Dan reported this:
The patch 2984c8684f96: "nullb: factor disk parameters" from Aug 14,
2017, leads to the following Smatch complaint:
drivers/block/null_blk.c:1759 null_init_tag_set()
error: we previously assumed 'nullb' could be null (see line
1750)
1755 set->cmd_size = sizeof(struct nullb_cmd);
1756 set->flags = BLK_MQ_F_SHOULD_MERGE;
1757 set->driver_data = NULL;
1758
1759 if (nullb->dev->blocking)
^^^^^^^^^^^^^^^^^^^^
And an unchecked dereference.
nullb could be NULL here.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Sometime disk could have tracks broken and data there is inaccessable,
but data in other parts can be accessed in normal way. MD RAID supports
such disks. But we don't have a good way to test it, because we can't
control which part of a physical disk is bad. For a virtual disk, this
can be easily controlled.
This patch adds a new 'badblock' attribute. Configure it in this way:
echo "+1-100" > xxx/badblock, this will make sector [1-100] as bad
blocks.
echo "-20-30" > xxx/badblock, this will make sector [20-30] good
If badblocks are accessed, the nullb disk will return IO error. Other
parts of the disk can accessed in normal way.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Software must flush disk cache to guarantee data safety. To check if
software correctly does disk cache flush, we must know the behavior of
disk. But physical disk behavior is uncontrollable. Even software
doesn't do the flush, the disk probably does the flush. This patch tries
to emulate a cache in the test disk.
All write will go to a cache first, when the cache is full, we then
flush some data to disk storage. A flush request will flush all data of
the cache to disk storage. A FUA write will write to memory store
directly and revalidate data in cache. If there is a power failure (by
writing to power attribute, 'echo 0 > disk_name/power'), we discard all
data in the cache, but preserve the data in disk storage. Later we can
power on the disk again as usual (write 1 to 'power' attribute), then we
can check data integrity and very if software does everything correctly.
A new attribute 'cache_size' (in MB) is added to configure cache size.
Based on original patch from Kyungchan Koh
Signed-off-by: Kyungchan Koh <kkc6196@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In test, we usually expect controllable disk speed. For example, in a
raid array, we'd like some disks are fast and some are slow. MD RAID
actually has a feature for this. To test the feature, we'd like to make
the disk run in specific speed.
block throttling probably can be used for this purpose, but it requires
cgroup setup. Here we just implement a simple throttling mechanism in
the driver. There is slight fluctuation in the mechanism, but it's good
enough for test.
To configure the bandwidth cap, user sets the 'mbps' attribute. mbps is
MB/s.
Based on original patch from Kyungchan Koh
Signed-off-by: Kyungchan Koh <kkc6196@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
discard makes sense for memory backed disk. And also it's useful to test
if upper layer supports dicard correctly.
User configures 'discard' attribute to enable/disable dicard support.
Based on original patch from Kyungchan Koh
Signed-off-by: Kyungchan Koh <kkc6196@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This adds memory backed store in nullb.
User configure 'memory_backed' attribute for this. By default, nullb
disk doesn't use memory backed store.
Based on original patch from Kyungchan Koh
Signed-off-by: Kyungchan Koh <kkc6196@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We now dynamically create disks. Managing the disk index with ida to
avoid bump up the index too much.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The device created in nullb configfs interface isn't power on by
default. After user configures the device, user can do 'echo 1 >
xxx/nullb/device_name/power' to power on the device, which will create a
disk. the xxx/nullb/device_name/index is the disk index, so if the index
is 2, the new created disk should be named as /dev/nullb2. Note, the
'index' is only valid after disk is power on.
'echo 0 > xxx/nullb/device_name/power' will remove the disk. Note, this
doesn't remove the device. To remove the device, user should do 'rmdir
xxx/nullb/device_name'. Removing the device will remove the disk too.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add configfs interface for nullb. configfs interface is more flexible
and easy to configure in a per-disk basis.
Configuration is something like this:
mount -t configfs none /mnt
Checking which features the driver supports:
cat /mnt/nullb/features
The 'features' attribute is for future extension. We probably will add
new features into the driver, userspace can check this attribute to find
the supported features.
Create/remove a device:
mkdir/rmdir /mnt/nullb/a
Then configure the device by setting attributes under /mnt/nullb/a, most
of nullb supported module parameters are converted to attributes:
size; /* device size in MB */
completion_nsec; /* time in ns to complete a request */
submit_queues; /* number of submission queues */
home_node; /* home node for the device */
queue_mode; /* block interface */
blocksize; /* block size */
irqmode; /* IRQ completion handler */
hw_queue_depth; /* queue depth */
use_lightnvm; /* register as a LightNVM device */
blocking; /* blocking blk-mq device */
use_per_node_hctx; /* use per-node allocation for hardware context */
Note, creating a device doesn't create a disk immediately. Creating a
disk is done in two phases: create a device and then power on the
device. Next patch will introduce device power on.
Based on original patch from Kyungchan Koh
Signed-off-by: Kyungchan Koh <kkc6196@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When we switch to configfs interface, each disk could have different
configuration. To prepare for the change, we move most disk setting to a
separate data structure. The existing module parameter interface is
kept. The 'nr_devices' and 'shared_tags' don't make sense for per-disk
setting, so they are remained as global settings.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
set submit_queues to 1 by default, and make sure it's value > 0.
Signed-off-by: weiping zhang <zhangweiping@didichuxing.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In case we use shared tags feature, blk_mq_alloc_tag_set might fail
during module initialization. In that case, fail the load with a
suitable error code. Also move the tagset initialization process after
defining the amount of submission queues.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some storage drivers need to share tag sets between devices. It's
useful to be able to model that with null_blk, to find hangs or
performance issues.
Add a 'shared_tags' bool module parameter that. If that is set to
true and nr_devices is bigger than 1, all devices allocated will
share the same tag set.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
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>
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 patch changes the behavior of the null_blk driver for the
LightNVM mode as follows:
* REQ_FAILFAST_MASK is set for read-ahead requests.
* If no I/O priority has been set in the bio, the I/O priority is
copied from the I/O context.
* The rq_disk member is initialized if bio->bi_bdev != NULL.
* req->errors is initialized to zero.
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>
Constify all instances of blk_mq_ops, as they are never modified.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This adds a new module parameter to null_blk, blocking. If set, null_blk
will set the BLK_MQ_F_BLOCKING flag, indicating that it sometimes/always
needs to block in its ->queue_rq() function. The intent is to help find
regressions in blocking drivers, since not many of them exist.
If null_blk is loaded with submit_queues > 1 and blocking=1, this
shows the regression recently fixed by bf4907c05e.
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Instead of keeping two levels of indirection for requests types, fold it
all into the operations. The little caveat here is that previously
cmd_type only applied to struct request, while the request and bio op
fields were set to plain REQ_OP_READ/WRITE even for passthrough
operations.
Instead this patch adds new REQ_OP_* for SCSI passthrough and driver
private requests, althought it has to add two for each so that we
can communicate the data in/out nature of the request.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
When the lightnvm core had the "gennvm" layer between the device and the
target, there was a need for the core to be able to figure out which
target it should send an end_io callback to. Leading to a "double"
end_io, first for the media manager instance, and then for the target
instance. Now that core and gennvm is merged, there is no longer a need
for this, and a single end_io callback will do.
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The number of configuration groups has been limited to one in current
code, even if there is support for up to four. With the introduction
of the open-channel SSD 1.3 specification, only a single
group is exposed onwards. Reflect this in the nvm_id structure.
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
ktime_set(S,N) was required for the timespec storage type and is still
useful for situations where a Seconds and Nanoseconds part of a time value
needs to be converted. For anything where the Seconds argument is 0, this
is pointless and can be replaced with a simple assignment.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
If CONFIG_NVM is disabled, loading null_block module with use_lightnvm=1
fails. But there are no messages and documents related to the failure.
Add the appropriate error message.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Massaged the text a bit.
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull blk-mq irq/cpu mapping updates from Jens Axboe:
"This is the block-irq topic branch for 4.9-rc. It's mostly from
Christoph, and it allows drivers to specify their own mappings, and
more importantly, to share the blk-mq mappings with the IRQ affinity
mappings. It's a good step towards making this work better out of the
box"
* 'for-4.9/block-irq' of git://git.kernel.dk/linux-block:
blk_mq: linux/blk-mq.h does not include all the headers it depends on
blk-mq: kill unused blk_mq_create_mq_map()
blk-mq: get rid of the cpumask in struct blk_mq_tags
nvme: remove the post_scan callout
nvme: switch to use pci_alloc_irq_vectors
blk-mq: provide a default queue mapping for PCI device
blk-mq: allow the driver to pass in a queue mapping
blk-mq: remove ->map_queue
blk-mq: only allocate a single mq_map per tag_set
blk-mq: don't redistribute hardware queues on a CPU hotplug event
LightNVM compatible device drivers does not have a method to expose
LightNVM specific sysfs entries.
To enable LightNVM sysfs entries to be exposed, lightnvm device
drivers require a struct device to attach it to. To allow both the
actual device driver and lightnvm sysfs entries to coexist, the device
driver tracks the lifetime of the nvm_dev structure.
This patch refactors NVMe and null_blk to handle the lifetime of struct
nvm_dev, which eliminates the need for struct gendisk when a lightnvm
compatible device is provided.
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
With LightNVM enabled devices, the gendisk structure is not exposed
to the user. This hides the device driver specific sysfs entries, and
prevents binding of LightNVM geometry information to the device.
Refactor the device registration process, so that gendisk and
non-gendisk devices are easily managed.
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
All drivers use the default, so provide an inline version of it. If we
ever need other queue mapping we can add an optional method back,
although supporting will also require major changes to the queue setup
code.
This provides better code generation, and better debugability as well.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
These two are confusing leftover of the old world order, combining
values of the REQ_OP_ and REQ_ namespaces. For callers that don't
special case we mostly just replace bi_rw with bio_data_dir or
op_is_write, except for the few cases where a switch over the REQ_OP_
values makes more sense. Any check for READA is replaced with an
explicit check for REQ_RAHEAD. Also remove the READA alias for
REQ_RAHEAD.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
After register null_blk devices into lightnvm, we forget
to add these devices to the the nullb_list, makes them
invisible to the null_blk driver.
Signed-off-by: Wenwei Tao <ww.tao0320@gmail.com>
Fixes: a514379b0c ("null_blk: oops when initializing without lightnvm")
Signed-off-by: Jens Axboe <axboe@fb.com>
If the LightNVM subsystem is not compiled into the kernel, and the
null_blk device driver requests lightnvm to be initialized. The call to
nvm_register fails and the null_add_dev function cleans up the
initialization. However, at this point the null block device has
already been added to the nullb_list and thus a second cleanup will
occur when the function has returned, that leads to a double call to
blk_cleanup_queue.
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
System block allows the device to initialize with its configured media
manager. The system blocks is written to disk, and read again when media
manager is determined. For this to work, the backend must store the
data. Device drivers, such as null_blk, does not have any backend
storage. This patch allows the media manager to be initialized without a
storage backend.
It also fix incorrect configuration of capabilities in null_blk, as it
does not support get/set bad block interface.
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull lightnvm fixes and updates from Jens Axboe:
"This should have been part of the drivers branch, but it arrived a bit
late and wasn't based on the official core block driver branch. So
they got a small scolding, but got a pass since it's still new. Hence
it's in a separate branch.
This is mostly pure fixes, contained to lightnvm/, and minor feature
additions"
* 'for-4.5/lightnvm' of git://git.kernel.dk/linux-block: (26 commits)
lightnvm: ensure that nvm_dev_ops can be used without CONFIG_NVM
lightnvm: introduce factory reset
lightnvm: use system block for mm initialization
lightnvm: introduce ioctl to initialize device
lightnvm: core on-disk initialization
lightnvm: introduce mlc lower page table mappings
lightnvm: add mccap support
lightnvm: manage open and closed blocks separately
lightnvm: fix missing grown bad block type
lightnvm: reference rrpc lun in rrpc block
lightnvm: introduce nvm_submit_ppa
lightnvm: move rq->error to nvm_rq->error
lightnvm: support multiple ppas in nvm_erase_ppa
lightnvm: move the pages per block check out of the loop
lightnvm: sectors first in ppa list
lightnvm: fix locking and mempool in rrpc_lun_gc
lightnvm: put block back to gc list on its reclaim fail
lightnvm: check bi_error in gc
lightnvm: return the get_bb_tbl return value
lightnvm: refactor end_io functions for sync
...
Pull block driver updates from Jens Axboe:
"This is the block driver pull request for 4.5, with the exception of
NVMe, which is in a separate branch and will be posted after this one.
This pull request contains:
- A set of bcache stability fixes, which have been acked by Kent.
These have been used and tested for more than a year by the
community, so it's about time that they got in.
- A set of drbd updates from the drbd team (Andreas, Lars, Philipp)
and Markus Elfring, Oleg Drokin.
- A set of fixes for xen blkback/front from the usual suspects, (Bob,
Konrad) as well as community based fixes from Kiri, Julien, and
Peng.
- A 2038 time fix for sx8 from Shraddha, with a fix from me.
- A small mtip32xx cleanup from Zhu Yanjun.
- A null_blk division fix from Arnd"
* 'for-4.5/drivers' of git://git.kernel.dk/linux-block: (71 commits)
null_blk: use sector_div instead of do_div
mtip32xx: restrict variables visible in current code module
xen/blkfront: Fix crash if backend doesn't follow the right states.
xen/blkback: Fix two memory leaks.
xen/blkback: make st_ statistics per ring
xen/blkfront: Handle non-indirect grant with 64KB pages
xen-blkfront: Introduce blkif_ring_get_request
xen-blkback: clear PF_NOFREEZE for xen_blkif_schedule()
xen/blkback: Free resources if connect_ring failed.
xen/blocks: Return -EXX instead of -1
xen/blkback: make pool of persistent grants and free pages per-queue
xen/blkback: get the number of hardware queues/rings from blkfront
xen/blkback: pseudo support for multi hardware queues/rings
xen/blkback: separate ring information out of struct xen_blkif
xen/blkfront: correct setting for xen_blkif_max_ring_order
xen/blkfront: make persistent grants pool per-queue
xen/blkfront: Remove duplicate setting of ->xbdev.
xen/blkfront: Cleanup of comments, fix unaligned variables, and syntax errors.
xen/blkfront: negotiate number of queues/rings to be used with backend
xen/blkfront: split per device io_lock
...
Pull core block updates from Jens Axboe:
"We don't have a lot of core changes this time around, it's mostly in
drivers, which will come in a subsequent pull.
The cores changes include:
- blk-mq
- Prep patch from Christoph, changing blk_mq_alloc_request() to
take flags instead of just using gfp_t for sleep/nosleep.
- Doc patch from me, clarifying the difference between legacy
and blk-mq for timer usage.
- Fixes from Raghavendra for memory-less numa nodes, and a reuse
of CPU masks.
- Cleanup from Geliang Tang, using offset_in_page() instead of open
coding it.
- From Ilya, rename request_queue slab to it reflects what it holds,
and a fix for proper use of bdgrab/put.
- A real fix for the split across stripe boundaries from Keith. We
yanked a broken version of this from 4.4-rc final, this one works.
- From Mike Krinkin, emit a trace message when we split.
- From Wei Tang, two small cleanups, not explicitly clearing memory
that is already cleared"
* 'for-4.5/core' of git://git.kernel.dk/linux-block:
block: use bd{grab,put}() instead of open-coding
block: split bios to max possible length
block: add call to split trace point
blk-mq: Avoid memoryless numa node encoded in hctx numa_node
blk-mq: Reuse hardware context cpumask for tags
blk-mq: add a flags parameter to blk_mq_alloc_request
Revert "blk-flush: Queue through IO scheduler when flush not required"
block: clarify blk_add_timer() use case for blk-mq
bio: use offset_in_page macro
block: do not initialise statics to 0 or NULL
block: do not initialise globals to 0 or NULL
block: rename request_queue slab cache
Dividing a sector_t number should be done using sector_div rather than do_div
to optimize the 32-bit sector_t case, and with the latest do_div optimizations,
we now get a compile-time warning for this:
arch/arm/include/asm/div64.h:32:95: note: expected 'uint64_t * {aka long long unsigned int *}' but argument is of type 'sector_t * {aka long unsigned int *}'
drivers/block/null_blk.c:521:81: warning: comparison of distinct pointer types lacks a cast
This changes the newly added code to use sector_div. It is a simplified version
of the original patch, as Linus Torvalds pointed out that we should not be using
an expensive division function in the first place.
This version was suggested by Matias Bjorling.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Matias Bjorling <m@bjorling.me>
Fixes: b2b7e00148 ("null_blk: register as a LightNVM device")
Signed-off-by: Jens Axboe <axboe@fb.com>
To implement sync I/O support within the LightNVM core, the end_io
functions are refactored to take an end_io function pointer instead of
testing for initialized media manager, followed by calling its end_io
function.
Sync I/O can then be implemented using a callback that signal I/O
completion. This is similar to the logic found in blk_to_execute_io().
By implementing it this way, the underlying device I/Os submission logic
is abstracted away from core, targets, and media managers.
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
If null_blk is run in NULL_IRQ_TIMER mode and with queue_mode NULL_Q_RQ,
we need to restart the queue from the hrtimer interrupt. We can't
directly invoke the request_fn from that context, so punt the queue run
to async kblockd context.
Tested-by: Rabin Vincent <rabin@rab.in>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_end_request_all may free request, so we need to save
request_queue pointer before blk_end_request_all call.
The problem was introduced in commit cf8ecc5a84
("null_blk: guarantee device restart in all irq modes")
and causes general protection fault with slab poisoning
enabled.
Fixes: cf8ecc5a84 ("null_blk: guarantee device
restart in all irq modes")
Signed-off-by: Mike Krinkin <krinkin.m.u@gmail.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Module couldn't release resource properly during the initialization. To
fix this issue, we will clean up the proper resource before returning.
Signed-off-by: Minfei Huang <mnfhuang@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
In the case where a request queue is passed to the low lever lightnvm
device drive integration, the device driver might pass its admin
commands through another queue. Instead pass nvm_dev, and let the
low level drive the appropriate queue.
Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
We already have the reserved flag, and a nowait flag awkwardly encoded as
a gfp_t. Add a real flags argument to make the scheme more extensible and
allow for a nicer calling convention.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
This commit at least doubles the maximum value for
completion_nsec. This helps in special cases where one wants/needs to
emulate an extremely slow I/O (for example to spot bugs).
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Signed-off-by: Arianna Avanzini <avanzini@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
In single-queue (block layer) mode,the function null_rq_prep_fn stops
the device if alloc_cmd fails. Then, once stopped, the device must be
restarted on the next command completion, so that the request(s) for
which alloc_cmd failed can be requeued. Otherwise the device hangs.
Unfortunately, device restart is currently performed only for delayed
completions, i.e., in irqmode==2. This fact causes hangs, for the
above reasons, with the other irqmodes in combination with single-queue
block layer.
This commits addresses this issue by making sure that, if stopped, the
device is properly restarted for all irqmodes on completions.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Signed-off-by: Arianna AVanzini <avanzini@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
For the Timer IRQ mode (i.e., when command completions are delayed),
there is one timer for each CPU. Each of these timers
. has a completion queue associated with it, containing all the
command completions to be executed when the timer fires;
. is set, and a new completion-to-execute is inserted into its
completion queue, every time the dispatch code for a new command
happens to be executed on the CPU related to the timer.
This implies that, if the dispatch of a new command happens to be
executed on a CPU whose timer has already been set, but has not yet
fired, then the timer is set again, to the completion time of the
newly arrived command. When the timer eventually fires, all its queued
completions are executed.
This way of handling delayed command completions entails the following
problem: if more than one command completion is inserted into the
queue of a timer before the timer fires, then the expiration time for
the timer is moved forward every time each of these completions is
enqueued. As a consequence, only the last completion enqueued enjoys a
correct execution time, while all previous completions are unjustly
delayed until the last completion is executed (and at that time they
are executed all together).
Specifically, if all the above completions are enqueued almost at the
same time, then the problem is negligible. On the opposite end, if
every completion is enqueued a while after the previous completion was
enqueued (in the extreme case, it is enqueued only right before the
timer would have expired), then every enqueued completion, except for
the last one, experiences an inflated delay, proportional to the number
of completions enqueued after it. In the end, commands, and thus I/O
requests, may be completed at an arbitrarily lower rate than the
desired one.
This commit addresses this issue by replacing per-CPU timers with
per-command timers, i.e., by associating an individual timer with each
command.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Signed-off-by: Arianna Avanzini <avanzini@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The gendisk structure has not been initialized when using lightnvm.
Make sure to not delete it upon exit. Also make sure that we use the
appropriate disk_name at unregistration.
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
Shaohua Li