From: Oliver Martin <oliver.martin@student.tuwien.ac.at>
To: Peter Grandi <pg_lxra@lxra.for.sabi.co.UK>
Cc: Linux RAID <linux-raid@vger.kernel.org>
Subject: Re: LVM performance
Date: Fri, 22 Feb 2008 14:41:45 +0100 [thread overview]
Message-ID: <47BED119.4070000@student.tuwien.ac.at> (raw)
In-Reply-To: <18364.6868.854623.613958@tree.ty.sabi.co.UK>
Peter Grandi schrieb:
> Those are as such not very meaningful. What matters most is
> whether the starting physical address of each logical volume
> extent is stripe aligned (and whether the filesystem makes use
> of that) and then the stripe size of the parity RAID set, not
> the chunk sizes in themselves.
>
> I am often surprised by how many people who use parity RAID
> don't seem to realize the crucial importance of physical stripe
> alignment, but I am getting used to it.
Am I right to assume that stripe alignment matters because of the
read-modify-write cycle needed for unaligned writes? If so, how come a
pure read benchmark (hdparm -t or plain dd) is slower on the LVM device
than on the md device?
Oliver
next prev parent reply other threads:[~2008-02-22 13:41 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-02-17 3:58 RAID5 to RAID6 reshape? Beolach
2008-02-17 11:50 ` Peter Grandi
2008-02-17 14:45 ` Conway S. Smith
2008-02-18 5:26 ` Janek Kozicki
2008-02-18 12:38 ` Beolach
2008-02-18 14:42 ` Janek Kozicki
2008-02-19 19:41 ` LVM performance (was: Re: RAID5 to RAID6 reshape?) Oliver Martin
2008-02-19 19:52 ` Jon Nelson
2008-02-19 20:00 ` Iustin Pop
2008-02-19 23:19 ` LVM performance Peter Rabbitson
2008-02-20 12:19 ` LVM performance (was: Re: RAID5 to RAID6 reshape?) Peter Grandi
2008-02-22 13:41 ` Oliver Martin [this message]
2008-03-07 8:14 ` LVM performance Peter Grandi
2008-03-09 19:56 ` Oliver Martin
2008-03-09 21:13 ` Michael Guntsche
2008-03-09 23:27 ` Oliver Martin
2008-03-09 23:53 ` Michael Guntsche
2008-03-10 8:54 ` Oliver Martin
2008-03-10 21:04 ` Peter Grandi
2008-03-12 14:03 ` Michael Guntsche
2008-03-12 19:54 ` Peter Grandi
2008-03-12 20:11 ` Guntsche Michael
2008-03-10 0:32 ` Richard Scobie
2008-03-10 0:53 ` Michael Guntsche
2008-03-10 0:59 ` Richard Scobie
2008-03-10 1:21 ` Michael Guntsche
2008-02-18 19:05 ` RAID5 to RAID6 reshape? Peter Grandi
2008-02-20 6:39 ` Alexander Kühn
2008-02-22 8:13 ` Peter Grandi
2008-02-23 20:40 ` Nagilum
2008-02-25 0:10 ` Peter Grandi
2008-02-25 16:31 ` Nagilum
2008-02-17 13:31 ` Janek Kozicki
2008-02-17 16:18 ` Conway S. Smith
2008-02-18 3:48 ` Neil Brown
2008-02-17 22:40 ` Mark Hahn
2008-02-17 23:54 ` Janek Kozicki
2008-02-18 12:46 ` Andre Noll
2008-02-18 18:23 ` Mark Hahn
2008-02-17 14:06 ` Janek Kozicki
2008-02-17 23:54 ` cat
2008-02-18 3:43 ` 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=47BED119.4070000@student.tuwien.ac.at \
--to=oliver.martin@student.tuwien.ac.at \
--cc=linux-raid@vger.kernel.org \
--cc=pg_lxra@lxra.for.sabi.co.UK \
/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).