linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: NeilBrown <neilb@suse.de>
To: Daniel Pocock <daniel@pocock.com.au>
Cc: linux-raid@vger.kernel.org
Subject: Re: read-ahead for md/lvm combination
Date: Sun, 13 May 2012 07:32:40 +1000	[thread overview]
Message-ID: <20120513073240.2d292ec4@notabene.brown> (raw)
In-Reply-To: <4FAD2866.8070209@pocock.com.au>

[-- Attachment #1: Type: text/plain, Size: 1485 bytes --]

On Fri, 11 May 2012 14:55:34 +0000 Daniel Pocock <daniel@pocock.com.au> wrote:

> 
> 
> While I was adding the SCTERC settings to my rc.local, I had a look over
> /sbin/blockdev --setra ... settings
> 
> I do things like this, for example:
> 
> /sbin/blockdev --setra 8192 /dev/mapper/myvg-large_media_files
> 
> What about
> - the devices /dev/sd[ab]2
> - the md device, /dev/md2  (which is the PV for LVM) ?
> 
> Would it be correct to leave /dev/sd[ab]2 and /dev/md2 at defaults, and
> only specify larger sizes for LVs that need it?  Or should I even make
> /dev/sd[ab]2 and /dev/md2 smaller than the default value (256)?

The read-ahead setting is interpreted by the pagecache.
So it only makes sense to set in on a device which is directly mounted or
accessed via /dev/XXX.

On other devices - such as the media device beneath and md array - you can
set the read-ahead to anything or nothing and it will have no effect at all.

NeilBrown

> 
> 
> Those disks are SATA - but I'm also planning to add in some SSDs and
> RAID1 them with md - they will hold things like source code and home
> directories (to make compiling and NFS home directories faster).  Can
> anyone comment on the read ahead config or any other aspect of such a plan?
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 828 bytes --]

      reply	other threads:[~2012-05-12 21:32 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-05-11 14:55 read-ahead for md/lvm combination Daniel Pocock
2012-05-12 21:32 ` NeilBrown [this message]

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=20120513073240.2d292ec4@notabene.brown \
    --to=neilb@suse.de \
    --cc=daniel@pocock.com.au \
    --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 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).