From: "Paul E. McKenney" <paulmck@kernel.org>
To: Sagi Grimberg <sagi@grimberg.me>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-nvme@lists.infradead.org, Ming Lei <ming.lei@redhat.com>,
linux-block@vger.kernel.org, Chao Leng <lengchao@huawei.com>,
Keith Busch <kbusch@kernel.org>, Ming Lin <mlin@kernel.org>,
Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH v5 1/2] blk-mq: add tagset quiesce interface
Date: Tue, 28 Jul 2020 17:31:24 -0700 [thread overview]
Message-ID: <20200729003124.GT9247@paulmck-ThinkPad-P72> (raw)
In-Reply-To: <d1ba2009-130a-d423-1389-c7af72e25a6a@grimberg.me>
On Tue, Jul 28, 2020 at 04:46:23PM -0700, Sagi Grimberg wrote:
> Hey Paul,
>
> > Indeed you cannot. And if you build with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
> > it will yell at you when you try.
> >
> > You -can- pass on-stack rcu_head structures to call_srcu(), though,
> > if that helps. You of course must have some way of waiting for the
> > callback to be invoked before exiting that function. This should be
> > easy for me to package into an API, maybe using one of the existing
> > reference-counting APIs.
> >
> > So, do you have a separate stack frame for each of the desired call_srcu()
> > invocations? If not, do you know at build time how many rcu_head
> > structures you need? If the answer to both of these is "no", then
> > it is likely that there needs to be an rcu_head in each of the relevant
> > data structures, as was noted earlier in this thread.
> >
> > Yeah, I should go read the code. But I would need to know where it is
> > and it is still early in the morning over here! ;-)
> >
> > I probably should also have read the remainder of the thread before
> > replying, as well. But what is the fun in that?
>
> The use-case is to quiesce submissions to queues. This flow is where we
> want to teardown stuff, and we can potentially have 1000's of queues
> that we need to quiesce each one.
>
> each queue (hctx) has either rcu or srcu depending if it may sleep
> during submission.
>
> The goal is that the overall quiesce should be fast, so we want
> to wait for all of these queues elapsed period ~once, in parallel,
> instead of synchronizing each serially as done today.
>
> The guys here are resisting to add a rcu_synchronize to each and
> every hctx because it will take 32 bytes more or less from 1000's
> of hctxs.
>
> Dynamically allocating each one is possible but not very scalable.
>
> The question is if there is some way, we can do this with on-stack
> or a single on-heap rcu_head or equivalent that can achieve the same
> effect.
If the hctx structures are guaranteed to stay put, you could count
them and then do a single allocation of an array of rcu_head structures
(or some larger structure containing an rcu_head structure, if needed).
You could then sequence through this array, consuming one rcu_head per
hctx as you processed it. Once all the callbacks had been invoked,
it would be safe to free the array.
Sounds too simple, though. So what am I missing?
Thanx, Paul
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2020-07-29 0:31 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-27 23:10 [PATCH v5 0/2] improve nvme quiesce time for large amount of namespaces Sagi Grimberg
2020-07-27 23:10 ` [PATCH v5 1/2] blk-mq: add tagset quiesce interface Sagi Grimberg
2020-07-27 23:32 ` Keith Busch
2020-07-28 0:12 ` Sagi Grimberg
2020-07-28 1:40 ` Ming Lei
2020-07-28 1:51 ` Jens Axboe
2020-07-28 2:17 ` Ming Lei
2020-07-28 2:23 ` Jens Axboe
2020-07-28 2:28 ` Ming Lei
2020-07-28 2:32 ` Jens Axboe
2020-07-28 3:29 ` Sagi Grimberg
2020-07-28 3:25 ` Sagi Grimberg
2020-07-28 7:18 ` Christoph Hellwig
2020-07-28 7:48 ` Sagi Grimberg
2020-07-28 9:16 ` Ming Lei
2020-07-28 9:24 ` Sagi Grimberg
2020-07-28 9:33 ` Ming Lei
2020-07-28 9:37 ` Sagi Grimberg
2020-07-28 9:43 ` Sagi Grimberg
2020-07-28 10:10 ` Ming Lei
2020-07-28 10:57 ` Christoph Hellwig
2020-07-28 14:13 ` Paul E. McKenney
2020-07-28 10:58 ` Christoph Hellwig
2020-07-28 16:25 ` Sagi Grimberg
2020-07-28 13:54 ` Paul E. McKenney
2020-07-28 23:46 ` Sagi Grimberg
2020-07-29 0:31 ` Paul E. McKenney [this message]
2020-07-29 0:43 ` Sagi Grimberg
2020-07-29 0:59 ` Keith Busch
2020-07-29 4:39 ` Sagi Grimberg
2020-08-07 9:04 ` Chao Leng
2020-08-07 9:24 ` Ming Lei
2020-08-07 9:35 ` Chao Leng
2020-07-29 4:10 ` Paul E. McKenney
2020-07-29 4:37 ` Sagi Grimberg
2020-07-27 23:10 ` [PATCH v5 2/2] nvme: use blk_mq_[un]quiesce_tagset Sagi Grimberg
2020-07-28 0:54 ` Sagi Grimberg
2020-07-28 3:21 ` Chao Leng
2020-07-28 3:34 ` Sagi Grimberg
2020-07-28 3:51 ` Chao Leng
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=20200729003124.GT9247@paulmck-ThinkPad-P72 \
--to=paulmck@kernel.org \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=lengchao@huawei.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=ming.lei@redhat.com \
--cc=mlin@kernel.org \
--cc=sagi@grimberg.me \
/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).