From: Andi Kleen <andi@firstfloor.org>
To: "Theodore Ts'o" <tytso@mit.edu>,
George Spelvin <linux@horizon.com>,
ahferroin7@gmail.com, andi@firstfloor.org, jepler@unpythonic.net,
linux-kernel@vger.kernel.org, linux@rasmusvillemoes.dk
Subject: Re: Updated scalable urandom patchkit
Date: Tue, 13 Oct 2015 18:20:44 +0200 [thread overview]
Message-ID: <20151013162044.GD3533@two.firstfloor.org> (raw)
In-Reply-To: <20151013024645.GA31306@thunk.org>
I tested the two proposed patches from earlier this thread on a 4S
system. This was just with my (worst case) micro.
Unfortunately both patches scale much worse than the duplicated pools,
and can be even worse than the baseline (not sure why).
The base line peaks at slightly above 200K ops/s with less than 20 CPUs.
And the it gets slower until settling around 100K ops/s with more CPUs.
Ted's patch peaks at 350K with four CPUs, but then quickly degrades to
50K ops/s at 20+ CPUs. At 144 CPUs it is slightly faster again at ~80K.
Spelvin's patch peaks at only 140K at 2 CPUs (so it's slower than base line),
stays around 120K upto 20, then degrades quickly to 50K and then slowly
improves again to ~80K.
The duplicated pool patch is ~200K upto 20 CPus, 400K upto 40, 600K at
slightly below 60 CPUs, and then very slowly degrades to 520K at 144.
-Andi
next prev parent reply other threads:[~2015-10-13 16:20 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-10 18:45 Updated scalable urandom patchkit George Spelvin
2015-10-11 2:31 ` Theodore Ts'o
2015-10-11 2:53 ` Theodore Ts'o
2015-10-11 4:35 ` George Spelvin
2015-10-11 22:25 ` Theodore Ts'o
2015-10-12 0:16 ` George Spelvin
2015-10-12 4:05 ` Theodore Ts'o
2015-10-12 7:49 ` George Spelvin
2015-10-12 13:54 ` Theodore Ts'o
2015-10-12 20:30 ` George Spelvin
2015-10-12 20:34 ` George Spelvin
2015-10-13 2:46 ` Theodore Ts'o
2015-10-13 3:50 ` Raymond Jennings
2015-10-13 7:50 ` George Spelvin
2015-10-13 6:24 ` George Spelvin
2015-10-13 16:20 ` Andi Kleen [this message]
2015-10-13 21:10 ` George Spelvin
2015-10-14 2:15 ` Andi Kleen
2015-10-16 5:28 ` [RFC PATCH 0/4] Alternate sclable urandom patchset George Spelvin
2015-10-16 5:29 ` [RFC PATCH 1/4] random: Reduce stack usage in _xfer_secondary_pool George Spelvin
2015-10-16 5:30 ` [RFC PATCH 2/4] random: Remove two unused arguments from extract_entropy() George Spelvin
2015-10-16 5:33 ` [RFC PATCH 3/4] random: Only do mixback once per read George Spelvin
2015-10-16 6:12 ` kbuild test robot
2015-10-16 8:11 ` George Spelvin
2015-10-16 6:23 ` kbuild test robot
2015-10-16 5:34 ` [RFC PATCH 4/4] random: Make non-blocking mixback non-blocking George Spelvin
2015-10-21 8:27 ` Updated scalable urandom patchkit George Spelvin
2015-10-21 11:47 ` Andi Kleen
2015-10-21 18:10 ` George Spelvin
-- strict thread matches above, loose matches on Subject: below --
2015-09-24 17:19 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=20151013162044.GD3533@two.firstfloor.org \
--to=andi@firstfloor.org \
--cc=ahferroin7@gmail.com \
--cc=jepler@unpythonic.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@horizon.com \
--cc=linux@rasmusvillemoes.dk \
--cc=tytso@mit.edu \
/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.