All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mark Knecht <markknecht@gmail.com>
To: Learner Study <learner.study@gmail.com>
Cc: linux-raid@vger.kernel.org, keld@dkuug.dk
Subject: Re: Linux Raid performance
Date: Fri, 2 Apr 2010 17:39:45 -0700	[thread overview]
Message-ID: <l2j5bdc1c8b1004021739z969b99v6011fcc6fddd470a@mail.gmail.com> (raw)
In-Reply-To: <x2q7efa8a7d1004021055oe2e832ccl8877e9171b8f3442@mail.gmail.com>

On Fri, Apr 2, 2010 at 10:55 AM, Learner Study <learner.study@gmail.com> wrote:
<SNIP>
>
> 2. Secondly, I would like to understand how raid stack (md driver)
> scales as we add more cores...if single core gives ~500MB/s, can two
> core give ~1000MB/s? can four cores give ~2000MB/s? etc....
<SNIP>

More cores by themselves certainly won't do it for you.

1) More disks in parallel. (striped data)

2) More ports to attach those drives.

3) More bandwidth on those ports. SATA3 is better than SATA2 is better
than SATA is better than PATA, etc. (Obviously disks must match ports,
right? SATA1 disks on SATA3 ports isn't the right thing...)

4) More bus bandwidth getting to those ports. PCI-Express16 is better
than PCI-Express1 is better than PCI, etc.

5) Faster RAID architectures for the number of disks chosen.

Once all of that is in place then possibly more cores will help, but I
suspect even then it probably hard to use 4 billion CPU cycles/second
doing nothing but disk I/O. SATA controllers are all doing DMA so CPU
overhead is relatively *very* low.

HTH,
Mark

  parent reply	other threads:[~2010-04-03  0:39 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-31 19:42 Linux Raid performance Learner Study
2010-03-31 20:15 ` Keld Simonsen
2010-04-02  3:07   ` Learner Study
2010-04-02  9:58     ` Nicolae Mihalache
2010-04-02 17:58       ` Learner Study
2010-04-02 11:05     ` Keld Simonsen
2010-04-02 11:18       ` Keld Simonsen
2010-04-02 17:55       ` Learner Study
2010-04-02 21:14         ` Keld Simonsen
2010-04-02 21:37           ` Learner Study
2010-04-03 11:20             ` Keld Simonsen
2010-04-03 15:56               ` Learner Study
2010-04-04  1:58                 ` Keld Simonsen
2010-04-03  0:10           ` Learner Study
2010-04-03  0:39         ` Mark Knecht [this message]
2010-04-03  1:00           ` John Robinson
2010-04-03  1:14           ` Richard Scobie
2010-04-03  1:32             ` Mark Knecht
2010-04-03  1:37               ` Richard Scobie
2010-04-03  3:06                 ` Learner Study
2010-04-03  3:00             ` Learner Study
2010-04-03 19:27               ` Richard Scobie
2010-04-03 18:14             ` MRK
2010-04-03 19:56               ` Richard Scobie
2010-04-04 15:00                 ` MRK
2010-04-04 18:26                   ` Learner Study
2010-04-04 18:46                     ` Mark Knecht
2010-04-04 21:28                       ` Jools Wills
2010-04-04 22:38                         ` Mark Knecht
2010-04-05 10:07                           ` Learner Study
2010-04-05 16:35                             ` John Robinson
2010-04-04 22:24                       ` Guy Watkins
2010-04-05 13:49                         ` Drew
2010-04-04 23:24                   ` Richard Scobie
2010-04-05 11:20                     ` MRK
2010-04-05 19:49                       ` Richard Scobie
2010-04-05 21:03                         ` Drew
2010-04-05 22:20                           ` Richard Scobie
2010-04-05 23:49                           ` Roger Heflin
2010-04-14 20:50             ` Bill Davidsen

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=l2j5bdc1c8b1004021739z969b99v6011fcc6fddd470a@mail.gmail.com \
    --to=markknecht@gmail.com \
    --cc=keld@dkuug.dk \
    --cc=learner.study@gmail.com \
    --cc=linux-raid@vger.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 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.