From: Stan Hoeppner <stan@hardwarefreak.com>
To: Phillip Susi <psusi@ubuntu.com>
Cc: linux-raid@vger.kernel.org
Subject: Re: Very long raid5 init/rebuild times
Date: Mon, 03 Feb 2014 21:30:21 -0600 [thread overview]
Message-ID: <52F05ECD.5060804@hardwarefreak.com> (raw)
In-Reply-To: <52EFAACE.40906@ubuntu.com>
On 2/3/2014 8:42 AM, Phillip Susi wrote:
> On 2/3/2014 1:34 AM, Stan Hoeppner wrote:
>> Please reread my statement above. Now let me restate that as:
>>
>> Measuring disk throughput when writing through the buffer cache
>> isn't a measurement of disk throughput as much as it is a
>> measurement of cache throughput. Thus, such measurements do not
>> demonstrate actual disk throughput.
>>
>> Do you disagree?
>
> Yes, I do because cache throughput is >>>> disk throughput.
It is because buffer cache throughput is greater that measurements of
disk throughput are not accurate. If one issues a sync after writing
through buffer cache the measured throughput should be fairly close.
But without issuing a sync you're measuring buffer cache throughput.
Thus, as I said previously, it is better to do parallel O_DIRECT writes
or use AIO with O_DIRECT for testing disk throughput as one doesn't have
to worry about these buffer cache issues.
--
Stan
next prev parent reply other threads:[~2014-02-04 3:30 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-21 7:35 Very long raid5 init/rebuild times Marc MERLIN
2014-01-21 16:37 ` Marc MERLIN
2014-01-21 17:08 ` Mark Knecht
2014-01-21 18:42 ` Chris Murphy
2014-01-22 7:55 ` Stan Hoeppner
2014-01-22 17:48 ` Marc MERLIN
2014-01-22 23:17 ` Stan Hoeppner
2014-01-23 14:28 ` John Stoffel
2014-01-24 1:02 ` Stan Hoeppner
2014-01-24 3:07 ` NeilBrown
2014-01-24 8:24 ` Stan Hoeppner
2014-01-23 2:37 ` Stan Hoeppner
2014-01-23 9:13 ` Marc MERLIN
2014-01-23 12:24 ` Stan Hoeppner
2014-01-23 21:01 ` Marc MERLIN
2014-01-24 5:13 ` Stan Hoeppner
2014-01-25 8:36 ` Marc MERLIN
2014-01-28 7:46 ` Stan Hoeppner
2014-01-28 16:50 ` Marc MERLIN
2014-01-29 0:56 ` Stan Hoeppner
2014-01-29 1:01 ` Marc MERLIN
2014-01-30 20:47 ` Phillip Susi
2014-02-01 22:39 ` Stan Hoeppner
2014-02-02 18:53 ` Phillip Susi
2014-02-03 6:34 ` Stan Hoeppner
2014-02-03 14:42 ` Phillip Susi
2014-02-04 3:30 ` Stan Hoeppner [this message]
2014-02-04 17:59 ` Larry Fenske
2014-02-04 18:08 ` Phillip Susi
2014-02-04 18:43 ` Stan Hoeppner
2014-02-04 18:55 ` Phillip Susi
2014-02-04 19:15 ` Stan Hoeppner
2014-02-04 20:16 ` Phillip Susi
2014-02-04 21:58 ` Stan Hoeppner
2014-02-05 1:19 ` Phillip Susi
2014-02-05 1:42 ` Stan Hoeppner
2014-01-30 20:36 ` Phillip Susi
2014-01-30 20:18 ` Phillip Susi
2014-01-22 19:38 ` Opal 2.0 SEDs on linux, was: " Chris Murphy
2014-01-21 18:31 ` Chris Murphy
2014-01-22 13:46 ` Ethan Wilson
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=52F05ECD.5060804@hardwarefreak.com \
--to=stan@hardwarefreak.com \
--cc=linux-raid@vger.kernel.org \
--cc=psusi@ubuntu.com \
/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).