our read-write instance is showing the following for onstat -g ioq (at bottom, excluded the gdf )

This article states that
"If you are using kaio monitor the kio queues. The maxlen values should not exceed 32. There will be one kio queue for each cpu virtual processor."

https://www.ibm.com/support/pages/where-do-i-start-diagnosis-generally-slow-performance-informix-servers

most of ours show 64 and it was captured this morning, we zero out stats nightly.

however the article does not offer any possible action items to help resolve this - Does anyone know what actions to take?

this is all stemming from high cpu usage on the db server at intermittent times. The only association is see is a particular sql that executes very quickly (.03 seconds) when i run it manually in server studio but server studio reports execution times up
to 20 seconds in duration and it usually coincides with increased cpu usage

Thanks
----------------------------------------------------





IBM Informix Dynamic Server Version 12.10.FC7 -- On-Line (Prim) -- Up 230 days 01:40:40 -- 13162768 Kbytes

AIO I/O queues:
q name/id len maxlen totalops dskread dskwrite dskcopy
fifo 0 0 0 0 0 0 0
drda_dbg 0 0 0 0 0 0 0
sqli_dbg 0 0 0 0 0 0 0
kio 0 0 64 23687530 23077181 610349 0
kio 1 0 64 29450304 28727714 722590 0
kio 2 0 64 16097247 15724399 372848 0
kio 3 0 64 287294 258479 28815 0
kio 4 0 64 1457799 1379189 78610 0
kio 5 0 64 3298546 3174058 124488 0
kio 6 0 64 2091801 1991715 100086 0
kio 7 0 64 5979232 5781239 197993 0
kio 8 0 64 1179511 1113737 65774 0
kio 9 0 33 667600 629247 38353 0
kio 10 0 64 154345 136763 17582 0
kio 11 0 38 215096 199771 15325 0
kio 12 0 64 911988 863421 48567 0
kio 13 0 64 160180 144185 15995 0
kio 14 0 64 504850 471138 33712 0
kio 15 0 64 394734 364759 29975 0
adt 0 0 0 0 0 0 0
msc 0 0 2 1190 0 0 0
aio 0 0 2 1207 595 0 0
pio 0 0 0 0 0 0 0
lio 0 0 0 0 0 0 0

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)