linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stan Hoeppner <stan@hardwarefreak.com>
To: NeilBrown <neilb@suse.de>
Cc: Shaohua Li <shli@kernel.org>,
	linux-raid@vger.kernel.org, axboe@kernel.dk
Subject: Re: [patch 0/3 v3] MD: improve raid1/10 write performance for fast storage
Date: Thu, 28 Jun 2012 20:29:21 -0500	[thread overview]
Message-ID: <4FED04F1.8010902@hardwarefreak.com> (raw)
In-Reply-To: <20120628190352.4dc1dd76@notabene.brown>

On 6/28/2012 4:03 AM, NeilBrown wrote:
> On Wed, 13 Jun 2012 17:11:43 +0800 Shaohua Li <shli@kernel.org> wrote:
> 
>> In raid1/10, all write requests are dispatched in a single thread. In fast
>> storage, the thread is a bottleneck, because it dispatches request too slow.
>> Also the thread migrates freely, which makes request completion cpu not match
>> with submission cpu even driver/block layer has such capability. This will
>> cause bad cache issue. Both these are not a big deal for slow storage.
>>
>> Switching the dispatching to percpu/perthread based dramatically increases
>> performance.  The more raid disk number is, the more performance boosts. In a
>> 4-disk raid10 setup, this can double the throughput.
>>
>> percpu/perthread based dispatch doesn't harm slow storage. This is the way how
>> raw device is accessed, and there is correct block plug set which can help do
>> request merge and reduce lock contention.
>>
>> V2->V3:
>> rebase to latest tree and fix cpuhotplug issue
>>
>> V1->V2:
>> 1. droped direct dispatch patches. That has better performance imporvement, but
>> is hopelessly made correct.
>> 2. Add a MD specific workqueue to do percpu dispatch.


> I still don't like the per-cpu allocations and the extra work queues.

Why don't you like this method Neil?  Complexity?  The performance seems
to be there.

-- 
Stan

  reply	other threads:[~2012-06-29  1:29 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-13  9:11 [patch 0/3 v3] MD: improve raid1/10 write performance for fast storage Shaohua Li
2012-06-13  9:11 ` [patch 1/3 v3] MD: add a specific workqueue to do dispatch Shaohua Li
2012-06-13  9:11 ` [patch 2/3 v3] raid1: percpu dispatch for write request if bitmap supported Shaohua Li
2012-06-13  9:11 ` [patch 3/3 v3] raid10: " Shaohua Li
2012-06-28  9:03 ` [patch 0/3 v3] MD: improve raid1/10 write performance for fast storage NeilBrown
2012-06-29  1:29   ` Stan Hoeppner [this message]
2012-06-29  2:52     ` NeilBrown
2012-06-29  3:02       ` Roberto Spadim
2012-06-30  4:37       ` Stan Hoeppner
2012-06-29  6:10   ` Shaohua Li
2012-07-02  7:36     ` Shaohua Li
2012-07-03  8:58       ` Shaohua Li
2012-07-04  1:45         ` NeilBrown

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=4FED04F1.8010902@hardwarefreak.com \
    --to=stan@hardwarefreak.com \
    --cc=axboe@kernel.dk \
    --cc=linux-raid@vger.kernel.org \
    --cc=neilb@suse.de \
    --cc=shli@kernel.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).