git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Jon Smirl" <jonsmirl@gmail.com>
To: "Nicolas Pitre" <nico@cam.org>
Cc: "Junio C Hamano" <gitster@pobox.com>, git@vger.kernel.org
Subject: Re: [PATCH 2/2] pack-objects: fix threaded load balancing
Date: Mon, 10 Dec 2007 01:06:59 -0500	[thread overview]
Message-ID: <9e4733910712092206o40e0c748s3796b95f637bf2b3@mail.gmail.com> (raw)
In-Reply-To: <9e4733910712092159s24cf5a7cx4610f797f61b1de5@mail.gmail.com>

On 12/10/07, Jon Smirl <jonsmirl@gmail.com> wrote:
> I just deleted the section looking for identical hashes.
>
> +                       while (sub_size && list[0]->hash &&
> +                              list[0]->hash == list[-1]->hash) {
> +                               list++;
> +                               sub_size--;
> +                       }
>
> Doing that allows the long chains to be split over the cores.
>
> My last 5% of objects is taking over 50% of the total CPU time in the
> repack. I think these objects are the ones from that 103,817 entry
> chain. It is also causing the explosion in RAM consumption.
>
> At the end I can only do 20 objects per clock second on four cores. It
> takes 30 clock minutes (120 CPU minutes) to do the last 3% of objects.

It's all in create_delta...

samples  %        symbol name
10344074 98.5961  create_delta
138010    1.3155  create_delta_index
4380      0.0417  find_deltas
2526      0.0241  patch_delta
776       0.0074  unpack_entry



>
> Can the chains be limited to not grow over some reasonable number, say
> 5,000? It will make the pack a little bigger but it will help a lot
> with performance.
>
> --
> Jon Smirl
> jonsmirl@gmail.com
>


-- 
Jon Smirl
jonsmirl@gmail.com

  reply	other threads:[~2007-12-10  6:07 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-12-08  5:03 [PATCH 2/2] pack-objects: fix threaded load balancing Nicolas Pitre
2007-12-08  9:18 ` Jeff King
2007-12-10  4:10 ` Jon Smirl
2007-12-10  4:30 ` Jon Smirl
2007-12-10  5:23   ` Jon Smirl
2007-12-10  5:59     ` Jon Smirl
2007-12-10  6:06       ` Jon Smirl [this message]
2007-12-10  6:19         ` Jon Smirl
2007-12-10 16:03           ` Nicolas Pitre
2007-12-10 16:14         ` Nicolas Pitre
2007-12-10 17:06           ` Jon Smirl
2007-12-10 18:21             ` Nicolas Pitre
2007-12-10 19:19               ` [PATCH] pack-objects: more threaded load balancing fix with often changed paths Nicolas Pitre
2007-12-11 17:02 ` [PATCH 2/2] pack-objects: fix threaded load balancing Johannes Sixt
2007-12-11 17:28   ` Nicolas Pitre
2007-12-13  7:15     ` Johannes Sixt

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=9e4733910712092206o40e0c748s3796b95f637bf2b3@mail.gmail.com \
    --to=jonsmirl@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=nico@cam.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).