From: "Keld Jørn Simonsen" <keld@dkuug.dk>
To: linux-raid@vger.kernel.org
Subject: my io testing scripts
Date: Mon, 11 Feb 2008 18:25:36 +0100 [thread overview]
Message-ID: <20080211172536.GA26017@rap.rap.dk> (raw)
Here are my testing scripts used in the performance howto:
http://linux-raid.osdl.org/index.php/Home_grown_testing_methods
=Hard disk performance scripts=
Here are the scripts that I used for my performance measuring. Use at your own risk.
They destroy the contents of the partitions involved. The /dev/md raid needs to
be stopped before initiating the test.
Copyright Keld Simonsen, keld@dkuug.dk 2008. Licensed under the GPL.
iotest:
#!/bin/sh
# invoked by
# iotest "mdadm -R -C /dev/md1 --chunk=256 -l 10 -n 2 -p f2 " /dev/md1 /mnt/md1 ext3 " /dev/hdb5 /dev/hdd5 "
echo "\n" $1 $5 "\n" >> /tmp/results
echo $1 $5
$1 $5
mkfs -t $4 $2
mkdir $3
mount $2 $3
cd $3
echo "\nmakefiles\n" >> /tmp/results
mkfiles 200
echo "\n remakefiles \n" >>/tmp/results
mkfiles 200
echo "\n catall \n" >>/tmp/results
cat * >/dev/null
echo "\n catnull \n" >>/tmp/results
catnull
cd
umount $2
mdadm -S $2
echo "\n finish " $1 " " $5 "\n" >> /tmp/results
Be careful with this script, and remember to change the ordinary test to only one partition
iorun:
#!/bin/sh
# set up ram disk
DISKS="/dev/sda2 /dev/sdb2"
iostat -k 10 > /tmp/results &
iotest " " /dev/sda2 /mnt/sda2 ext3 " "
iotest "mdadm -C /dev/md1 --chunk=256 -R -l 0 -n 2 " /dev/md1 /mnt/md1 ext3 "$DISKS"
iotest "mdadm -C /dev/md1 --chunk=256 -R -l 1 -n 2 " /dev/md1 /mnt/md1 ext3 "$DISKS"
iotest "mdadm -C /dev/md1 --chunk=256 -R -l 10 -n 2 " /dev/md1 /mnt/md1 ext3 "$DISKS"
iotest "mdadm -C /dev/md1 --chunk=256 -R -l 10 -n 2 -p f2 " /dev/md1 /mnt/md1 ext3 "$DISKS"
# iotest "mdadm -C /dev/md1 --chunk=256 -R -l 10 -n 2 -p o2 " /dev/md1 /mnt/md1 ext3 "$DISKS"
mkfiles:
#!/bin/sh
for (( i = 1; i < $1 ; i++ )) ; do dd if=/dev/hda1 of=$i bs=1MB count=40 ; done
for (( i = 1; i < $1 ; i++ )) ; do dd if=/dev/hda1 of=$i bs=1MB count=40 & ; done
catnull:
#!/bin/tcsh
foreach i ( * )
cat $i >/dev/null &
end
wait
reply other threads:[~2008-02-11 17:25 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20080211172536.GA26017@rap.rap.dk \
--to=keld@dkuug.dk \
--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).