linux_old1/block/blk-rq-qos.h

228 lines
5.6 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef RQ_QOS_H
#define RQ_QOS_H
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/blk_types.h>
#include <linux/atomic.h>
#include <linux/wait.h>
block: fix race between adding/removing rq qos and normal IO Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang@redhat.com> Cc: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Yi Zhang <yi.zhang@redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-09 09:58:21 +08:00
#include <linux/blk-mq.h>
#include "blk-mq-debugfs.h"
struct blk_mq_debugfs_attr;
enum rq_qos_id {
RQ_QOS_WBT,
RQ_QOS_LATENCY,
blkcg: implement blk-iocost This patchset implements IO cost model based work-conserving proportional controller. While io.latency provides the capability to comprehensively prioritize and protect IOs depending on the cgroups, its protection is binary - the lowest latency target cgroup which is suffering is protected at the cost of all others. In many use cases including stacking multiple workload containers in a single system, it's necessary to distribute IO capacity with better granularity. One challenge of controlling IO resources is the lack of trivially observable cost metric. The most common metrics - bandwidth and iops - can be off by orders of magnitude depending on the device type and IO pattern. However, the cost isn't a complete mystery. Given several key attributes, we can make fairly reliable predictions on how expensive a given stream of IOs would be, at least compared to other IO patterns. The function which determines the cost of a given IO is the IO cost model for the device. This controller distributes IO capacity based on the costs estimated by such model. The more accurate the cost model the better but the controller adapts based on IO completion latency and as long as the relative costs across differents IO patterns are consistent and sensible, it'll adapt to the actual performance of the device. Currently, the only implemented cost model is a simple linear one with a few sets of default parameters for different classes of device. This covers most common devices reasonably well. All the infrastructure to tune and add different cost models is already in place and a later patch will also allow using bpf progs for cost models. Please see the top comment in blk-iocost.c and documentation for more details. v2: Rebased on top of RQ_ALLOC_TIME changes and folded in Rik's fix for a divide-by-zero bug in current_hweight() triggered by zero inuse_sum. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Andy Newell <newella@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-29 06:05:58 +08:00
RQ_QOS_COST,
RQ_QOS_IOPRIO,
};
struct rq_wait {
wait_queue_head_t wait;
atomic_t inflight;
};
struct rq_qos {
struct rq_qos_ops *ops;
struct request_queue *q;
enum rq_qos_id id;
struct rq_qos *next;
#ifdef CONFIG_BLK_DEBUG_FS
struct dentry *debugfs_dir;
#endif
};
struct rq_qos_ops {
void (*throttle)(struct rq_qos *, struct bio *);
void (*track)(struct rq_qos *, struct request *, struct bio *);
void (*merge)(struct rq_qos *, struct request *, struct bio *);
void (*issue)(struct rq_qos *, struct request *);
void (*requeue)(struct rq_qos *, struct request *);
void (*done)(struct rq_qos *, struct request *);
void (*done_bio)(struct rq_qos *, struct bio *);
void (*cleanup)(struct rq_qos *, struct bio *);
void (*queue_depth_changed)(struct rq_qos *);
void (*exit)(struct rq_qos *);
const struct blk_mq_debugfs_attr *debugfs_attrs;
};
struct rq_depth {
unsigned int max_depth;
int scale_step;
bool scaled_max;
unsigned int queue_depth;
unsigned int default_depth;
};
static inline struct rq_qos *rq_qos_id(struct request_queue *q,
enum rq_qos_id id)
{
struct rq_qos *rqos;
for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
if (rqos->id == id)
break;
}
return rqos;
}
static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
{
return rq_qos_id(q, RQ_QOS_WBT);
}
static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
{
return rq_qos_id(q, RQ_QOS_LATENCY);
}
static inline void rq_wait_init(struct rq_wait *rq_wait)
{
atomic_set(&rq_wait->inflight, 0);
init_waitqueue_head(&rq_wait->wait);
}
static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
{
block: fix race between adding/removing rq qos and normal IO Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang@redhat.com> Cc: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Yi Zhang <yi.zhang@redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-09 09:58:21 +08:00
/*
* No IO can be in-flight when adding rqos, so freeze queue, which
* is fine since we only support rq_qos for blk-mq queue.
*
* Reuse ->queue_lock for protecting against other concurrent
* rq_qos adding/deleting
*/
blk_mq_freeze_queue(q);
spin_lock_irq(&q->queue_lock);
rqos->next = q->rq_qos;
q->rq_qos = rqos;
block: fix race between adding/removing rq qos and normal IO Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang@redhat.com> Cc: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Yi Zhang <yi.zhang@redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-09 09:58:21 +08:00
spin_unlock_irq(&q->queue_lock);
blk_mq_unfreeze_queue(q);
if (rqos->ops->debugfs_attrs) {
mutex_lock(&q->debugfs_mutex);
blk_mq_debugfs_register_rqos(rqos);
mutex_unlock(&q->debugfs_mutex);
}
}
static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
{
struct rq_qos **cur;
block: fix race between adding/removing rq qos and normal IO Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang@redhat.com> Cc: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Yi Zhang <yi.zhang@redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-09 09:58:21 +08:00
/*
* See comment in rq_qos_add() about freezing queue & using
* ->queue_lock.
*/
blk_mq_freeze_queue(q);
spin_lock_irq(&q->queue_lock);
for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
if (*cur == rqos) {
*cur = rqos->next;
break;
}
}
block: fix race between adding/removing rq qos and normal IO Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang@redhat.com> Cc: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Yi Zhang <yi.zhang@redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-09 09:58:21 +08:00
spin_unlock_irq(&q->queue_lock);
blk_mq_unfreeze_queue(q);
mutex_lock(&q->debugfs_mutex);
blk_mq_debugfs_unregister_rqos(rqos);
mutex_unlock(&q->debugfs_mutex);
}
typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data);
typedef void (cleanup_cb_t)(struct rq_wait *rqw, void *private_data);
void rq_qos_wait(struct rq_wait *rqw, void *private_data,
acquire_inflight_cb_t *acquire_inflight_cb,
cleanup_cb_t *cleanup_cb);
bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
bool rq_depth_scale_up(struct rq_depth *rqd);
bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
bool rq_depth_calc_max_depth(struct rq_depth *rqd);
void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio);
void __rq_qos_done(struct rq_qos *rqos, struct request *rq);
void __rq_qos_issue(struct rq_qos *rqos, struct request *rq);
void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq);
void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio);
void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio);
void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio);
void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio);
void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
{
if (q->rq_qos)
__rq_qos_cleanup(q->rq_qos, bio);
}
static inline void rq_qos_done(struct request_queue *q, struct request *rq)
{
if (q->rq_qos)
__rq_qos_done(q->rq_qos, rq);
}
static inline void rq_qos_issue(struct request_queue *q, struct request *rq)
{
if (q->rq_qos)
__rq_qos_issue(q->rq_qos, rq);
}
static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
{
if (q->rq_qos)
__rq_qos_requeue(q->rq_qos, rq);
}
block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei <ming.lei@redhat.com> Cc: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-14 15:15:02 +08:00
static inline void rq_qos_done_bio(struct bio *bio)
{
block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei <ming.lei@redhat.com> Cc: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-14 15:15:02 +08:00
if (bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
bio_flagged(bio, BIO_QOS_MERGED))) {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
if (q->rq_qos)
__rq_qos_done_bio(q->rq_qos, bio);
}
}
static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
{
if (q->rq_qos) {
block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei <ming.lei@redhat.com> Cc: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-14 15:15:02 +08:00
bio_set_flag(bio, BIO_QOS_THROTTLED);
__rq_qos_throttle(q->rq_qos, bio);
}
}
static inline void rq_qos_track(struct request_queue *q, struct request *rq,
struct bio *bio)
{
if (q->rq_qos)
__rq_qos_track(q->rq_qos, rq, bio);
}
static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
{
block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei <ming.lei@redhat.com> Cc: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-14 15:15:02 +08:00
if (q->rq_qos) {
bio_set_flag(bio, BIO_QOS_MERGED);
__rq_qos_merge(q->rq_qos, rq, bio);
block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei <ming.lei@redhat.com> Cc: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-14 15:15:02 +08:00
}
}
static inline void rq_qos_queue_depth_changed(struct request_queue *q)
{
if (q->rq_qos)
__rq_qos_queue_depth_changed(q->rq_qos);
}
void rq_qos_exit(struct request_queue *);
#endif