[Okta Webinar] Learn how to a build a cloud-first strategyRegister Now

x
  • Status: Solved
  • Priority: Medium
  • Security: Public
  • Views: 352
  • Last Modified:

Average Disk time % high

Hi,

We have a server that is displaying high % disk time, often through out a day application that are server based become slow and unresponsive.  We have pretty mush narrowed this down to a disk bottleneck that kicks in when Trend micro updates.  However we have this on much older servers and dont have any problems.

Can anyone recommend any tools that can tell me what applications are causing the disk usage so that we can make sure nothing unusual is accessing the disks.  The cpu usage is prety steady.

Thanks

Lee
0
leehewson
Asked:
leehewson
  • 4
  • 3
1 Solution
 
NikCommented:
If you narrowed it down, you can try to disable Trend Micro and see if you've still experience issues.
The best way to check for disk bottleneck issues is to use Microsoft Performance monitor.

Here are two useful links, which can help you:
http://www.computerperformance.co.uk/HealthCheck/Disk_Health.htm
http://articles.techrepublic.com.com/5100-22_11-5298961.html
0
 
leehewsonAuthor Commented:
The trend services run every hour and send the disk queue high and % time. However in between time the disk utilization is a minimum of 20%. On a 10 user windows 2003 server. Would like to find out what applications are putting a Load in the disk.  Any ideas on inboard sata storage controller for a ml310 g5 settings or fault diagnosis would be a help
0
 
leehewsonAuthor Commented:
Hi all. Have done a passmark test on the disks. Get 55 MBs sequential read speed and only 1.77 mbs sequential write speed. Writing is faster on my IDE laptop. Any ideas
0
Concerto Cloud for Software Providers & ISVs

Can Concerto Cloud Services help you focus on evolving your application offerings, while delivering the best cloud experience to your customers? From DevOps to revenue models and customer support, the answer is yes!

Learn how Concerto can help you.

 
lnkevinCommented:
- What is the server HW brand and model?
- Is there a HW RAID on this server? What RAID is currently setting?
- Did you look at the physical server or check its management software tool to ensure there is no fail HD (if RAID is set)? If the hard drive is failed in RAID you will see the performance degraded.

K
0
 
leehewsonAuthor Commented:
Hi Kevin,

The server is an ML310 Proliant with an onboard SATA RAID, currenlty set to raid one.  None of the drives are degraded

Just seems to be extremely slow writing to the HD which slows the overall performance down.  We have a fix to try after xmas which is to enable write cache in the raid bios.  Any other ideas would be welcome.

Thanks

Lee
0
 
lnkevinCommented:
None of the drives are degraded....

I assume you check your array status in Proliant Support Pack. Can you run array diagnostic and post the text file here?

Enable write cache on the controller will give you some performance boost. However, you just want to make sure the server power is redundant and on battery (UPS). If the power is cut off during the write back occurred, your data is at risk.

K
0
 
lnkevinCommented:
Other thing you can do that significantly helpful is update your firmware. Download and update your firmware may solve your problem as well. If not, it's good to keep it up to date:

http://h20000.www2.hp.com/bizsupport/TechSupport/SoftwareDescription.jsp?lang=en&cc=us&prodTypeId=15351&prodSeriesId=428936&prodNameId=3288114&swEnvOID=1005&swLang=8&mode=2&taskId=135&swItem=MTX-124beffbed3842cea0b9b3f962

K
0
 
leehewsonAuthor Commented:
Carried out suggestion and found that speed of the disk access improved. Many thanks.
0

Featured Post

Get quick recovery of individual SharePoint items

Free tool – Veeam Explorer for Microsoft SharePoint, enables fast, easy restores of SharePoint sites, documents, libraries and lists — all with no agents to manage and no additional licenses to buy.

  • 4
  • 3
Tackle projects and never again get stuck behind a technical roadblock.
Join Now