All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nigel Cunningham <nigel@tuxonice.net>
To: Mark Lord <kernel@teksavvy.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	pm list <linux-pm@lists.linux-foundation.org>
Subject: Re: 2.6.35 Regression: Ages spent discarding blocks that weren't used!
Date: Thu, 05 Aug 2010 07:22:30 +1000	[thread overview]
Message-ID: <4C59DA16.4020500@tuxonice.net> (raw)
In-Reply-To: <4C5960B0.7020003@teksavvy.com>

Hi.

On 04/08/10 22:44, Mark Lord wrote:
> Looks to me like more and more things are using the block discard
> functionality, and as predicted it is slowing things down enormously.
>
> The problem is that we still only discard tiny bits (a single range
> still??)
> per TRIM command, rather than batching larger ranges and larger numbers
> of ranges into single TRIM commands.
>
> That's a very poor implementation, especially when things start enabling
> it by default. Eg. the swap code, mke2fs, etc..
>
> Ugh.

I was hoping for a nice quick and simple answer. Since I haven't got 
one, I'll try to find time to do a git bisect. I think I'll also look at 
the swap code more carefully and see if it's doing the sensible thing. I 
can't (at the moment) see the logic behind calling discard when 
allocating swap. At freeing time makes much more sense to me.

Regards,

Nigel

  parent reply	other threads:[~2010-08-04 21:22 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-08-04  1:40 2.6.35 Regression: Ages spent discarding blocks that weren't used! Nigel Cunningham
2010-08-04  8:59 ` Stefan Richter
2010-08-04  9:16   ` Nigel Cunningham
2010-08-04  9:16   ` Nigel Cunningham
2010-08-04  8:59 ` Stefan Richter
2010-08-04 12:44 ` Mark Lord
2010-08-04 12:44 ` Mark Lord
2010-08-04 18:02   ` Martin K. Petersen
2010-08-04 18:02   ` Martin K. Petersen
2010-08-04 21:22   ` Nigel Cunningham
2010-08-04 21:22   ` Nigel Cunningham [this message]
2010-08-05  3:58     ` Hugh Dickins
2010-08-05  6:28       ` Nigel Cunningham
2010-08-06  1:15         ` Hugh Dickins
2010-08-06  1:15         ` Hugh Dickins
2010-08-06  4:40           ` Nigel Cunningham
2010-08-06 22:07             ` Hugh Dickins
2010-08-06 22:07             ` Hugh Dickins
2010-08-07 22:47               ` Nigel Cunningham
2010-08-07 22:47               ` Nigel Cunningham
2010-08-13 11:54               ` Christoph Hellwig
2010-08-13 18:15                 ` Hugh Dickins
2010-08-14 11:43                   ` Christoph Hellwig
2010-08-14 11:43                   ` Christoph Hellwig
2010-08-13 18:15                 ` Hugh Dickins
2010-08-13 11:54               ` Christoph Hellwig
2010-08-06  4:40           ` Nigel Cunningham
2010-08-05  6:28       ` Nigel Cunningham
2010-08-05  3:58     ` Hugh Dickins
2010-08-04  1:40 Nigel Cunningham

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=4C59DA16.4020500@tuxonice.net \
    --to=nigel@tuxonice.net \
    --cc=kernel@teksavvy.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@lists.linux-foundation.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 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.