August 25, 2005 at 12:48 pm
Hello!
I have collected counters using perfmon from our Production SQL Server. I have noticed that %Disk Time counter averaging 111 with maximum value being 2249 for particular drive. I was wondering how I detect whether this value indicates a bottleneck. Drive in question is RAID 10. Is there conversion formula I should use?
I know that value over 60 indicates a potential problem. Average Disk Queue lenght is 1 which means to me that disk is OK. I am confused by high %Disk Time value.
Any advice is appreciated,
Igor
August 26, 2005 at 12:36 am
Find out which one of %Disk Write Time or %Disk Read Time is higher? This will indicate the type of operation that keeps spinning your disks.
How are any applications accessing your database?
Also is this happening at a specific time, or time span. You should then look at the list of processes during that time span with SP_WHO or SP_WHO2 and find the ones with the highest IO. These queries might be your culprits.
Also look at the paging factor. It could be that your cache is too small and SQL is constantly paging for information. This could also lead to a lack of memory condition. Can you past the result of your dbcc memorystatus during these bottleneck periods?
You have enough to get started. I will be looking forward to your updates.
crasc
August 26, 2005 at 3:12 am
Hi,
Take a look at these pages. It seems that this will answer your question. You're looking at numbers that don't seem to be measured reliable!
JP
http://www.oreillynet.com/pub/a/network/2002/01/18/diskperf.html
http://searchstorage.techtarget.com/tip/1,289483,sid5_gci852081,00.html
August 26, 2005 at 4:44 pm
Thanks a lot ! I does answer my question.
Igor
Viewing 4 posts - 1 through 3 (of 3 total)
You must be logged in to reply to this topic. Login to reply