iostat puzzle
Tolga Evren
tolgae at paro.com.tr
Thu Oct 6 19:45:20 UTC 2005
Hi Jeremy,
Thanks for your reply.
I use EMC disk array , and i have 1 HBA with fibre channel. This can provide 100MB. per second io.
My test sql is simple : select count(*) from table_a
The table size is 1gb.
When i run this by using aio , (which shows reasonable values in iostat , 100MB.read per second) it takes 15 sec. ( This is also expected with this io rate)
On the other hand , for the above case , it takes 30 sec. If 500mb. iorate is correct , this must take 3-4 secs.(including the overhead of file system)
Comparing the r/s values , the above output says :
r/s : 14344.44
rkB/s : 568785.19
%util : 1851.85
Issuing 14344.44 read request per second? Isnt 200-250 read per second io enough to saturate a scsi disk ?
(The %util value is also strange)
And , according to the iostat
avg-cpu: %user %nice %sys %idle
20.83 0.00 68.98 10.19
%sys is 68.98.
For the reasonable io , the r/s value is <500 and same amount of %sys is generated.
Most importanly , as i sad above , it takes longer .
This is a datawarehouse system . Most of the queries are full table scans and i always use parallel query .
The datafiles are not raw , i use ext3. ( This is development )
Direct-io which bypasses the page cache and puts data directly to the user process , is supported but not enabled on my server dues to an oracle bug.
I tuned the oracle in order to increase the perfomance of full table scans.
Oracle on each io operation via pread or kio , requests 1MB. data from the operating system.Oracle parallel query bypasses its own cache , so each parallel query requests data from the operating system.( Whether this data is supplied from the page cache or from the disk array depends on the io type.) I dont use directio , so page cache is used for my data files. I think this explain the sar -B page in values.
Kind Regards,
tolga
________________________________
From: redhat-list-bounces at redhat.com on behalf of Jeremy Lyon
Sent: Thu 10/6/2005 5:59 PM
To: General Red Hat Linux discussion list
Subject: Re: iostat puzzle
Tolga,
What kind of hardware do you have? Have you done some tests (with dd
perhaps) to see if you are actually getting this type of throughput?
Update 2 for RHEL 3 is pretty old. The latest rev of the kernel is
-37.ELsmp. You may want to consider updating.
Jeremy
redhat-list-bounces at redhat.com wrote on 10/05/2005 11:49:27 PM:
> Hi ,
>
> The below is the iostat output redhat linux 3.0 which shows very large
> values for rkB/s field (568785.19 )
>
> Reading 568785.19 kB per second! Impossible.
>
> $uname -a:
> Linux koccrmdev 2.4.21-15.ELsmp #1 SMP Thu Apr 22 00:18:24 EDT 2004
> i686 i686 i386 GNU/Linux
>
> $ cat /etc/redhat-release
> Red Hat Enterprise Linux ES release 3 (Taroon Update 2)
>
> I have oracle running on this server. I can basically regenerate this
> pattern easily ,this happens when i disable async. io at oracle part .
>
> With aio enabled , oracle does not use pread or readv system calls and
> i see reasonable values at iostat for the system.
>
> But when i disable it , iostat shows very high values.
>
> For clarity , when i get these results , the only user on the system is
>
> me.
>
> avg-cpu: %user %nice %sys %idle
> 20.83 0.00 68.98 10.19
>
> Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s rkB/s wkB/s
> avgrq-sz avgqu-sz await svctm %util
> /dev/sda 127851.85 7748.15 14344.44 879.63 1137570.37 69007.41
> 568785.19 34503.70 79.25 1966.67 12.91 1.22 1851.85
> /dev/sda1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 0.00 0.00 0.00 0.00
> /dev/sda2 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 0.00 0.00 0.00 0.00
> /dev/sda3 127824.07 37.04 14118.52 77.78 1135540.74 918.52 567770.37
>
> 459.26 80.05 1914.81 13.48 1.30 1851.85
> /dev/sda5 27.78 12.96 18.52 9.26 370.37 177.78 185.19 88.89
> 19.73 2.96 10.67 8.00 22.22
> /dev/sda6 0.00 7698.15 207.41 792.59 1659.26 67911.11 829.63
> 33955.56 69.57 48.70 4.89 4.00 400.00
>
> Can this be a redhat bug?
>
> Kind Regards,
> tolga
>
>
>
> --
> redhat-list mailing list
> unsubscribe mailto:redhat-list-request at redhat.com?subject=unsubscribe
> https://www.redhat.com/mailman/listinfo/redhat-list--
redhat-list mailing list
unsubscribe mailto:redhat-list-request at redhat.com?subject=subscribe
https://www.redhat.com/mailman/listinfo/redhat-list
More information about the redhat-list
mailing list