Hi,
We were facing some performance issues in the server since 1 week. While analyzing, had a doubt that it may be due to DiskIO. So, have created User-Defined Performance Monitor and added parameters such as IO Other Bytes/Sec, IO Data Bytes/sec, Avg. Disk Sec/Read, Avg. Disk Sec/Write, Avg.Disk Queue Length.
Now, when I see the Performance Monitor which has run for 18 hrs, I have some questions for which I am not able to find clear answers.
- For each counter, the scale is different.
Example: For IO Other Bytes/Sec it is 0.000001, for Avg. Disk Sec/Read it is 100 and for Avg.Disk Queue Length it is 0.1
Why the scale values are different. How to interpret the exact values in graph with these scale values
- For Avg.Disk Queue Length:
Scale = 0.1; Avg Value = 47.3; Minimum = 0; Maximum = 1511.6.
How to interpret these values
- In one of the blogs it has been indicated that for Avg.Disk Queue Length "if the average is greater than 2 per spindle, it's a cause for concern"
Reference: http://blogs.msdn.com/b/sqljourney/archive/2013/06/04/how-to-troubleshooting-sql-server-i-o-bottlenecks.aspx
Is it possible to determine the number of spindles in server. Or do we have to ask it to Hard-Ware IT guys.
If I get answers to the above clarifications, it would be very much helpful.
Thanks in advance
Raksha