public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Kent Overstreet <kmo@daterainc.com>
To: Alexander Gordeev <agordeev@redhat.com>
Cc: linux-kernel@vger.kernel.org,
	Peter Zijlstra <peterz@infradead.org>,
	Jens Axboe <axboe@kernel.dk>,
	"Nicholas A. Bellinger" <nab@linux-iscsi.org>
Subject: Re: [PATCH 4/4] percpu_ida: Do not steal all remote CPU tags at once
Date: Wed, 26 Feb 2014 15:08:59 -0800	[thread overview]
Message-ID: <20140226230859.GG11655@kmo> (raw)
In-Reply-To: <20140216112528.GA13853@dhcp-26-207.brq.redhat.com>

On Sun, Feb 16, 2014 at 12:25:29PM +0100, Alexander Gordeev wrote:
> When stealing from a remote CPU all available tags are moved
> from the remote CPU's cache to the stealing CPU's one. Since
> the best CPU to steal from is not selected the victim might
> actively performing IO and (as result of losing all local
> tags) a further cycle of cache rebouncing and/or stealing
> could be provoked.
> 
> This update is an attempt to soften the described scenario
> and limit the number of tags to be stolen at once to the
> value of percpu_batch_size.

I don't want this patch without a benchmark justifying the change and more
analysis; this could easily lead to more stealing and cacheline bouncing.

> 
> Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
> Cc: Kent Overstreet <kmo@daterainc.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Jens Axboe <axboe@kernel.dk>
> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org>
> ---
>  lib/percpu_ida.c |   18 ++++++++++--------
>  1 files changed, 10 insertions(+), 8 deletions(-)
> 
> diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
> index fad029c..b4c4cc7 100644
> --- a/lib/percpu_ida.c
> +++ b/lib/percpu_ida.c
> @@ -84,20 +84,22 @@ static inline void steal_tags(struct percpu_ida *pool,
>  		pool->cpu_last_stolen = cpu;
>  		remote = per_cpu_ptr(pool->tag_cpu, cpu);
>  
> -		cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
> -
> -		if (remote == tags)
> +		if (remote == tags) {
> +			cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
>  			continue;
> +		}
>  
>  		spin_lock(&remote->lock);
>  
>  		if (remote->nr_free) {
> -			memcpy(tags->freelist,
> -			       remote->freelist,
> -			       sizeof(unsigned) * remote->nr_free);
> +			const struct percpu_ida *p = pool;
> +
> +			move_tags(tags->freelist, &tags->nr_free,
> +				  remote->freelist, &remote->nr_free,
> +				  min(remote->nr_free, p->percpu_batch_size));
>  
> -			tags->nr_free = remote->nr_free;
> -			remote->nr_free = 0;
> +			if (!remote->nr_free)
> +				cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
>  		}
>  
>  		spin_unlock(&remote->lock);
> -- 
> 1.7.7.6
> 
> -- 
> Regards,
> Alexander Gordeev
> agordeev@redhat.com

  reply	other threads:[~2014-02-26 23:09 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-02-06 12:24 [PATCH RESEND 0/3] percpu_ida: Various tweaks Alexander Gordeev
2014-02-06 12:24 ` [PATCH RESEND 1/3] percpu_ida: Fix data race on cpus_have_tags cpumask Alexander Gordeev
2014-02-26 23:05   ` Kent Overstreet
2014-03-02 14:42     ` Ming Lei
2014-03-11 14:03       ` Alexander Gordeev
2014-03-11 15:34         ` Ming Lei
2014-03-11 15:59           ` Alexander Gordeev
2014-03-11 16:31           ` Alexander Gordeev
2014-03-12 11:27             ` Ming Lei
2014-02-06 12:24 ` [PATCH RESEND 2/3] percpu_ida: Move waking up waiters out of atomic contexts Alexander Gordeev
2014-02-06 12:24 ` [PATCH RESEND 3/3] percpu_ida: Sanity check initialization parameters Alexander Gordeev
2014-02-26 23:07   ` Kent Overstreet
2014-02-16 11:25 ` [PATCH 4/4] percpu_ida: Do not steal all remote CPU tags at once Alexander Gordeev
2014-02-26 23:08   ` Kent Overstreet [this message]
2014-02-26 21:11 ` [PATCH RESEND 0/3] percpu_ida: Various tweaks Alexander Gordeev
2014-02-26 23:01   ` Kent Overstreet

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=20140226230859.GG11655@kmo \
    --to=kmo@daterainc.com \
    --cc=agordeev@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nab@linux-iscsi.org \
    --cc=peterz@infradead.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