commit 01e99aeca3 ("blk-mq: insert passthrough request into
hctx->dispatch directly") may change to add flush request to the tail
of dispatch by applying the 'add_head' parameter of
blk_mq_sched_insert_request.
Turns out this way causes performance regression on NCQ controller because
flush is non-NCQ command, which can't be queued when there is any in-flight
NCQ command. When adding flush rq to the front of hctx->dispatch, it is
easier to introduce extra time to flush rq's latency compared with adding
to the tail of dispatch queue because of S_SCHED_RESTART, then chance of
flush merge is increased, and less flush requests may be issued to
controller.
So always insert flush request to the front of dispatch queue just like
before applying commit 01e99aeca3 ("blk-mq: insert passthrough request
into hctx->dispatch directly").
Cc: Damien Le Moal <Damien.LeMoal@wdc.com>
Cc: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Fixes: 01e99aeca3 ("blk-mq: insert passthrough request into hctx->dispatch directly")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For some reason, device may be in one situation which can't handle
FS request, so STS_RESOURCE is always returned and the FS request
will be added to hctx->dispatch. However passthrough request may
be required at that time for fixing the problem. If passthrough
request is added to scheduler queue, there isn't any chance for
blk-mq to dispatch it given we prioritize requests in hctx->dispatch.
Then the FS IO request may never be completed, and IO hang is caused.
So passthrough request has to be added to hctx->dispatch directly
for fixing the IO hang.
Fix this issue by inserting passthrough request into hctx->dispatch
directly together withing adding FS request to the tail of
hctx->dispatch in blk_mq_dispatch_rq_list(). Actually we add FS request
to tail of hctx->dispatch at default, see blk_mq_request_bypass_insert().
Then it becomes consistent with original legacy IO request
path, in which passthrough request is always added to q->queue_head.
Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit c48dac137a ("block: don't hold q->sysfs_lock in elevator_init_mq")
removes q->sysfs_lock from elevator_init_mq(), but forgot to deal with
lockdep_assert_held() called in blk_mq_sched_free_requests() which is
run in failure path of elevator_init_mq().
blk_mq_sched_free_requests() is called in the following 3 functions:
elevator_init_mq()
elevator_exit()
blk_cleanup_queue()
In blk_cleanup_queue(), blk_mq_sched_free_requests() is followed exactly
by 'mutex_lock(&q->sysfs_lock)'.
So moving the lockdep_assert_held() from blk_mq_sched_free_requests()
into elevator_exit() for fixing the report by syzbot.
Reported-by: syzbot+da3b7677bb913dc1b737@syzkaller.appspotmail.com
Fixed: c48dac137a ("block: don't hold q->sysfs_lock in elevator_init_mq")
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No code that occurs between blk_mq_get_ctx() and blk_mq_put_ctx() depends
on preemption being disabled for its correctness. Since removing the CPU
preemption calls does not measurably affect performance, simplify the
blk-mq code by removing the blk_mq_put_ctx() function and also by not
disabling preemption in blk_mq_get_ctx().
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
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>
blk_mq_sched_free_requests() may be called in failure path in which
q->elevator may not be setup yet, so remove WARN_ON(!q->elevator) from
blk_mq_sched_free_requests for avoiding the false positive.
This function is actually safe to call in case of !q->elevator because
hctx->sched_tags is checked.
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Yi Zhang <yi.zhang@redhat.com>
Fixes: c3e2219216 ("block: free sched's request pool in blk_cleanup_queue")
Reported-by: syzbot+b9d0d56867048c7bcfde@syzkaller.appspotmail.com
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In theory, IO scheduler belongs to request queue, and the request pool
of sched tags belongs to the request queue too.
However, the current tags allocation interfaces are re-used for both
driver tags and sched tags, and driver tags is definitely host wide,
and doesn't belong to any request queue, same with its request pool.
So we need tagset instance for freeing request of sched tags.
Meantime, blk_mq_free_tag_set() often follows blk_cleanup_queue() in case
of non-BLK_MQ_F_TAG_SHARED, this way requires that request pool of sched
tags to be freed before calling blk_mq_free_tag_set().
Commit 47cdee29ef ("block: move blk_exit_queue into __blk_release_queue")
moves blk_exit_queue into __blk_release_queue for simplying the fast
path in generic_make_request(), then causes oops during freeing requests
of sched tags in __blk_release_queue().
Fix the above issue by move freeing request pool of sched tags into
blk_cleanup_queue(), this way is safe becasue queue has been frozen and no any
in-queue requests at that time. Freeing sched tags has to be kept in queue's
release handler becasue there might be un-completed dispatch activity
which might refer to sched tags.
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Christoph Hellwig <hch@lst.de>
Fixes: 47cdee29ef ("block: move blk_exit_queue into __blk_release_queue")
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Just like aio/io_uring, we need to grab 2 refcount for queuing one
request, one is for submission, another is for completion.
If the request isn't queued from plug code path, the refcount grabbed
in generic_make_request() serves for submission. In theroy, this
refcount should have been released after the sumission(async run queue)
is done. blk_freeze_queue() works with blk_sync_queue() together
for avoiding race between cleanup queue and IO submission, given async
run queue activities are canceled because hctx->run_work is scheduled with
the refcount held, so it is fine to not hold the refcount when
running the run queue work function for dispatch IO.
However, if request is staggered into plug list, and finally queued
from plug code path, the refcount in submission side is actually missed.
And we may start to run queue after queue is removed because the queue's
kobject refcount isn't guaranteed to be grabbed in flushing plug list
context, then kernel oops is triggered, see the following race:
blk_mq_flush_plug_list():
blk_mq_sched_insert_requests()
insert requests to sw queue or scheduler queue
blk_mq_run_hw_queue
Because of concurrent run queue, all requests inserted above may be
completed before calling the above blk_mq_run_hw_queue. Then queue can
be freed during the above blk_mq_run_hw_queue().
Fixes the issue by grab .q_usage_counter before calling
blk_mq_sched_insert_requests() in blk_mq_flush_plug_list(). This way is
safe because the queue is absolutely alive before inserting request.
Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: James Smart <james.smart@broadcom.com>
Cc: linux-scsi@vger.kernel.org,
Cc: Martin K . Petersen <martin.petersen@oracle.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>,
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
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>
blk_mq_try_issue_directly() can return BLK_STS*_RESOURCE for requests that
have been queued. If that happens when blk_mq_try_issue_directly() is called
by the dm-mpath driver then dm-mpath will try to resubmit a request that is
already queued and a kernel crash follows. Since it is nontrivial to fix
blk_mq_request_issue_directly(), revert the blk_mq_request_issue_directly()
changes that went into kernel v5.0.
This patch reverts the following commits:
* d6a51a97c0 ("blk-mq: replace and kill blk_mq_request_issue_directly") # v5.0.
* 5b7a6f128a ("blk-mq: issue directly with bypass 'false' in blk_mq_sched_insert_requests") # v5.0.
* 7f556a44e6 ("blk-mq: refactor the code of issue request directly") # v5.0.
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: James Smart <james.smart@broadcom.com>
Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: <stable@vger.kernel.org>
Reported-by: Laurence Oberman <loberman@redhat.com>
Tested-by: Laurence Oberman <loberman@redhat.com>
Fixes: 7f556a44e6 ("blk-mq: refactor the code of issue request directly") # v5.0.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently, the queue mapping result is saved in a two-dimensional
array. In the hot path, to get a hctx, we need do following:
q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]]
This isn't very efficient. We could save the queue mapping result into
ctx directly with different hctx type, like,
ctx->hctxs[type]
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When a request is added to rq list of sw queue(ctx), the rq may be from
a different type of hctx, especially after multi queue mapping is
introduced.
So when dispach request from sw queue via blk_mq_flush_busy_ctxs() or
blk_mq_dequeue_from_ctx(), one request belonging to other queue type of
hctx can be dispatched to current hctx in case that read queue or poll
queue is enabled.
This patch fixes this issue by introducing per-queue-type list.
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Changed by me to not use separately cacheline aligned lists, just
place them all in the same cacheline where we had just the one list
and lock before.
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>
It is not necessary to issue request directly with bypass 'true'
in blk_mq_sched_insert_requests and handle the non-issued requests
itself. Just set bypass to 'false' and let blk_mq_try_issue_directly
handle them totally. Remove the blk_rq_can_direct_dispatch check,
because blk_mq_try_issue_directly can handle it well.If request is
direct-issued unsuccessfully, insert the reset.
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If the first request allocated and issued by a process is a passhthrough
request, we don't set up an IO context for it. Ensure that
blk_mq_sched_assign_ioc() ignores a NULL io_context.
Fixes: e2b3fa5af7 ("block: Remove bio->bi_ioc")
Reported-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
bio->bi_ioc is never set so always NULL. Remove references to it in
bio_disassociate_task() and in rq_ioc() and delete this field from
struct bio. With this change, rq_ioc() always returns
current->io_context without the need for a bio argument. Further
simplify the code and make it more readable by also removing this
helper, which also allows to simplify blk_mq_sched_assign_ioc() by
removing its bio argument.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Adam Manzanares <adam.manzanares@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With the legacy request path gone there is no good reason to keep
queue_lock as a pointer, we can always use the embedded lock now.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Fixed floppy and blk-cgroup missing conversions and half done edits.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It's somewhat strange to have a list insertion function that
relies on the fact that the caller has mapped things correctly.
Pass in the hardware queue directly for insertion, which makes
for a much cleaner interface and implementation.
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We call blk_mq_map_queue() a lot, at least two times for each
request per IO, sometimes more. Since we now have an indirect
call as well in that function. cache the mapping so we don't
have to re-call blk_mq_map_queue() for the same request
multiple times.
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The mapping used to be dependent on just the CPU location, but
now it's a tuple of (type, cpu) instead. This is a prep patch
for allowing a single software queue to map to multiple hardware
queues. No functional changes in this patch.
This changes the software queue count to an unsigned short
to save a bit of space. We can still support 64K-1 CPUs,
which should be enough. Add a check to catch a wrap.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Prep patch for being able to place request based not just on
CPU location, but also on the type of request.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
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>
Currently, when update nr_hw_queues, IO scheduler's init_hctx will
be invoked before the mapping between ctx and hctx is adapted
correctly by blk_mq_map_swqueue. The IO scheduler init_hctx (kyber)
may depend on this mapping and get wrong result and panic finally.
A simply way to fix this is that switch the IO scheduler to 'none'
before update the nr_hw_queues, and then switch it back after
update nr_hw_queues. blk_mq_sched_init_/exit_hctx are removed due
to nobody use them any more.
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In case of 'none' io scheduler, when hw queue isn't busy, it isn't
necessary to enqueue request to sw queue and dequeue it from
sw queue because request may be submitted to hw queue asap without
extra cost, meantime there shouldn't be much request in sw queue,
and we don't need to worry about effect on IO merge.
There are still some single hw queue SCSI HBAs(HPSA, megaraid_sas, ...)
which may connect high performance devices, so 'none' is often required
for obtaining good performance.
This patch improves IOPS and decreases CPU unilization on megaraid_sas,
per Kashyap's test.
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It won't be efficient to dequeue request one by one from sw queue,
but we have to do that when queue is busy for better merge performance.
This patch takes the Exponential Weighted Moving Average(EWMA) to figure
out if queue is busy, then only dequeue request one by one from sw queue
when queue is busy.
Fixes: b347689ffb ("blk-mq-sched: improve dispatching from sw queue")
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Only attempt to merge bio iff the ctx->rq_list isn't empty, because:
1) for high-performance SSD, most of times dispatch may succeed, then
there may be nothing left in ctx->rq_list, so don't try to merge over
sw queue if it is empty, then we can save one acquiring of ctx->lock
2) we can't expect good merge performance on per-cpu sw queue, and missing
one merge on sw queue won't be a big deal since tasks can be scheduled from
one CPU to another.
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We have to remove synchronize_rcu() from blk_queue_cleanup(),
otherwise long delay can be caused during lun probe. For removing
it, we have to avoid to iterate the set->tag_list in IO path, eg,
blk_mq_sched_restart().
This patch reverts 5b79413946d (Revert "blk-mq: don't handle
TAG_SHARED in restart"). Given we have fixed enough IO hang issue,
and there isn't any reason to restart all queues in one tags any more,
see the following reasons:
1) blk-mq core can deal with shared-tags case well via blk_mq_get_driver_tag(),
which can wake up queues waiting for driver tag.
2) SCSI is a bit special because it may return BLK_STS_RESOURCE if queue,
target or host is ready, but SCSI built-in restart can cover all these well,
see scsi_end_request(), queue will be rerun after any request initiated from
this host/target is completed.
In my test on scsi_debug(8 luns), this patch may improve IOPS by 20% ~ 30%
when running I/O on these 8 luns concurrently.
Fixes: 705cda97ee ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list")
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: linux-scsi@vger.kernel.org
Reported-by: Andrew Jones <drjones@redhat.com>
Tested-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now we setup q->nr_requests when switching to one new scheduler,
but not do it for 'none', then q->nr_requests may not be correct
for 'none'.
This patch fixes this issue by always updating 'nr_requests' when
switching to 'none'.
Cc: Marco Patalano <mpatalan@redhat.com>
Cc: "Ewan D. Milne" <emilne@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Both callers take just around so function call, so move it in.
Also remove the now pointless blk_mq_sched_init wrapper.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reported-by: Damien Le Moal <Damien.LeMoal@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No functional changes in this patch, just a prep patch for utilizing
this in an IO scheduler.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Omar Sandoval <osandov@fb.com>
After commit:
923218f616 ("blk-mq: don't allocate driver tag upfront for flush rq")
we no longer use the 'can_block' argument in
blk_mq_sched_insert_request(). Kill it.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Added actual commit message as to why it's being removed.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit de14829740
("blk-mq: introduce .get_budget and .put_budget in blk_mq_ops")
changes the function to return bool type, and then commit 1f460b63d4
("blk-mq: don't restart queue when .get_budget returns BLK_STS_RESOURCE")
changes it back to void, but the comment remains.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we are inconsistent in when we decide to run the queue. Using
blk_mq_run_hw_queues() we check if the hctx has pending IO before
running it, but we don't do that from the individual queue run function,
blk_mq_run_hw_queue(). This results in a lot of extra and pointless
queue runs, potentially, on flush requests and (much worse) on tag
starvation situations. This is observable just looking at top output,
with lots of kworkers active. For the !async runs, it just adds to the
CPU overhead of blk-mq.
Move the has-pending check into the run function instead of having
callers do it.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit 358a3a6bcc.
We have cases that aren't covered 100% in the drivers, so for now
we have to retain the shared tag restart loops.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The idea behind it is simple:
1) for none scheduler, driver tag has to be borrowed for flush rq,
otherwise we may run out of tag, and that causes an IO hang. And
get/put driver tag is actually noop for none, so reordering tags
isn't necessary at all.
2) for a real I/O scheduler, we need not allocate a driver tag upfront
for flush rq. It works just fine to follow the same approach as
normal requests: allocate driver tag for each rq just before calling
->queue_rq().
One driver visible change is that the driver tag isn't shared in the
flush request sequence. That won't be a problem, since we always do that
in legacy path.
Then flush rq need not be treated specially wrt. get/put driver tag.
This cleans up the code - for instance, reorder_tags_to_front() can be
removed, and we needn't worry about request ordering in dispatch list
for avoiding I/O deadlock.
Also we have to put the driver tag before requeueing.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In case of IO scheduler we always pre-allocate one driver tag before
calling blk_insert_flush(), and flush request will be marked as
RQF_FLUSH_SEQ once it is in flush machinery.
So if RQF_FLUSH_SEQ isn't set, we call blk_insert_flush() to handle
the request, otherwise the flush request is dispatched to ->dispatch
list directly.
This is a preparation patch for not preallocating a driver tag for flush
requests, and for not treating flush requests as a special case. This is
similar to what the legacy path does.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It is enough to just check if we can get the budget via .get_budget().
And we don't need to deal with device state change in .get_budget().
For SCSI, one issue to be fixed is that we have to call
scsi_mq_uninit_cmd() to free allocated ressources if SCSI device fails
to handle the request. And it isn't enough to simply call
blk_mq_end_request() to do that if this request is marked as
RQF_DONTPREP.
Fixes: 0df21c86bdbf(scsi: implement .get_budget and .put_budget for blk-mq)
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
SCSI restarts its queue in scsi_end_request() automatically, so we don't
need to handle this case in blk-mq.
Especailly any request won't be dequeued in this case, we needn't to
worry about IO hang caused by restart vs. dispatch.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now restart is used in the following cases, and TAG_SHARED is for
SCSI only.
1) .get_budget() returns BLK_STS_RESOURCE
- if resource in target/host level isn't satisfied, this SCSI device
will be added in shost->starved_list, and the whole queue will be rerun
(via SCSI's built-in RESTART) in scsi_end_request() after any request
initiated from this host/targe is completed. Forget to mention, host level
resource can't be an issue for blk-mq at all.
- the same is true if resource in the queue level isn't satisfied.
- if there isn't outstanding request on this queue, then SCSI's RESTART
can't work(blk-mq's can't work too), and the queue will be run after
SCSI_QUEUE_DELAY, and finally all starved sdevs will be handled by SCSI's
RESTART when this request is finished
2) scsi_dispatch_cmd() returns BLK_STS_RESOURCE
- if there isn't onprogressing request on this queue, the queue
will be run after SCSI_QUEUE_DELAY
- otherwise, SCSI's RESTART covers the rerun.
3) blk_mq_get_driver_tag() failed
- BLK_MQ_S_TAG_WAITING covers the cross-queue RESTART for driver
allocation.
In one word, SCSI's built-in RESTART is enough to cover the queue
rerun, and we don't need to pay special attention to TAG_SHARED wrt. restart.
In my test on scsi_debug(8 luns), this patch improves IOPS by 20% ~ 30% when
running I/O on these 8 luns concurrently.
Aslo Roman Pen reported the current RESTART is very expensive especialy
when there are lots of LUNs attached in one host, such as in his
test, RESTART causes half of IOPS be cut.
Fixes: https://marc.info/?l=linux-kernel&m=150832216727524&w=2
Fixes: 6d8c6c0f97 ("blk-mq: Restart a single queue if tag sets are shared")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
SCSI devices use host-wide tagset, and the shared driver tag space is
often quite big. However, there is also a queue depth for each lun(
.cmd_per_lun), which is often small, for example, on both lpfc and
qla2xxx, .cmd_per_lun is just 3.
So lots of requests may stay in sw queue, and we always flush all
belonging to same hw queue and dispatch them all to driver.
Unfortunately it is easy to cause queue busy because of the small
.cmd_per_lun. Once these requests are flushed out, they have to stay in
hctx->dispatch, and no bio merge can happen on these requests, and
sequential IO performance is harmed.
This patch introduces blk_mq_dequeue_from_ctx for dequeuing a request
from a sw queue, so that we can dispatch them in scheduler's way. We can
then avoid dequeueing too many requests from sw queue, since we don't
flush ->dispatch completely.
This patch improves dispatching from sw queue by using the .get_budget
and .put_budget callbacks.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For SCSI devices, there is often a per-request-queue depth, which needs
to be respected before queuing one request.
Currently blk-mq always dequeues the request first, then calls
.queue_rq() to dispatch the request to lld. One obvious issue with this
approach is that I/O merging may not be successful, because when the
per-request-queue depth can't be respected, .queue_rq() has to return
BLK_STS_RESOURCE, and then this request has to stay in hctx->dispatch
list. This means it never gets a chance to be merged with other IO.
This patch introduces .get_budget and .put_budget callback in blk_mq_ops,
then we can try to get reserved budget first before dequeuing request.
If the budget for queueing I/O can't be satisfied, we don't need to
dequeue request at all. Hence the request can be left in the IO
scheduler queue, for more merging opportunities.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
So that it becomes easy to support to dispatch from sw queue in the
following patch.
No functional change.
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Suggested-by: Christoph Hellwig <hch@lst.de> # for simplifying dispatch logic
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When the hw queue is busy, we shouldn't take requests from the scheduler
queue any more, otherwise it is difficult to do IO merge.
This patch fixes the awful IO performance on some SCSI devices(lpfc,
qla2xxx, ...) when mq-deadline/kyber is used by not taking requests if
hw queue is busy.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When mq-deadline is taken, IOPS of sequential read and
seqential write is observed more than 20% drop on sata(scsi-mq)
devices, compared with using 'none' scheduler.
The reason is that the default nr_requests for scheduler is
too big for small queuedepth devices, and latency is increased
much.
Since the principle of taking 256 requests for mq scheduler
is based on 128 queue depth, this patch changes into
double size of min(hw queue_depth, 128).
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull in the fix for shared tags, as it conflicts with the pending
changes in for-4.13/block. We already pulled in v4.12-rc5 to solve
other conflicts or get fixes that went into 4.12, so not a lot
of changes in this merge.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we have shared tags enabled, then every IO completion will trigger
a full loop of every queue belonging to a tag set, and every hardware
queue for each of those queues, even if nothing needs to be done.
This causes a massive performance regression if you have a lot of
shared devices.
Instead of doing this huge full scan on every IO, add an atomic
counter to the main queue that tracks how many hardware queues have
been marked as needing a restart. With that, we can avoid looking for
restartable queues, if we don't have to.
Max reports that this restores performance. Before this patch, 4K
IOPS was limited to 22-23K IOPS. With the patch, we are running at
950-970K IOPS.
Fixes: 6d8c6c0f97 ("blk-mq: Restart a single queue if tag sets are shared")
Reported-by: Max Gurtovoy <maxg@mellanox.com>
Tested-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Tested-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Document the locking assumptions in functions that modify
blk_mq_ctx.rq_list to make it easier for humans to verify
this code.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It is required that no dispatch can happen any more once
blk_mq_quiesce_queue() returns, and we don't have such requirement
on APIs of stopping queue.
But blk_mq_quiesce_queue() still may not block/drain dispatch in the
the case of BLK_MQ_S_START_ON_RUN, so use the new introduced flag of
QUEUE_FLAG_QUIESCED and evaluate it inside RCU read-side critical
sections for fixing this issue.
Also blk_mq_quiesce_queue() is implemented via stopping queue, which
limits its uses, and easy to cause race, because any queue restart in
other paths may break blk_mq_quiesce_queue(). With the introduced
flag of QUEUE_FLAG_QUIESCED, we don't need to depend on stopping queue
for quiescing any more.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
