linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Disseldorp <ddiss@suse.de>
To: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org, linux-doc@vger.kernel.org,
	Matthew Wilcox <willy@infradead.org>
Subject: Re: [PATCH RESEND 1/3] initramfs: move unnecessary memcmp from hot path
Date: Wed, 4 Aug 2021 15:37:49 +0200	[thread overview]
Message-ID: <20210804153749.5bb69afd@suse.de> (raw)
In-Reply-To: <YQqOrCw29ff7zJHb@zeniv-ca.linux.org.uk>

On Wed, 4 Aug 2021 12:57:16 +0000, Al Viro wrote:

> On Wed, Aug 04, 2021 at 11:31:29AM +0200, David Disseldorp wrote:
> > Ping, any feedback on this change?
> > 
> > I think it's a no brainer, but for kicks I ran a few unrealistic micro
> > benchmarks on my laptop. Extraction time for a cpio image with 1M+
> > directories improved by 5ms (pre: 14.614s, post: 14.609s), when averaged
> > across 20 runs of:
> >   qemu-system-x86_64 -machine accel=kvm -smp cpus=1 -m 10240 \
> >         -kernel ~/linux/arch/x86/boot/bzImage \
> >         -initrd ./initrds/gen_cpio.out \
> >         -append "initramfs_async=0 console=ttyS0 panic=0" -nographic \
> >         | awk '/Trying to unpack rootfs/ {start_ts = $2};
> >                /Freeing initrd memory/ {end_ts = $2}
> >                END {printf "%f\n", end_ts - start_ts}'  
> 
> What was the dispersion for those runs?

Too high for the 5ms to be considered statistically significant. Std
deviations were pre: 171ms, post: 214ms... <sigh> I'll redo this on a
proper test rig.

Cheers, David

      reply	other threads:[~2021-08-04 13:37 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-21 11:51 [PATCH RESEND 1/3] initramfs: move unnecessary memcmp from hot path David Disseldorp
2021-07-21 11:51 ` [PATCH RESEND 2/3] initramfs: print helpful cpio error on "crc" magic David Disseldorp
2021-07-21 11:51 ` [PATCH v2 3/3] docs: remove mention of "crc" cpio format support David Disseldorp
2021-08-04  9:31 ` [PATCH RESEND 1/3] initramfs: move unnecessary memcmp from hot path David Disseldorp
2021-08-04 12:57   ` Al Viro
2021-08-04 13:37     ` David Disseldorp [this message]

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=20210804153749.5bb69afd@suse.de \
    --to=ddiss@suse.de \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@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;
as well as URLs for NNTP newsgroup(s).