Storage Boards Cleanup
To make it easier to find information about HPE Storage products and solutions, we are doing spring cleaning. This includes consolidation of some older boards, and a simpler structure that more accurately reflects how people use HPE Storage.
Disk Arrays
cancel
Showing results for 
Search instead for 
Did you mean: 

va7410 optimum queue depth for luns

SOLVED
Go to solution
Charles McCary
Valued Contributor

va7410 optimum queue depth for luns

Group,

I have a va7410 with 67 luns ranging in size from 10gb to 100gb.

This array is connected to a hard partitioned rp7420 (effectively two systems).

All disks are at the default queue depth for HPUX 11.11, is there some way to figure if I need to change the scsi queue depth and if so to what?

I know this relates to the number of luns, number of host ports (in this case 4), etc...but I'm not sure about the calculation or if I need to apply whatever I come up with to all disks.

Further info, running several different databases on the two systems (oracle).

thanks,

c
2 REPLIES
skris
Trusted Contributor
Solution

Re: va7410 optimum queue depth for luns

Hi Charles,
Normally the QFT is set to 750.If you have been seeing QFull messages then you could consider altering them:

Here is a formula that yields Best results:

2 or 3*(#disks in RG)/(#ports in RG)

PS: There isn't a mandatory rule as such.

For HP-UX, you need to have PHKL_29047 to avoid host performance issues when the host gets the Queue Full message from the array.

Cheers!
Shiva
Charles McCary
Valued Contributor

Re: va7410 optimum queue depth for luns

We're not getting any errors, but I'm just concerned that I'm not getting the best perf out of the array.