linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dan Christensen <jdc@uwo.ca>
To: mingz@ele.uri.edu
Cc: Linux RAID <linux-raid@vger.kernel.org>
Subject: Re: RAID-5 streaming read performance
Date: Wed, 13 Jul 2005 08:48:02 -0400	[thread overview]
Message-ID: <87eka2g9dp.fsf@uwo.ca> (raw)
In-Reply-To: <1121257494.5504.4.camel@localhost.localdomain>

Ming Zhang <mingz@ele.uri.edu> writes:

> have u try the parallel write?

I haven't tested it as thoroughly, as it brings lvm and the filesystem
into the mix.  (The disks are in "production" use, and are fairly
full, so I can't do writes directly to the disk partitions/raid
device.)

My preliminary finding is that raid writes are faster than non-raid
writes:  49MB/s vs 39MB/s.  Still not stellar performance, though.
Question for the list:  if I'm doing a long sequential write, naively
each parity block will get recalculated and rewritten several times,
once for each non-parity block in the stripe.  Does the write-caching
that the kernel does mean that each parity block will only get written
once?

Dan

  reply	other threads:[~2005-07-13 12:48 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-07-11 15:11 RAID-5 streaming read performance Dan Christensen
2005-07-13  2:08 ` Ming Zhang
2005-07-13  2:52   ` Dan Christensen
2005-07-13  3:15     ` berk walker
2005-07-13 12:24     ` Ming Zhang
2005-07-13 12:48       ` Dan Christensen [this message]
2005-07-13 12:52         ` Ming Zhang
2005-07-13 14:23           ` Dan Christensen
2005-07-13 14:29             ` Ming Zhang
2005-07-13 17:56               ` Dan Christensen
2005-07-13 22:38                 ` Neil Brown
2005-07-14  0:09                   ` Ming Zhang
2005-07-14  1:16                     ` Neil Brown
2005-07-14  1:25                       ` Ming Zhang
2005-07-13 18:02             ` David Greaves
2005-07-13 18:14               ` Ming Zhang
2005-07-13 21:18                 ` David Greaves
2005-07-13 21:44                   ` Ming Zhang
2005-07-13 21:50                     ` David Greaves
2005-07-13 21:55                       ` Ming Zhang
2005-07-13 22:52                   ` Neil Brown
2005-07-14  3:58               ` Dan Christensen
2005-07-14  4:13                 ` Mark Hahn
2005-07-14 21:16                   ` Dan Christensen
2005-07-14 21:30                     ` Ming Zhang
2005-07-14 23:29                       ` Mark Hahn
2005-07-15  1:23                         ` Ming Zhang
2005-07-15  2:11                           ` Dan Christensen
2005-07-15 12:28                             ` Ming Zhang
2005-07-14 12:30                 ` Ming Zhang
2005-07-14 14:23                   ` Ming Zhang
2005-07-14 17:54                   ` Dan Christensen
2005-07-14 18:00                     ` Ming Zhang
2005-07-14 18:03                       ` Dan Christensen
2005-07-14 18:10                         ` Ming Zhang
2005-07-14 19:16                           ` Dan Christensen
2005-07-14 20:13                             ` Ming Zhang
2005-07-15  2:38                 ` Dan Christensen
2005-07-15  6:01                   ` Holger Kiehl
2005-07-15 12:29                     ` Ming Zhang
2005-07-13 22:42         ` Neil Brown

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=87eka2g9dp.fsf@uwo.ca \
    --to=jdc@uwo.ca \
    --cc=linux-raid@vger.kernel.org \
    --cc=mingz@ele.uri.edu \
    /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).