From: Tejun Heo <tj@kernel.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>,
linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: [PATCH block/for-3.17-fixes/core] blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe
Date: Tue, 23 Sep 2014 15:24:32 -0400 [thread overview]
Message-ID: <20140923192432.GA24441@mtj.dyndns.org> (raw)
In-Reply-To: <5421968B.7080309@kernel.dk>
blk-mq uses percpu_ref for its usage counter which tracks the number
of in-flight commands and used to synchronously drain the queue on
freeze. percpu_ref shutdown takes measureable wallclock time as it
involves a sched RCU grace period. This means that draining a blk-mq
takes measureable wallclock time. One would think that this shouldn't
matter as queue shutdown should be a rare event which takes place
asynchronously w.r.t. userland.
Unfortunately, SCSI probing involves synchronously setting up and then
tearing down a lot of request_queues back-to-back for non-existent
LUNs. This means that SCSI probing may take more than ten seconds
when scsi-mq is used.
This will be properly fixed by implementing a mechanism to keep
q->mq_usage_counter in atomic mode till genhd registration; however,
that involves rather big updates to percpu_ref which is difficult to
apply late in the devel cycle (v3.17-rc6 at the moment). As a
stop-gap measure till the proper fix can be implemented in the next
cycle, this patch introduces __percpu_ref_kill_expedited() and makes
blk_mq_freeze_queue() use it. This is heavy-handed but should work
for testing the experimental SCSI blk-mq implementation.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de
Fixes: add703fda981 ("blk-mq: use percpu_ref for mq usage count")
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
---
Hello, Jens, Christoph.
How about this one? This is kinda ugly but should work fine in most
cases and easy to apply to v3.17 and take out during v3.18.
Thanks.
block/blk-mq.c | 11 ++++++++++-
include/linux/percpu-refcount.h | 1 +
lib/percpu-refcount.c | 16 ++++++++++++++++
3 files changed, 27 insertions(+), 1 deletion(-)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -120,7 +120,16 @@ void blk_mq_freeze_queue(struct request_
spin_unlock_irq(q->queue_lock);
if (freeze) {
- percpu_ref_kill(&q->mq_usage_counter);
+ /*
+ * XXX: Temporary kludge to work around SCSI blk-mq stall.
+ * SCSI synchronously creates and destroys many queues
+ * back-to-back during probe leading to lengthy stalls.
+ * This will be fixed by keeping ->mq_usage_counter in
+ * atomic mode until genhd registration, but, for now,
+ * let's work around using expedited synchronization.
+ */
+ __percpu_ref_kill_expedited(&q->mq_usage_counter);
+
blk_mq_run_queues(q, false);
}
wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -72,6 +72,7 @@ void percpu_ref_reinit(struct percpu_ref
void percpu_ref_exit(struct percpu_ref *ref);
void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
percpu_ref_func_t *confirm_kill);
+void __percpu_ref_kill_expedited(struct percpu_ref *ref);
/**
* percpu_ref_kill - drop the initial ref
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -189,3 +189,19 @@ void percpu_ref_kill_and_confirm(struct
call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
}
EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
+
+/*
+ * XXX: Temporary kludge to work around SCSI blk-mq stall. Used only by
+ * block/blk-mq.c::blk_mq_freeze_queue(). Will be removed during v3.18
+ * devel cycle. Do not use anywhere else.
+ */
+void __percpu_ref_kill_expedited(struct percpu_ref *ref)
+{
+ WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
+ "percpu_ref_kill() called more than once on %pf!",
+ ref->release);
+
+ ref->pcpu_count_ptr |= PCPU_REF_DEAD;
+ synchronize_sched_expedited();
+ percpu_ref_kill_rcu(&ref->rcu);
+}
next prev parent reply other threads:[~2014-09-23 19:24 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-19 11:38 boot stall regression due to blk-mq: use percpu_ref for mq usage count Christoph Hellwig
2014-09-19 19:13 ` Jens Axboe
2014-09-23 5:55 ` Christoph Hellwig
2014-09-23 5:56 ` Tejun Heo
2014-09-23 5:57 ` Tejun Heo
2014-09-23 5:59 ` Christoph Hellwig
2014-09-23 6:01 ` Tejun Heo
2014-09-23 6:03 ` Tejun Heo
2014-09-23 6:09 ` Christoph Hellwig
2014-09-23 6:11 ` Tejun Heo
2014-09-23 14:57 ` Elliott, Robert (Server Storage)
2014-09-23 15:49 ` Jens Axboe
2014-09-23 19:24 ` Tejun Heo [this message]
2014-09-23 19:29 ` [PATCH block/for-3.17-fixes/core] blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe Jens Axboe
2014-09-23 19:48 ` Tejun Heo
2014-09-24 8:23 ` Christoph Hellwig
2014-09-24 14:30 ` Jens Axboe
2014-09-24 14:33 ` Tejun Heo
2014-09-24 14:33 ` Jens Axboe
2014-09-24 17:20 ` [PATCH percpu/for-3.18] Revert "blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe" Tejun Heo
2014-09-23 6:08 ` [PATCH block/for-3.18/core] blk-mq: start q->mq_usage_counter in atomic mode Tejun Heo
2014-09-24 17:33 ` Tejun Heo
2014-09-24 17:43 ` [PATCH percpu/for-3.18] blk-mq, percpu_ref: " Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140923192432.GA24441@mtj.dyndns.org \
--to=tj@kernel.org \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).