From: <yael.chemla@foss.arm.com>
To: 'Mike Snitzer' <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Subject: Re: md: dm-verity: aggregate crypto API calls
Date: Thu, 14 Dec 2017 09:54:24 +0200 [thread overview]
Message-ID: <008101d374b0$c4b5ef00$4e21cd00$@foss.arm.com> (raw)
In-Reply-To: <20171025151916.GA28274@redhat.com>
we are trying to be able to parallalize the handling of blocks, this patch is a precursor to that effort.
currently this patch does not change CPU utiliztion but we wanted to veritfy there is no objection to the direction first, hence sending the patch.
Thanks,
Yael
-----Original Message-----
From: Mike Snitzer [mailto:snitzer@redhat.com]
Sent: Wednesday, 25 October 2017 18:19
To: Yael Chemla <yael.chemla@foss.arm.com>
Cc: dm-devel@redhat.com
Subject: Re: md: dm-verity: aggregate crypto API calls
On Wed, Oct 25 2017 at 4:58am -0400,
Yael Chemla <yael.chemla@foss.arm.com> wrote:
> Current implementation makes multiple crypto API calls for a single
> block, forcing underlying crypto tfm implementation to "stop & go",
> leading to under utilization of CPU (e.g. SIMD state saves) or HW
> engines. To fix it unify calls to crypto init/update/final into a
> digest call with a single sg which contains multiple buffers.
>
> This also opens the way later on to parallelizing the work on
> different blocks.
>
> Tested on physical Arm 32 and x86_64 and virtual ARM 64.
>
> Performance numbers were not changed.
OK, but what about CPU utilization? Was it reduced?
Thanks,
Mike
next prev parent reply other threads:[~2017-12-14 7:54 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-25 8:58 [PATCH] md: dm-verity: aggregate crypto API calls Yael Chemla
2017-10-25 15:19 ` Mike Snitzer
2017-12-14 7:54 ` yael.chemla [this message]
2017-12-16 1:58 ` Mike Snitzer
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='008101d374b0$c4b5ef00$4e21cd00$@foss.arm.com' \
--to=yael.chemla@foss.arm.com \
--cc=dm-devel@redhat.com \
--cc=snitzer@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.