Hello Greg,

Am 07.12.2023 um 18:13 schrieb Greg Wilburn <gwilburn@xxxxxxxxxxxxxxxxxxxxxxx>:

When this degredation occurs, WRKSYSACT sorted by I/O shows SMPOL001 at the top with 20K Non-DB Write over about 15 minutes.

Found this when searching for SMPOL001:

https://archive.midrange.com/midrange-l/200110/msg00105.html

The coincidence of your observed behavior happening after the upgrade is a mystery, because the applications should behave as before.

If we can't nail this down, our alternative is a relatively pricey upgrade that involves a new box and jumping up a processor group.

I'm not yet sure if this would help.

It might be interesting to find out what triggers this sudden massive writeback. Apparently, a lot of changed data has accumulated in RAM. Why this isn't written back steadily in the background I don't know. I think, this has happened with the earlier release (possibly needing less RAM for itself) and so you didn't notice.

Maybe Richard Theis' hint is towards the right direction? Accumulated dirty pages reach a certain threshold count and are then written back with higher priority, in turn affecting everything else. More RAM *could* help. Or closely review your pool definitions. Or both. :-)

Just thinking out loud here…

:wq! PoC




As an Amazon Associate we earn from qualifying purchases.

This thread ...

Replies:

Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.