From: Eric Dumazet <eric.dumazet@gmail.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: herbert@gondor.hengli.com.au, dm-devel@redhat.com,
linux-kernel@vger.kernel.org, agk@redhat.com, ak@linux.intel.com
Subject: Re: [PATCH] DM-CRYPT: Scale to multiple CPUs
Date: Mon, 31 May 2010 18:34:55 +0200 [thread overview]
Message-ID: <1275323695.3291.122.camel@edumazet-laptop> (raw)
In-Reply-To: <20100531160425.GA20344@basil.fritz.box>
Le lundi 31 mai 2010 à 18:04 +0200, Andi Kleen a écrit :
> DM-CRYPT: Scale to multiple CPUs
>
> Currently dm-crypt does all encryption work per dmcrypt mapping in a
> single workqueue. This does not scale well when multiple CPUs
> are submitting IO at a high rate. The single CPU running the single
> thread cannot keep up with the encryption and encrypted IO performance
> tanks.
>
> This patch changes the crypto workqueue to be per CPU. This means
> that as long as the IO submitter (or the interrupt target CPUs
> for reads) runs on different CPUs the encryption work will be also
> parallel.
>
> To avoid a bottleneck on the IO worker I also changed those to be
> per CPU threads.
>
> There is still some shared data, so I suspect some bouncing
> cache lines. But I haven't done a detailed study on that yet.
>
> All the threads are global, not per CPU. That is to avoid a thread
> explosion on systems with a large number of CPUs and a larger
> number of dm-crypt mappings. The code takes care to avoid problems
> with nested mappings.
>
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> /*
> + * Duplicated per cpu state. Access through
> + * per_cpu_ptr() only.
> + */
> + struct crypt_cpu *cpu;
> +
> + /*
> * Layout of each crypto request:
> *
Since commit e0fdb0e050eae331, we have a __percpu annotation so that
sparse can be augmented. This would also make the comment unnecessary...
We also have this_cpu_ accessors
> + return per_cpu_ptr(cc->cpu, smp_processor_id());
this_cpu_ptr(cc->cpu)
and __thic_cpu_ptr() for the 'raw' version
> + __get_cpu_var(io_wq_cpu) = current;
this_cpu_write(io_wq_cpu, current)
next prev parent reply other threads:[~2010-05-31 16:57 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-31 16:04 Andi Kleen
2010-05-31 16:34 ` Eric Dumazet [this message]
2010-05-31 17:46 ` Andi Kleen
2010-05-31 17:52 ` Eric Dumazet
2010-05-31 17:22 ` [dm-devel] " Milan Broz
2010-05-31 17:42 ` Andi Kleen
2010-05-31 18:10 ` Milan Broz
2010-05-31 18:27 ` Andi Kleen
2010-05-31 18:55 ` Milan Broz
2010-05-31 19:04 ` Andi Kleen
2010-05-31 22:07 ` Herbert Xu
2010-06-01 1:46 ` huang ying
2010-06-01 2:39 ` Mikulas Patocka
2010-06-01 2:44 ` Mikulas Patocka
2010-06-01 4:39 ` Herbert Xu
2010-06-02 5:10 ` Mikulas Patocka
2010-06-02 5:14 ` Herbert Xu
2010-06-02 5:25 ` Mikulas Patocka
2010-06-02 6:07 ` Herbert Xu
2010-06-02 6:30 ` Steffen Klassert
2010-06-02 7:07 ` Herbert Xu
2010-06-02 7:51 ` Andi Kleen
2010-06-01 6:40 ` Andi Kleen
2010-06-02 5:15 ` Mikulas Patocka
2010-06-02 5:20 ` Herbert Xu
2010-06-02 7:53 ` Andi Kleen
2010-06-02 10:20 ` Herbert Xu
2010-05-31 18:47 Tomasz Chmielewski
2010-06-01 7:21 ` Andi Kleen
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=1275323695.3291.122.camel@edumazet-laptop \
--to=eric.dumazet@gmail.com \
--cc=agk@redhat.com \
--cc=ak@linux.intel.com \
--cc=andi@firstfloor.org \
--cc=dm-devel@redhat.com \
--cc=herbert@gondor.hengli.com.au \
--cc=linux-kernel@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
all inboxes | Powered by JetHome®