
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
In blk_mq_alloc_request_hctx, blk_mq_sched_get_request doesn't
get sw context so we don't need to put the context with
blk_mq_put_ctx. Unless, we will see preempt counter underflow.
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
In blk_mq_alloc_request_hctx, blk_mq_sched_get_request doesn't
get sw context so we don't need to put the context with
blk_mq_put_ctx. Unless, we will see preempt counter underflow.
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
Currently we return true in blk_mq_dispatch_rq_list() if we queued IO
successfully, but we really want to return whether or not the we made
progress. Progress includes if we got an error return. If we don't,
this can lead to a hang in blk_mq_sched_dispatch_requests() when a
driver is draining IO by returning BLK_MQ_QUEUE_ERROR instead of
manually ending the IO in error and return BLK_MQ_QUEUE_OK.
Tested-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When try to issue a request directly and we fail we will requeue the
request, but call blk_mq_end_request() as well. This leads to the
completed request being on a queuelist and getting ended twice, which
causes list corruption in schedulers and other shenanigans.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
blkg_conf_prep() currently calls blkg_lookup_create() while holding
request queue spinlock. This means allocating memory for struct
blkcg_gq has to be made non-blocking. This causes occasional -ENOMEM
failures in call paths like below:
pcpu_alloc+0x68f/0x710
__alloc_percpu_gfp+0xd/0x10
__percpu_counter_init+0x55/0xc0
cfq_pd_alloc+0x3b2/0x4e0
blkg_alloc+0x187/0x230
blkg_create+0x489/0x670
blkg_lookup_create+0x9a/0x230
blkg_conf_prep+0x1fb/0x240
__cfqg_set_weight_device.isra.105+0x5c/0x180
cfq_set_weight_on_dfl+0x69/0xc0
cgroup_file_write+0x39/0x1c0
kernfs_fop_write+0x13f/0x1d0
__vfs_write+0x23/0x120
vfs_write+0xc2/0x1f0
SyS_write+0x44/0xb0
entry_SYSCALL_64_fastpath+0x18/0xad
In the code path above, percpu allocator cannot call vmalloc() due to
queue spinlock.
A failure in this call path gives grief to tools which are trying to
configure io weights. We see occasional failures happen shortly after
reboots even when system is not under any memory pressure. Machines
with a lot of cpus are more vulnerable to this condition.
Do struct blkcg_gq allocations outside the queue spinlock to allow
blocking during memory allocations.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
I inadvertently applied the v5 version of this patch, whereas
the agreed upon version was v5. Revert this one so we can apply
the right one.
This reverts commit 7fc6b87a9f.
CONFIG_DEBUG_TEST_DRIVER_REMOVE found a possible leak of q->rq_wb when a
request queue is reregistered. This has been a problem since wbt was
introduced, but the WARN_ON(!list_empty(&stats->callbacks)) in the
blk-stat rework exposed it. Fix it by cleaning up wbt when we unregister
the queue.
Fixes: 87760e5eef ("block: hook up writeback throttling")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_alloc_queue_node() already allocates q->stats, so
blk_mq_init_allocated_queue() is overwriting it with a new allocation.
Fixes: a83b576c9c ("block: fix stacked driver stats init and free")
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Now that the remaining drivers have been converted to one request queue
per gendisk, let's warn if a request queue gets registered more than
once. This will catch future drivers which might do it inadvertently or
any old drivers that I may have missed.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Before commit 780db2071a(blk-mq: decouble blk-mq freezing
from generic bypassing), the dying flag is checked before
entering queue, and Tejun converts the checking into .mq_freeze_depth,
and assumes the counter is increased just after dying flag
is set. Unfortunately we doesn't do that in blk_set_queue_dying().
This patch calls blk_freeze_queue_start() in blk_set_queue_dying(),
so that we can block new I/O coming once the queue is set as dying.
Given blk_set_queue_dying() is always called in remove path
of block device, and queue will be cleaned up later, we don't
need to worry about undoing the counter.
Cc: Tejun Heo <tj@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
As the .q_usage_counter is used by both legacy and
mq path, we need to block new I/O if queue becomes
dead in blk_queue_enter().
So rename it and we can use this function in both
paths.
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Without the barrier, reading DEAD flag of .q_usage_counter
and reading .mq_freeze_depth may be reordered, then the
following wait_event_interruptible() may never return.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch adds comment on two races related with
timeout handler:
- requeue from queue busy vs. timeout
- rq free & reallocation vs. timeout
Both the races themselves and current solution aren't
explicit enough, so add comments on them.
Cc: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
blkg_conf_prep() currently calls blkg_lookup_create() while holding
request queue spinlock. This means allocating memory for struct
blkcg_gq has to be made non-blocking. This causes occasional -ENOMEM
failures in call paths like below:
pcpu_alloc+0x68f/0x710
__alloc_percpu_gfp+0xd/0x10
__percpu_counter_init+0x55/0xc0
cfq_pd_alloc+0x3b2/0x4e0
blkg_alloc+0x187/0x230
blkg_create+0x489/0x670
blkg_lookup_create+0x9a/0x230
blkg_conf_prep+0x1fb/0x240
__cfqg_set_weight_device.isra.105+0x5c/0x180
cfq_set_weight_on_dfl+0x69/0xc0
cgroup_file_write+0x39/0x1c0
kernfs_fop_write+0x13f/0x1d0
__vfs_write+0x23/0x120
vfs_write+0xc2/0x1f0
SyS_write+0x44/0xb0
entry_SYSCALL_64_fastpath+0x18/0xad
In the code path above, percpu allocator cannot call vmalloc() due to
queue spinlock.
A failure in this call path gives grief to tools which are trying to
configure io weights. We see occasional failures happen shortly after
reboots even when system is not under any memory pressure. Machines
with a lot of cpus are more vulnerable to this condition.
Update blkg_create() function to temporarily drop the rcu and queue
locks when it is allowed by gfp mask.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
One hard problem adding .low limit is to detect idle cgroup. If one
cgroup doesn't dispatch enough IO against its low limit, we must have a
mechanism to determine if other cgroups dispatch more IO. We added the
think time detection mechanism before, but it doesn't work for all
workloads. Here we add a latency based approach.
We already have mechanism to calculate latency threshold for each IO
size. For every IO dispatched from a cgorup, we compare its latency
against its threshold and record the info. If most IO latency is below
threshold (in the code I use 75%), the cgroup could be treated idle and
other cgroups can dispatch more IO.
Currently this latency target check is only for SSD as we can't
calcualte the latency target for hard disk. And this is only for cgroup
leaf node so far.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
User configures latency target, but the latency threshold for each
request size isn't fixed. For a SSD, the IO latency highly depends on
request size. To calculate latency threshold, we sample some data, eg,
average latency for request size 4k, 8k, 16k, 32k .. 1M. The latency
threshold of each request size will be the sample latency (I'll call it
base latency) plus latency target. For example, the base latency for
request size 4k is 80us and user configures latency target 60us. The 4k
latency threshold will be 80 + 60 = 140us.
To sample data, we calculate the order base 2 of rounded up IO sectors.
If the IO size is bigger than 1M, it will be accounted as 1M. Since the
calculation does round up, the base latency will be slightly smaller
than actual value. Also if there isn't any IO dispatched for a specific
IO size, we will use the base latency of smaller IO size for this IO
size.
But we shouldn't sample data at any time. The base latency is supposed
to be latency where disk isn't congested, because we use latency
threshold to schedule IOs between cgroups. If disk is congested, the
latency is higher, using it for scheduling is meaningless. Hence we only
do the sampling when block throttling is in the LOW limit, with
assumption disk isn't congested in such state. If the assumption isn't
true, eg, low limit is too high, calculated latency threshold will be
higher.
Hard disk is completely different. Latency depends on spindle seek
instead of request size. Currently this feature is SSD only, we probably
can use a fixed threshold like 4ms for hard disk though.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Currently there is no way to know the request size when the request is
finished. Next patch will need this info. We could add extra field to
record the size, but blk_issue_stat has enough space to record it, so
this patch just overloads blk_issue_stat. With this, we will have 49bits
to track time, which still is very long time.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Here we introduce per-cgroup latency target. The target determines how a
cgroup can afford latency increasement. We will use the target latency
to calculate a threshold and use it to schedule IO for cgroups. If a
cgroup's bandwidth is below its low limit but its average latency is
below the threshold, other cgroups can safely dispatch more IO even
their bandwidth is higher than their low limits. On the other hand, if
the first cgroup's latency is higher than the threshold, other cgroups
are throttled to their low limits. So the target latency determines how
we efficiently utilize free disk resource without sacifice of worload's
IO latency.
For example, assume 4k IO average latency is 50us when disk isn't
congested. A cgroup sets the target latency to 30us. Then the cgroup can
accept 50+30=80us IO latency. If the cgroupt's average IO latency is
90us and its bandwidth is below low limit, other cgroups are throttled
to their low limit. If the cgroup's average IO latency is 60us, other
cgroups are allowed to dispatch more IO. When other cgroups dispatch
more IO, the first cgroup's IO latency will increase. If it increases to
81us, we then throttle other cgroups.
User will configure the interface in this way:
echo "8:16 rbps=2097152 wbps=max latency=100 idle=200" > io.low
latency is in microsecond unit
By default, latency target is 0, which means to guarantee IO latency.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Last patch introduces a way to detect idle cgroup. We use it to make
upgrade/downgrade decision. And the new algorithm can detect completely
idle cgroup too, so we can delete the corresponding code.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Add interface to configure the threshold. The io.low interface will
like:
echo "8:16 rbps=2097152 wbps=max idle=2000" > io.low
idle is in microsecond unit.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A cgroup gets assigned a low limit, but the cgroup could never dispatch
enough IO to cross the low limit. In such case, the queue state machine
will remain in LIMIT_LOW state and all other cgroups will be throttled
according to low limit. This is unfair for other cgroups. We should
treat the cgroup idle and upgrade the state machine to lower state.
We also have a downgrade logic. If the state machine upgrades because of
cgroup idle (real idle), the state machine will downgrade soon as the
cgroup is below its low limit. This isn't what we want. A more
complicated case is cgroup isn't idle when queue is in LIMIT_LOW. But
when queue gets upgraded to lower state, other cgroups could dispatch
more IO and this cgroup can't dispatch enough IO, so the cgroup is below
its low limit and looks like idle (fake idle). In this case, the queue
should downgrade soon. The key to determine if we should do downgrade is
to detect if cgroup is truely idle.
Unfortunately it's very hard to determine if a cgroup is real idle. This
patch uses the 'think time check' idea from CFQ for the purpose. Please
note, the idea doesn't work for all workloads. For example, a workload
with io depth 8 has disk utilization 100%, hence think time is 0, eg,
not idle. But the workload can run higher bandwidth with io depth 16.
Compared to io depth 16, the io depth 8 workload is idle. We use the
idea to roughly determine if a cgroup is idle.
We treat a cgroup idle if its think time is above a threshold (by
default 1ms for SSD and 100ms for HD). The idea is think time above the
threshold will start to harm performance. HD is much slower so a longer
think time is ok.
The patch (and the latter patches) uses 'unsigned long' to track time.
We convert 'ns' to 'us' with 'ns >> 10'. This is fast but loses
precision, should not a big deal.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When cgroups all reach low limit, cgroups can dispatch more IO. This
could make some cgroups dispatch more IO but others not, and even some
cgroups could dispatch less IO than their low limit. For example, cg1
low limit 10MB/s, cg2 limit 80MB/s, assume disk maximum bandwidth is
120M/s for the workload. Their bps could something like this:
cg1/cg2 bps: T1: 10/80 -> T2: 60/60 -> T3: 10/80
At T1, all cgroups reach low limit, so they can dispatch more IO later.
Then cg1 dispatch more IO and cg2 has no room to dispatch enough IO. At
T2, cg2 only dispatches 60M/s. Since We detect cg2 dispatches less IO
than its low limit 80M/s, we downgrade the queue from LIMIT_MAX to
LIMIT_LOW, then all cgroups are throttled to their low limit (T3). cg2
will have bandwidth below its low limit at most time.
The big problem here is we don't know the maximum bandwidth of the
workload, so we can't make smart decision to avoid the situation. This
patch makes cgroup bandwidth change smooth. After disk upgrades from
LIMIT_LOW to LIMIT_MAX, we don't allow cgroups use all bandwidth upto
their max limit immediately. Their bandwidth limit will be increased
gradually to avoid above situation. So above example will became
something like:
cg1/cg2 bps: 10/80 -> 15/105 -> 20/100 -> 25/95 -> 30/90 -> 35/85 -> 40/80
-> 45/75 -> 22/98
In this way cgroups bandwidth will be above their limit in majority
time, this still doesn't fully utilize disk bandwidth, but that's
something we pay for sharing.
Scale up is linear. The limit scales up 1/2 .low limit every
throtl_slice after upgrade. The scale up will stop if the adjusted limit
hits .max limit. Scale down is exponential. We cut the scale value half
if a cgroup doesn't hit its .low limit. If the scale becomes 0, we then
fully downgrade the queue to LIMIT_LOW state.
Note this doesn't completely avoid cgroup running under its low limit.
The best way to guarantee cgroup doesn't run under its limit is to set
max limit. For example, if we set cg1 max limit to 40, cg2 will never
run under its low limit.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
cgroup could be assigned a limit, but doesn't dispatch enough IO, eg the
cgroup is idle. When this happens, the cgroup doesn't hit its limit, so
we can't move the state machine to higher level and all cgroups will be
throttled to their lower limit, so we waste bandwidth. Detecting idle
cgroup is hard. This patch handles a simple case, a cgroup doesn't
dispatch any IO. We ignore such cgroup's limit, so other cgroups can use
the bandwidth.
Please note this will be replaced with a more sophisticated algorithm
later, but this demonstrates the idea how we handle idle cgroups, so I
leave it here.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The throtl_slice is 100ms by default. This is a long time for SSD, a lot
of IO can run. To make cgroups have smoother throughput, we choose a
small value (20ms) for SSD.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
throtl_slice is important for blk-throttling. It's called slice
internally but it really is a time window blk-throttling samples data.
blk-throttling will make decision based on the samplings. An example is
bandwidth measurement. A cgroup's bandwidth is measured in the time
interval of throtl_slice.
A small throtl_slice meanse cgroups have smoother throughput but burn
more CPUs. It has 100ms default value, which is not appropriate for all
disks. A fast SSD can dispatch a lot of IOs in 100ms. This patch makes
it tunable.
Since throtl_slice isn't a time slice, the sysfs name
'throttle_sample_time' reflects its character better.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
cgroup could be throttled to a limit but when all cgroups cross high
limit, queue enters a higher state and so the group should be throttled
to a higher limit. It's possible the cgroup is sleeping because of
throttle and other cgroups don't dispatch IO any more. In this case,
nobody can trigger current downgrade/upgrade logic. To fix this issue,
we could either set up a timer to wakeup the cgroup if other cgroups are
idle or make sure this cgroup doesn't sleep too long. Setting up a timer
means we must change the timer very frequently. This patch chooses the
latter. Making cgroup sleep time not too big wouldn't change cgroup
bps/iops, but could make it wakeup more frequently, which isn't a big
issue because throtl_slice * 8 is already quite big.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When queue state machine is in LIMIT_MAX state, but a cgroup is below
its low limit for some time, the queue should be downgraded to lower
state as one cgroup's low limit isn't met.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When queue is in LIMIT_LOW state and all cgroups with low limit cross
the bps/iops limitation, we will upgrade queue's state to
LIMIT_MAX. To determine if a cgroup exceeds its limitation, we check if
the cgroup has pending request. Since cgroup is throttled according to
the limit, pending request means the cgroup reaches the limit.
If a cgroup has limit set for both read and write, we consider the
combination of them for upgrade. The reason is read IO and write IO can
interfere with each other. If we do the upgrade based in one direction
IO, the other direction IO could be severly harmed.
For a cgroup hierarchy, there are two cases. Children has lower low
limit than parent. Parent's low limit is meaningless. If children's
bps/iops cross low limit, we can upgrade queue state. The other case is
children has higher low limit than parent. Children's low limit is
meaningless. As long as parent's bps/iops (which is a sum of childrens
bps/iops) cross low limit, we can upgrade queue state.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
each queue will have a state machine. Initially queue is in LIMIT_LOW
state, which means all cgroups will be throttled according to their low
limit. After all cgroups with low limit cross the limit, the queue state
gets upgraded to LIMIT_MAX state.
For max limit, cgroup will use the limit configured by user.
For low limit, cgroup will use the minimal value between low limit and
max limit configured by user. If the minimal value is 0, which means the
cgroup doesn't configure low limit, we will use max limit to throttle
the cgroup and the cgroup is ready to upgrade to LIMIT_MAX
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Add low limit for cgroup and corresponding cgroup interface. To be
consistent with memcg, we allow users configure .low limit higher than
.max limit. But the internal logic always assumes .low limit is lower
than .max limit. So we add extra bps/iops_conf fields in throtl_grp for
userspace configuration. Old bps/iops fields in throtl_grp will be the
actual limit we use for throttling.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
As discussed in LSF, add configure option for the interface and mark it
as experimental, so people can try/test.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We are going to support low/max limit, each cgroup will have 2 limits
after that. This patch prepares for the multiple limits change.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
commit c18a1e0(block: introduce bio_clone_bioset_partial()) introduced
bio_clone_bioset_partial() for raid1 write behind IO. Now the write behind is
rewritten by Ming. We don't need the API any more, so revert the commit.
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
blk_integrity_profile's are never modified, so mark them 'const' so that
they are placed in .rodata and benefit from memory protection.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Paolo Valente