linux-kernel - Re: [PATCH] ring-buffer: speed up buffer resets by avoiding synchronize

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 29 Jun 2020 18:16:25 -0400
From:   Steven Rostedt <rostedt@...dmis.org>
To:     Nicholas Piggin <npiggin@...il.com>
Cc:     Paul McKenney <paulmck@...nel.org>,
        Anton Blanchard <anton@...abs.org>,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH] ring-buffer: speed up buffer resets by avoiding
 synchronize_rcu for each CPU

On Thu, 25 Jun 2020 15:34:03 +1000
Nicholas Piggin <npiggin@...il.com> wrote:

> Batch these up so we disable all the per-cpu buffers first, then
> synchronize_rcu() once, then reset each of the buffers. This brings
> the time down to about 0.5s.

After applying this patch, running tools/testing/selftests/ftracetest
went from 5 minutes and 35 seconds to 5 minutes 5 seconds to complete
on my 4 core (8 with hyperthreading) machine! That's almost a 10% drop!

Thanks, I'm definitely applying this for the next merge window.

-- Steve