Re: raid 5 disaster
- From: "Michael McMullen" <ganstadba@xxxxxxxxxxx>
- To: <oracle-l@xxxxxxxxxxxxx>
- Date: Mon, 16 Aug 2004 08:46:48 -0400
Who hijacked my thread? :-)
Anyways, on my original thread. I always new i/o was the culprit. Here's a
snippet from stats back for 3 minutes when i/o waits were 75%.
Top 5 Timed Events
~~~~~~~~~~~~~~~~~~ %
Total
Event Waits Time (s) Ela
Time
-------------------------------------------- ------------ ----------- ------
--
enqueue 151 446
29.67
db file sequential read 77,094 350
23.33
CPU time 319
21.22
rdbms ipc reply 111 214
14.26
local write wait 114 115
7.63
-------------------------------------------------------------
The box was a dog right from the beginning. We can only use raid 5.
Mandated right from the top. Management refused to do anything but raid 5 on
another server that was i/o bound. So quick i/o and a t3 at raid 0 for
reports did the trick there. That must have cost close over 50K. Always
money for new things but not to change things.
Anyways I just added to Cary's bank account the other day so the next time
they ask me again why the box is so slow I'll do the Cary thing and nail
them with that.
Now back to pros and cons of documentation.
Mike
----------------------------------------------------------------
Please see the official ORACLE-L FAQ: http://www.orafaq.com
----------------------------------------------------------------
To unsubscribe send email to: oracle-l-request@xxxxxxxxxxxxx
put 'unsubscribe' in the subject line.
--
Archives are at //www.freelists.org/archives/oracle-l/
FAQ is at //www.freelists.org/help/fom-serve/cache/1.html
-----------------------------------------------------------------
Other related posts:
