From: Browett, Darren (dbrowett@coquitlam.ca)
Date: Mon Nov 10 2003 - 14:54:38 EST
Hi managers,
I am having performance issues with my DS20E/DS20 5.1b Cluster.
Starting today, I have collect
running on both nodes, and will collect information for the next couple
of days.
I am sure I can generate all kinds of fancy reports, but I am not sure
what those reports will be telling me.
Where can I look for any kind of metrics to assist me in finding
problems. ?
For instance I ran collect the other day using the following syntax
collect -sd 1 5, and only one set of disks showed any activity, the ones
where I have oracle RAC installed.
There are 6 disks, each is 72Gb/10K, using RAID 5 on a MA8000 enclosure
controlled by an HSG80.
It reported back that it was 25 %busy, 108 r/s and 11481 rkb/s 17 w/s
and 125 wkb/s.
Is that good ???? I have no idea. Should the r/s be 208 or higher ?.
Another "peformance" problem was with ps. If I use ps -ef | grep pmon
on member 1, it litterly pauses
after each line (approx 10 of them). Again not sure where to start to
look for this problem.
Any pointers would be greatly appreciated.
Thank you in advance
Darren
------------------------------------------------------------------------
--------------------------------------------------
Darren Browett P.Eng This
message was transmitted
Data Administrator using
100% recycled electrons
Information and Communication Technology
City of Coquitlam
P:(604)927 - 3614
E:dbrowett@coquitlam.ca
------------------------------------------------------------------------
---------------------------------------------------
This archive was generated by hypermail 2.1.7 : Sat Apr 12 2008 - 10:49:43 EDT