dm-devel.redhat.com archive mirror
 help / color / mirror / Atom feed
From: Alasdair G Kergon <agk@redhat.com>
To: device-mapper development <dm-devel@redhat.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>, Milan Broz <mbroz@redhat.com>
Subject: Re: [PATCH 20/20] dm-crypt: sort writes
Date: Tue, 21 Aug 2012 11:57:48 +0100	[thread overview]
Message-ID: <20120821105748.GB29183@agk-dp.fab.redhat.com> (raw)
In-Reply-To: <55cef4f342136f3b57d7449b88b4eb1fc6fc7569.1345477953.git.mbroz@redhat.com>

On Tue, Aug 21, 2012 at 11:09:31AM +0200, Mikulas Patocka wrote:
> In theory the sorting should be performed by the underlying disk scheduler,
> however, in practice the disk scheduler accepts and sorts only 128 requests.
> In order to sort more requests, we need to implement our own sorting.
 
Why 128?  Isn't this nr_requests?
(I thought we discussed this before.)

Alasdair

  reply	other threads:[~2012-08-21 10:57 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-21  9:08 [RFC PATCH 00/20] dm-crypt: parallel processing Milan Broz
2012-08-21  9:09 ` [PATCH 01/20] dm-crypt: remove per-cpu structure Mikulas Patocka
2012-08-21  9:09   ` [PATCH 02/20] dm-crypt: use unbound workqueue for request processing Mikulas Patocka
2012-08-21  9:09   ` [PATCH 03/20] dm-crypt: remove completion restart Mikulas Patocka
2012-08-21  9:09   ` [PATCH 04/20] dm-crypt: use encryption threads Mikulas Patocka
2012-08-21  9:09   ` [PATCH 05/20] dm-crypt: Unify spinlock Mikulas Patocka
2012-08-21  9:09   ` [PATCH 06/20] dm-crypt: Introduce an option that sets the number of threads Mikulas Patocka
2012-08-21  9:09   ` [PATCH 07/20] dm-crypt: don't use write queue Mikulas Patocka
2012-08-21  9:09   ` [PATCH 08/20] dm-crypt: simplify io queue Mikulas Patocka
2012-08-21  9:09   ` [PATCH 09/20] dm-crypt: unify io_queue and crypt_queue Mikulas Patocka
2012-08-21  9:09   ` [PATCH 10/20] dm-crypt: don't allocate pages for a partial request Mikulas Patocka
2012-08-21  9:09   ` [PATCH 11/20] dm-crypt: avoid deadlock in mempools Mikulas Patocka
2012-08-21  9:09   ` [PATCH 12/20] dm-crypt: simplify cc_pending Mikulas Patocka
2012-08-21  9:09   ` [PATCH 13/20] dm-crypt merge convert_context and dm_crypt_io Mikulas Patocka
2012-08-21  9:09   ` [PATCH 14/20] dm-crypt: move error handling to crypt_convert Mikulas Patocka
2012-08-21  9:09   ` [PATCH 15/20] dm-crypt: remove io_pending field Mikulas Patocka
2012-08-21  9:09   ` [PATCH 16/20] dm-crypt: small changes Mikulas Patocka
2012-08-21  9:09   ` [PATCH 17/20] dm-crypt: move temporary values to stack Mikulas Patocka
2012-08-21  9:09   ` [PATCH 18/20] dm-crypt: offload writes to thread Mikulas Patocka
2012-08-21  9:09   ` [PATCH 19/20] dm-crypt: retain write ordering Mikulas Patocka
2012-08-21  9:09   ` [PATCH 20/20] dm-crypt: sort writes Mikulas Patocka
2012-08-21 10:57     ` Alasdair G Kergon [this message]
2012-08-21 13:39       ` Mikulas Patocka
2012-08-21  9:37 ` [RFC PATCH 00/20] dm-crypt: parallel processing Milan Broz
2012-08-21 18:23   ` Tejun Heo
2012-08-21 19:26     ` Vivek Goyal
2012-08-22 10:28     ` Milan Broz
2012-08-23 20:15       ` Tejun Heo
2012-08-21 13:32 ` Mike Snitzer

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=20120821105748.GB29183@agk-dp.fab.redhat.com \
    --to=agk@redhat.com \
    --cc=dm-devel@redhat.com \
    --cc=mbroz@redhat.com \
    --cc=mpatocka@redhat.com \
    /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).