Re: Dirty LRU exceeding the LRU_MAX of 2%
Posted in 1999
Topics: Server Administration, Logging & Checkpoints, Platform-Specific Issues, Versions, Editions & End-of-Life
Hi
>Andrew Lawrenson wrote:
>Kernoal.Stephens@AUTOZONE.COM wrote in message
><80csie$ad9$1@news.xmission.com>...
>>
>>
>>
>>
>>Here is what I am seeing. In onstat -R the dirty q's are over 2% dirty.
>>onstat -F shows all the flushers as Idle.>>
>>I know I have seen this in the post but cannot find it in search.
>>
>>Attached.
>>onstat -R output
<onstat -F output>onconfig output
>IDS 7.30.UC6
>AIX 4.3.2
>4CPU
>512MB
>
<snip>
>There's a bug in certain versions of online that may be affecting you -
>Defect 115741, whereby the wakeup code for the page cleaners doesn't work
>ad the dirty queues grow beyond LRU_MAX_DIRTY. It certainly affected me
in
>te NT ver 7.30 (the bug does also affect unix) - we had checkpoints of up
>to 2 minutes, where they should have been 1-2 seconds. Upgrading to 7.31
>fixed it for me.
>
>
> Andrew Lawrenson
I am running
IDS 7.31.UC3
AIX 4.3.2
4CPU
1GB
and I see the same picture on my AIX-box.
So I doubt that it is fixed in 7.31 version.
I know that I have KAIO turned on. On AIX it is turned on default when your
root_dbs is created
on a raw-device.
Bjarne Wilken Jensen
Alm. Brand
Denmark
In article <80h7ee$jnf$1@news.xmission.com>, bjarne.wilken.jensen@almbra
nd.dk writes
>
>Hi
>>Andrew Lawrenson wrote:
>>Kernoal.Stephens@AUTOZONE.COM wrote in message
>><80csie$ad9$1@news.xmission.com>...
>>>
>>>
>>>
>>>
>>>Here is what I am seeing. In onstat -R the dirty q's are over 2% dirty.
>>>onstat -F shows all the flushers as Idle.>>>
>>>I know I have seen this in the post but cannot find it in search.
>>>
>>>Attached.
>>>onstat -R output
><onstat -F output>>onconfig output
>>IDS 7.30.UC6
>>AIX 4.3.2
>>4CPU
>>512MB
>>
><snip>
>>There's a bug in certain versions of online that may be affecting you -
>>Defect 115741, whereby the wakeup code for the page cleaners doesn't work
>>ad the dirty queues grow beyond LRU_MAX_DIRTY. It certainly affected me
>in
>>te NT ver 7.30 (the bug does also affect unix) - we had checkpoints of up
>>to 2 minutes, where they should have been 1-2 seconds. Upgrading to 7.31
>>fixed it for me.
>>
>>
>> Andrew Lawrenson
>
>I am running
>IDS 7.31.UC3
>AIX 4.3.2
>4CPU
>1GB
>
Fixed in 7.31.UC4-1
>and I see the same picture on my AIX-box.
>So I doubt that it is fixed in 7.31 version.
>I know that I have KAIO turned on. On AIX it is turned on default when your
>root_dbs is created
>on a raw-device.
>
>
>Bjarne Wilken Jensen
>Alm. Brand
>Denmark
>
>
>
>
>
--
David Williams