Link to home
Start Free TrialLog in
Avatar of bahard
bahardFlag for Türkiye

asked on

IO tuning for AIX running oracle ASM

Hello,

Changing pbuf values (like pv_min_pbuf) has an IO performance change on ASM disks?

Thanks.
Avatar of woolmilkporc
woolmilkporc
Flag of Germany image

No, it hasn't.

pv_min_pbuf is for LVM controlled hdisks (i.e. accessed via logical volumes) and not for raw disks as used by ASM.

wmp
ASM uses LVM raw volumes
LVM parameters apply, but since pbufs are auto-tuned by system no care needed there.
More gold is hidden around AIO tunables.
Avatar of bahard

ASKER

Hello gheist&wmp,

I had known that pv_min_buf does not have a control over ASM disks until I attended a powercare session by IBM and in this training session, the IBM expert said that actually it does. But I have no documentation of it so I am really in doubt about that.

What do you mean by "LVM raw volumes"? When defining ASM disks, we only use disks major and minor number, which means that it is only hdisk-related and there should be no relation with LVM.

And also, this is the first time that I see auto-tune parameters for IBM. If so, could you please explain why I see a regular increase in "blocked_io_count" in "lvmo -a" output. Is there a way to eable auto?

Kind Regards.
I do not know why oe would use PVs, as LVM adds ability to migrate data away from broken hardware while app keeps working....
ASKER CERTIFIED SOLUTION
Avatar of woolmilkporc
woolmilkporc
Flag of Germany image

Link to home
membership
This solution is only available to members.
To access this solution, you must be a member of Experts Exchange.
Start Free Trial
oracle uses AIO to queue requests to storage. if AIO queue is smaller than all pbufs, then obviously they go underutilized... (which is usually the case)