Rename deadline_is_seq_writes() to deadline_is_seq_write() (remove the
"s" plural) to more correctly reflect the fact that this function tests
a single request, not multiple requests.
Fixes: 015d02f485 ("block: mq-deadline: Do not break sequential write streams to zoned HDDs")
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Link: https://lore.kernel.org/r/20221126025550.967914-2-damien.lemoal@opensource.wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
mq-deadline ensures an in order dispatching of write requests to zoned
block devices using a per zone lock (a bit). This implies that for any
purely sequential write workload, the drive is exercised most of the
time at a maximum queue depth of one.
However, when such sequential write workload crosses a zone boundary
(when sequentially writing multiple contiguous zones), zone write
locking may prevent the last write to one zone to be issued (as the
previous write is still being executed) but allow the first write to the
following zone to be issued (as that zone is not yet being writen and
not locked). This result in an out of order delivery of the sequential
write commands to the device every time a zone boundary is crossed.
While such behavior does not break the sequential write constraint of
zoned block devices (and does not generate any write error), some zoned
hard-disks react badly to seeing these out of order writes, resulting in
lower write throughput.
This problem can be addressed by always dispatching the first request
of a stream of sequential write requests, regardless of the zones
targeted by these sequential writes. To do so, the function
deadline_skip_seq_writes() is introduced and used in
deadline_next_request() to select the next write command to issue if the
target device is an HDD (blk_queue_nonrot() being false).
deadline_fifo_request() is modified using the new
deadline_earlier_request() and deadline_is_seq_write() helpers to ignore
requests in the fifo list that have a preceding request in lba order
that is sequential.
With this fix, a sequential write workload executed with the following
fio command:
fio --name=seq-write --filename=/dev/sda --zonemode=zbd --direct=1 \
--size=68719476736 --ioengine=libaio --iodepth=32 --rw=write \
--bs=65536
results in an increase from 225 MB/s to 250 MB/s of the write throughput
of an SMR HDD (11% increase).
Cc: <stable@vger.kernel.org>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20221124021208.242541-3-damien.lemoal@opensource.wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
dd_finish_request() tests if the per prio fifo_list is not empty to
determine if request dispatching must be restarted for handling blocked
write requests to zoned devices with a call to
blk_mq_sched_mark_restart_hctx(). While simple, this implementation has
2 problems:
1) Only the priority level of the completed request is considered.
However, writes to a zone may be blocked due to other writes to the
same zone using a different priority level. While this is unlikely to
happen in practice, as writing a zone with different IO priorirites
does not make sense, nothing in the code prevents this from
happening.
2) The use of list_empty() is dangerous as dd_finish_request() does not
take dd->lock and may run concurrently with the insert and dispatch
code.
Fix these 2 problems by testing the write fifo list of all priority
levels using the new helper dd_has_write_work(), and by testing each
fifo list using list_empty_careful().
Fixes: c807ab520f ("block/mq-deadline: Add I/O priority support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20221124021208.242541-2-damien.lemoal@opensource.wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use the new blk_opf_t type for an argument that represents a bitwise
combination of a request operation and request flags. Rename that
argument from 'op' into 'opf'.
This patch does not change any functionality.
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20220714180729.1065367-9-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
q->elevator is referred in blk_mq_has_sqsched() without any protection,
no .q_usage_counter is held, no queue srcu and rcu read lock is held,
so potential use-after-free may be triggered.
Fix the issue by adding one queue flag for checking if the elevator
uses single queue style dispatch. Meantime the elevator feature flag
of ELEVATOR_F_MQ_AWARE isn't needed any more.
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220616014401.817001-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Before commit 322cff70d4 the fifo_time member of requests on a dispatch
list was not used. Commit 322cff70d4 introduces code that reads the
fifo_time member of requests on dispatch lists. Hence this patch that sets
the fifo_time member when adding a request to a dispatch list.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Fixes: 322cff70d4 ("block/mq-deadline: Prioritize high-priority requests")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20220513171307.32564-1-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A previous commit added this feature, but it inadvertently used the wrong
variable to show/store the setting from/to, victimized by copy/paste. Fix
it up so that the async_depth sysfs interface reads and writes from the
right setting.
Fixes: 07757588e5 ("block/mq-deadline: Reserve 25% of scheduler tags for synchronous requests")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215485
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now that we use shared tags for shared sbitmap support, we don't require
the tags sbitmap pointers, so drop them.
This essentially reverts commit 222a5ae03c ("blk-mq: Use pointers for
blk_mq_tags bitmap tags").
Function blk_mq_init_bitmap_tags() is removed also, since it would be only
a wrappper for blk_mq_init_bitmaps().
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1633429419-228500-14-git-send-email-john.garry@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In addition to reverting commit 7b05bf7710 ("Revert "block/mq-deadline:
Prioritize high-priority requests""), this patch uses 'jiffies' instead
of ktime_get() in the code for aging lower priority requests.
This patch has been tested as follows:
Measured QD=1/jobs=1 IOPS for nullb with the mq-deadline scheduler.
Result without and with this patch: 555 K IOPS.
Measured QD=1/jobs=8 IOPS for nullb with the mq-deadline scheduler.
Result without and with this patch: about 380 K IOPS.
Ran the following script:
set -e
scriptdir=$(dirname "$0")
if [ -e /sys/module/scsi_debug ]; then modprobe -r scsi_debug; fi
modprobe scsi_debug ndelay=1000000 max_queue=16
sd=''
while [ -z "$sd" ]; do
sd=$(basename /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*)
done
echo $((100*1000)) > "/sys/block/$sd/queue/iosched/prio_aging_expire"
if [ -e /sys/fs/cgroup/io.prio.class ]; then
cd /sys/fs/cgroup
echo restrict-to-be >io.prio.class
echo +io > cgroup.subtree_control
else
cd /sys/fs/cgroup/blkio/
echo restrict-to-be >blkio.prio.class
fi
echo $$ >cgroup.procs
mkdir -p hipri
cd hipri
if [ -e io.prio.class ]; then
echo none-to-rt >io.prio.class
else
echo none-to-rt >blkio.prio.class
fi
{ "${scriptdir}/max-iops" -a1 -d32 -j1 -e mq-deadline "/dev/$sd" >& ~/low-pri.txt & }
echo $$ >cgroup.procs
"${scriptdir}/max-iops" -a1 -d32 -j1 -e mq-deadline "/dev/$sd" >& ~/hi-pri.txt
Result:
* 11000 IOPS for the high-priority job
* 40 IOPS for the low-priority job
If the prio aging expiry time is changed from 100s into 0, the IOPS results
change into 6712 and 6796 IOPS.
The max-iops script is a script that runs fio with the following arguments:
--bs=4K --gtod_reduce=1 --ioengine=libaio --ioscheduler=${arg_e} --runtime=60
--norandommap --rw=read --thread --buffered=0 --numjobs=${arg_j}
--iodepth=${arg_d} --iodepth_batch_submit=${arg_a}
--iodepth_batch_complete=$((arg_d / 2)) --name=${positional_argument_1}
--filename=${positional_argument_1}
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Niklas Cassel <Niklas.Cassel@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Link: https://lore.kernel.org/r/20210927220328.1410161-5-bvanassche@acm.org
[axboe: @latest -> @latest_start]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Calculating the sum over all CPUs of per-CPU counters frequently is
inefficient. Hence switch from per-CPU to individual counters. Three
counters are protected by the mq-deadline spinlock since these are
only accessed from contexts that already hold that spinlock. The fourth
counter is atomic because protecting it with the mq-deadline spinlock
would trigger lock contention.
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210927220328.1410161-4-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Check a statistics invariant at module unload time. When running
blktests, the invariant is verified every time a request queue is
removed and hence is verified at least once per test.
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210927220328.1410161-3-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The scheduler .insert_requests() callback is called when a request is
queued for the first time and also when it is requeued. Only count a
request the first time it is queued. Additionally, since the mq-deadline
scheduler only performs zone locking for requests that have been
inserted, skip the zone unlock code for requests that have not been
inserted into the mq-deadline scheduler.
Fixes: 38ba64d12d ("block/mq-deadline: Track I/O statistics")
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210927220328.1410161-2-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Except for the features passed to blk_queue_required_elevator_features,
elevator.h is only needed internally to the block layer. Move the
ELEVATOR_F_* definitions to blkdev.h, and the move elevator.h to
block/, dropping all the spurious includes outside of that.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20210920123328.1399408-13-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If CONFIG_BLK_DEBUG_FS=n:
block/mq-deadline.c:274:12: warning: ‘dd_queued’ defined but not used [-Wunused-function]
274 | static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio)
| ^~~~~~~~~
Fix this by moving dd_queued() just before the sole function that calls
it.
Fixes: 7b05bf7710 ("Revert "block/mq-deadline: Prioritize high-priority requests"")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Fixes: 38ba64d12d ("block/mq-deadline: Track I/O statistics")
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210830091128.1854266-1-geert@linux-m68k.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit fb926032b3.
Zhen reports that this commit slows down mq-deadline on a 128 thread
box, going from 258K IOPS to 170-180K. My testing shows that Optane
gen2 IOPS goes from 2.3M IOPS to 1.2M IOPS on a 64 thread box.
Looking in detail at the code, the main culprit here is needing to sum
percpu counters in the dispatch hot path, leading to very high CPU
utilization there. To make matters worse, the code currently needs to
sum 2 percpu counters, and it does so in the most naive way of iterating
possible CPUs _twice_.
Since we're close to release, revert this commit and we can re-do it
with regular per-priority counters instead for the 5.15 kernel.
Link: https://lore.kernel.org/linux-block/20210826144039.2143-1-thunder.leizhen@huawei.com/
Reported-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The block layer may call the I/O scheduler .finish_request() callback
without having called the .insert_requests() callback. Make sure that the
mq-deadline I/O statistics are correct if the block layer inserts an I/O
request that bypasses the I/O scheduler. This patch prevents that lower
priority I/O is delayed longer than necessary for mixed I/O priority
workloads.
Cc: Niklas Cassel <Niklas.Cassel@wdc.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Fixes: 08a9ad8bf6 ("block/mq-deadline: Add cgroup support")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210824170520.1659173-1-bvanassche@acm.org
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
Tested-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit 08a9ad8bf6 ("block/mq-deadline: Add cgroup support")
and a follow-up commit c06bc5a3fb ("block/mq-deadline: Remove a
WARN_ON_ONCE() call"). The added cgroup support has the following issues:
* It breaks cgroup interface file format rule by adding custom elements to a
nested key-value file.
* It registers mq-deadline as a cgroup-aware policy even though all it's
doing is collecting per-cgroup stats. Even if we need these stats, this
isn't the right way to add them.
* It hasn't been reviewed from cgroup side.
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Maintain statistics per cgroup and export these to user space. These
statistics are essential for verifying whether the proper I/O priorities
have been assigned to requests. An example of the statistics data with
this patch applied:
$ cat /sys/fs/cgroup/io.stat
11:2 rbytes=0 wbytes=0 rios=3 wios=0 dbytes=0 dios=0 [NONE] dispatched=0 inserted=0 merged=171 [RT] dispatched=0 inserted=0 merged=0 [BE] dispatched=0 inserted=0 merged=0 [IDLE] dispatched=0 inserted=0 merged=0
8:32 rbytes=2142720 wbytes=0 rios=105 wios=0 dbytes=0 dios=0 [NONE] dispatched=0 inserted=0 merged=171 [RT] dispatched=0 inserted=0 merged=0 [BE] dispatched=0 inserted=0 merged=0 [IDLE] dispatched=0 inserted=0 merged=0
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-16-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Track I/O statistics per I/O priority and export these statistics to
debugfs. These statistics help developers of the deadline scheduler.
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-15-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Maintain one dispatch list and one FIFO list per I/O priority class: RT, BE
and IDLE. Maintain statistics for each priority level. Split the debugfs
attributes per priority level as follows:
$ ls /sys/kernel/debug/block/.../sched/
async_depth dispatch2 read_next_rq write2_fifo_list
batching read0_fifo_list starved write_next_rq
dispatch0 read1_fifo_list write0_fifo_list
dispatch1 read2_fifo_list write1_fifo_list
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-14-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When dispatching the first request of a batch, the deadline_move_request()
call clears .next_rq[] for the opposite data direction. .next_rq[] is not
restored when changing data direction. Fix this by not clearing .next_rq[]
and by keeping track of the data direction of a batch in a variable instead.
This patch is a micro-optimization because:
- The number of deadline_next_request() calls for the read direction is
halved.
- The number of times that deadline_next_request() returns NULL is reduced.
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-13-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For interactive workloads it is important that synchronous requests are
not delayed. Hence reserve 25% of scheduler tags for synchronous requests.
This patch still allows asynchronous requests to fill the hardware queues
since blk_mq_init_sched() makes sure that the number of scheduler requests
is the double of the hardware queue depth. From blk_mq_init_sched():
q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth,
BLKDEV_MAX_RQ);
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-12-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Define separate macros for integers and jiffies to improve readability.
Use sysfs_emit() and kstrtoint() instead of sprintf() and simple_strtol().
The former functions are the recommended functions.
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-11-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Modern compilers complain if an out-of-range value is passed to a function
argument that has an enumeration type. Let the compiler detect out-of-range
data direction arguments instead of verifying the data_dir argument at
runtime.
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-10-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Change "queue" into "sched" to make the function names reflect better the
purpose of these functions.
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-9-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Make __dd_dispatch_request() easier to read by removing two local
variables.
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-8-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Document the locking strategy by adding two lockdep_assert_held()
statements.
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-7-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Make the code easier to read by adding more comments.
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210618004456.7280-6-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
__blk_mq_sched_bio_merge() gets the ctx and hctx for the current CPU and
passes the hctx to ->bio_merge(). kyber_bio_merge() then gets the ctx
for the current CPU again and uses that to get the corresponding Kyber
context in the passed hctx. However, the thread may be preempted between
the two calls to blk_mq_get_ctx(), and the ctx returned the second time
may no longer correspond to the passed hctx. This "works" accidentally
most of the time, but it can cause us to read garbage if the second ctx
came from an hctx with more ctx's than the first one (i.e., if
ctx->index_hw[hctx->type] > hctx->nr_ctx).
This manifested as this UBSAN array index out of bounds error reported
by Jakub:
UBSAN: array-index-out-of-bounds in ../kernel/locking/qspinlock.c:130:9
index 13106 is out of range for type 'long unsigned int [128]'
Call Trace:
dump_stack+0xa4/0xe5
ubsan_epilogue+0x5/0x40
__ubsan_handle_out_of_bounds.cold.13+0x2a/0x34
queued_spin_lock_slowpath+0x476/0x480
do_raw_spin_lock+0x1c2/0x1d0
kyber_bio_merge+0x112/0x180
blk_mq_submit_bio+0x1f5/0x1100
submit_bio_noacct+0x7b0/0x870
submit_bio+0xc2/0x3a0
btrfs_map_bio+0x4f0/0x9d0
btrfs_submit_data_bio+0x24e/0x310
submit_one_bio+0x7f/0xb0
submit_extent_page+0xc4/0x440
__extent_writepage_io+0x2b8/0x5e0
__extent_writepage+0x28d/0x6e0
extent_write_cache_pages+0x4d7/0x7a0
extent_writepages+0xa2/0x110
do_writepages+0x8f/0x180
__writeback_single_inode+0x99/0x7f0
writeback_sb_inodes+0x34e/0x790
__writeback_inodes_wb+0x9e/0x120
wb_writeback+0x4d2/0x660
wb_workfn+0x64d/0xa10
process_one_work+0x53a/0xa80
worker_thread+0x69/0x5b0
kthread+0x20b/0x240
ret_from_fork+0x1f/0x30
Only Kyber uses the hctx, so fix it by passing the request_queue to
->bio_merge() instead. BFQ and mq-deadline just use that, and Kyber can
map the queues itself to avoid the mismatch.
Fixes: a6088845c2 ("block: kyber: make kyber more friendly with merging")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Link: https://lore.kernel.org/r/c7598605401a48d5cfeadebb678abd10af22b83f.1620691329.git.osandov@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since commit 01e99aeca3 'blk-mq: insert passthrough request into
hctx->dispatch directly', passthrough request should not appear in
IO-scheduler any more, so blk_rq_is_passthrough checking in addon IO
schedulers is redundant.
(Notes: this patch passes generic IO load test with hdds under SAS
controller and hdds under AHCI controller but obviously not covers all.
Not sure if passthrough request can still escape into IO scheduler from
blk_mq_sched_insert_requests, which is used by blk_mq_flush_plug_list and
has lots of indirect callers.)
Signed-off-by: Lin Feng <linf@wangsu.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Get rid of the wrapper for trace_block_rq_insert() and call the function
directly.
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit b445547ec1.
Since both mq-deadline and BFQ completely ignore hctx they are passed to
their dispatch function and dispatch whatever request they deem fit
checking whether any request for a particular hctx is queued is just
pointless since we'll very likely get a request from a different hctx
anyway. In the following commit we'll deal with lock contention in these
IO schedulers in presence of multiple HW queues in a different way.
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
High CPU utilization on "native_queued_spin_lock_slowpath" due to lock
contention is possible for mq-deadline and bfq IO schedulers
when nr_hw_queues is more than one.
It is because kblockd work queue can submit IO from all online CPUs
(through blk_mq_run_hw_queues()) even though only one hctx has pending
commands.
The elevator callback .has_work for mq-deadline and bfq scheduler considers
pending work if there are any IOs on request queue but it does not account
hctx context.
Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering
the elevator even though there are no requests queued.
[jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap]
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
None of the I/O schedulers actually needs it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Introduce the definition of elevator features through the
elevator_features flags in the elevator_type structure. Each flag can
represent a feature supported by an elevator. The first feature defined
by this patch is support for zoned block device sequential write
constraint with the flag ELEVATOR_F_ZBD_SEQ_WRITE, which is implemented
by the mq-deadline elevator using zone write locking.
Other possible features are IO priorities, write hints, latency targets
or single-LUN dual-actuator disks (for which the elevator could maintain
one LBA ordered list per actuator).
The required_elevator_features field is also added to the request_queue
structure to allow a device driver to specify elevator feature flags
that an elevator must support for the correct operation of the device
(e.g. device drivers for zoned block devices can have the
ELEVATOR_F_ZBD_SEQ_WRITE flag as a required feature).
The helper function blk_queue_required_elevator_features() is
defined for setting this new field.
With these two new fields in place, the elevator functions
elevator_match() and elevator_find() are modified to allow a user to set
only an elevator with a set of features that satisfies the device
required features. Elevators not matching the device requirements are
not shown in the device sysfs queue/scheduler file to prevent their use.
The "none" elevator can always be selected as before.
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit 7211aef86f ("block: mq-deadline: Fix write completion
handling") added a call to blk_mq_sched_mark_restart_hctx() in
dd_dispatch_request() to make sure that write request dispatching does
not stall when all target zones are locked. This fix left a subtle race
when a write completion happens during a dispatch execution on another
CPU:
CPU 0: Dispatch CPU1: write completion
dd_dispatch_request()
lock(&dd->lock);
...
lock(&dd->zone_lock); dd_finish_request()
rq = find request lock(&dd->zone_lock);
unlock(&dd->zone_lock);
zone write unlock
unlock(&dd->zone_lock);
...
__blk_mq_free_request
check restart flag (not set)
-> queue not run
...
if (!rq && have writes)
blk_mq_sched_mark_restart_hctx()
unlock(&dd->lock)
Since the dispatch context finishes after the write request completion
handling, marking the queue as needing a restart is not seen from
__blk_mq_free_request() and blk_mq_sched_restart() not executed leading
to the dispatch stall under 100% write workloads.
Fix this by moving the call to blk_mq_sched_mark_restart_hctx() from
dd_dispatch_request() into dd_finish_request() under the zone lock to
ensure full mutual exclusion between write request dispatch selection
and zone unlock on write request completion.
Fixes: 7211aef86f ("block: mq-deadline: Fix write completion handling")
Cc: stable@vger.kernel.org
Reported-by: Hans Holmberg <Hans.Holmberg@wdc.com>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Rename the block documentation files to ReST, add an
index for them and adjust in order to produce a nice html
output via the Sphinx build system.
At its new index.rst, let's add a :orphan: while this is not linked to
the main index.rst file, in order to avoid build warnings.
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
We only need the number of segments in the blk-mq submission path.
Remove the field from struct bio, and return it from a variant of
blk_queue_split instead of that it can passed as an argument to
those functions that need the value.
This also means we stop recounting segments except for cloning
and partial segments.
To keep the number of arguments in this how path down remove
pointless struct request_queue arguments from any of the functions
that had it and grew a nr_segs argument.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Various block layer files do not have any licensing information at all.
Add SPDX tags for the default kernel GPLv2 license to those.
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For a zoned block device using mq-deadline, if a write request for a
zone is received while another write was already dispatched for the same
zone, dd_dispatch_request() will return NULL and the newly inserted
write request is kept in the scheduler queue waiting for the ongoing
zone write to complete. With this behavior, when no other request has
been dispatched, rq_list in blk_mq_sched_dispatch_requests() is empty
and blk_mq_sched_mark_restart_hctx() not called. This in turn leads to
__blk_mq_free_request() call of blk_mq_sched_restart() to not run the
queue when the already dispatched write request completes. The newly
dispatched request stays stuck in the scheduler queue until eventually
another request is submitted.
This problem does not affect SCSI disk as the SCSI stack handles queue
restart on request completion. However, this problem is can be triggered
the nullblk driver with zoned mode enabled.
Fix this by always requesting a queue restart in dd_dispatch_request()
if no request was dispatched while WRITE requests are queued.
Fixes: 5700f69178 ("mq-deadline: Introduce zone locking support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Add missing export of blk_mq_sched_restart()
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is a remnant of when we had ops for both SQ and MQ
schedulers. Now it's just MQ, so get rid of the union.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This removes a bunch of core and elevator related code. On the core
front, we remove anything related to queue running, draining,
initialization, plugging, and congestions. We also kill anything
related to request allocation, merging, retrieval, and completion.
Remove any checking for single queue IO schedulers, as they no
longer exist. This means we can also delete a bunch of code related
to request issue, adding, completion, etc - and all the SQ related
ops and helpers.
Also kill the load_default_modules(), as all that did was provide
for a way to load the default single queue elevator.
Tested-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Convert the S_<FOO> symbolic permissions to their octal equivalents as
using octal and not symbolic permissions is preferred by many as more
readable.
see: https://lkml.org/lkml/2016/8/2/1945
Done with automated conversion via:
$ ./scripts/checkpatch.pl -f --types=SYMBOLIC_PERMS --fix-inplace <files...>
Miscellanea:
o Wrapped modified multi-line calls to a single line where appropriate
o Realign modified multi-line calls to open parenthesis
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In case of a failed write request (all retries failed) and when using
libata, the SCSI error handler calls scsi_finish_command(). In the
case of blk-mq this means that scsi_mq_done() does not get called,
that blk_mq_complete_request() does not get called and also that the
mq-deadline .completed_request() method is not called. This results in
the target zone of the failed write request being left in a locked
state, preventing that any new write requests are issued to the same
zone.
Fix this by replacing the .completed_request() method with the
.finish_request() method as this method is always called whether or
not a request completes successfully. Since the .finish_request()
method is only called by the blk-mq core if a .prepare_request()
method exists, add a dummy .prepare_request() method.
Fixes: 5700f69178 ("mq-deadline: Introduce zone locking support")
Cc: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
[ bvanassche: edited patch description ]
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Don't pass in the hardware queue to __dd_dispatch_request(), since it
leads the reader to believe that we are returning a request for that
specific hardware queue. That's not how mq-deadline works, the state
for determining which request to serve next is shared across all
hardware queues for a device.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Introduce zone write locking to avoid write request reordering with
zoned block devices. This is achieved using a finer selection of the
next request to dispatch:
1) Any non-write request is always allowed to proceed.
2) Any write to a conventional zone is always allowed to proceed.
3) For a write to a sequential zone, the zone lock is first checked.
a) If the zone is not locked, the write is allowed to proceed after
its target zone is locked.
b) If the zone is locked, the write request is skipped and the next
request in the dispatch queue tested (back to step 1).
For a write request that has locked its target zone, the zone is
unlocked either when the request completes with a call to the method
deadline_request_completed() or when the request is requeued using
dd_insert_request().
Requests targeting a locked zone are always left in the scheduler queue
to preserve the lba ordering for write requests. If no write request
can be dispatched, allow reads to be dispatched even if the write batch
is not done.
If the device used is not a zoned block device, or if zoned block device
support is disabled, this patch does not modify mq-deadline behavior.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Avoid directly referencing the next_rq and fifo_list arrays using the
helper functions deadline_next_request() and deadline_fifo_request() to
facilitate changes in the dispatch request selection in
__dd_dispatch_request() for zoned block devices.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The scheduler framework now supports looking up the appropriate
scheduler with the {name,mq} tupple. We can register mq-deadline
with the alias of 'deadline', so that switching to 'deadline'
will do the right thing based on the type of driver attached to
it.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
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>
Damien Le Moal