| Blogs | Classifieds | Downloads | FlashChat | Gallery | Googlemap | Invite Friends | Links | Projects | Reviews | Wiki |
| |||||||||
Welcome to the pSeries Tech Forums,
our free peer-based support site for administrators, engineers and architects working with IBM pSeries servers and software. You are currently viewing our site as a guest which gives you limited access to view most discussions, articles, tutorials and access our other free features. By joining our community you will be able to collaborate with administrators, engineers and architects charged with designing, delivering or maintaining IBM pSeries server environments. Founded by a recognized IBM pSeries consultant and IBM Redbook author, pSeries Tech Forums was developed with the single mission of bringing IBM pSeries professionals together into a single self-help community. Registration is fast, simple and absolutely free to all IT professionals with responsibility for or interest in IBM pSeries servers. We invite you to join our community today! If you have any problems with the registration process or your account login, please contact contact support. |
| Our Sponsors | |
| | |
| Want to advertise? | |
![]() |
| | LinkBack | Thread Tools |
|
#1
| ||||
| ||||
I need help on a possible performance problem. We have a p560 running AIX v5.3 8 cpu/32gb mem with 2 fiber cards that is running Oracle 10g. Disk I/O is heavy during certain times but from iostat and vmstat output, I don't think there is alot we could do to help performance with such heavy I/O occurring. Not seeing any paging to page space but seeing heavy paging to file system (via nmon). Attached is a vmstat of what we typical see. Thanks, Danny Last edited by DANNYC; June 6th, 2008 at 09:39. |
|
#2
| ||||
| ||||
Except for the I/O waits everything looks pretty normal. The I/O waits are not necessarily cause by disk I/O, they could be Network I/O or waiting for another process to complete. How are your disks set up in this environment? Direct attached Fibre, Local SCSI, Virtual I/O? How much CPU and how many virtual CPUs do you have? What are your vmo settings, as that may shed some light on what it is doing?
__________________ Ross Mather, IBM AIX IT Specialist. That said anything I say here is my own opinion and not anything that you can ever hold against IBM. Ohhh and don't forget that I make mistakes too.... |
|
#3
| ||||
| ||||
Thanks for the reply Ross. We are attached to ds6800 disk via our SAN. The is an 8cpu server with SMT turned on so 16 logical processors. These vmo setttings are the only ones I changed: MINPERM%=3 MAXPERM%=90 MAXCLIENT%=90 lru_file_repage=0 AIO is also turned on. |
|
#4
| ||||
| ||||
what you'll need to do is to find out which files are being written and see if you can split them off into different SAN LUNs that is probably the only thing you'll be able to do to help. That sort of analysis is not something I can help you with online. You'll need to use filemon to work out what is going on.
__________________ Ross Mather, IBM AIX IT Specialist. That said anything I say here is my own opinion and not anything that you can ever hold against IBM. Ohhh and don't forget that I make mistakes too.... |
|
#8
| ||||
| ||||
You are correct though that most I/O problems like this with Oracle are caused by the programming at an Oracle level rather than anything else. But it never hurts to have back up when talking to your DBAs :-).....
__________________ Ross Mather, IBM AIX IT Specialist. That said anything I say here is my own opinion and not anything that you can ever hold against IBM. Ohhh and don't forget that I make mistakes too.... |
![]() |
| Bookmarks |
| Tags |
| i or o, problem |
| Currently Active Users Viewing This Thread: 1 (0 members and 1 guests) | |
| Thread Tools | |
| |