- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
VM disk Read/Write latency is more then 300ms
Hi,
I am facing latency issue in Particular VM in ESXi 6.0. The VM has Windows server 2012R2 OS. It contains AD user profiles and network share files.
Am facing issue only office working hours. While checking Performance Chart I found Disk read and write latency going more than 300ms.
Anyone tell me what is the normal disk latency? and any idea about this.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The normal disk latency depends on the workload.
Values that widely being used:
Good: < 10ms
Okay: 10 – 20ms
Anything over 20ms can be considered troublesome.
Some recommendations:
Use Storage VMotion to migrate I/O-intensive virtual machines across multiple hosts.
Check swap statistics in the guest operating system to verify that virtual machines have adequate memory. Increase the guest memory if needed.
Use the most current hypervisor software.
Blog: https://rickverstegen84.wordpress.com/
Twitter: https://twitter.com/verstegenrick
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks, RickVerstegen
I have tried >Use Storage VMotion to migrate I/O-intensive virtual machines across multiple hosts.
Also, I have checked at the time of issue there is no huge memory utilization.
Check swap statistics in the guest operating system to verify that virtual machines have adequate memory. Increase the guest memory if needed.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Sample Image for your reference.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Sample2 Image for your reference,
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Can you provide details about the back-end storage and network that is being used?
Blog: https://rickverstegen84.wordpress.com/
Twitter: https://twitter.com/verstegenrick
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I have created a separate virtual switch for this VM and directly allocated a physical NIC to that VM. We are using IBM ds3512 ISCSI Storage.
Physical NIC :-
VM NIC:-
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I had that problem on some HPE DL360 G6's because their old BBWC batteries were finished and disabled the smart array acceleration.
I saw the errors by selecting the Host, Monitor, Events, and got a lot of:
"Device naa.... performance has deteriorated. I/O latency increased from average value of ..."
After they were repaired with home-made cells, a few hours later they were charged up, and everything was as fast as expected.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
ESXTOP can help you identify where the problem is occurring. https://kb.vmware.com/s/article/1008205 I've used this many times to help see where the problem is occurring. VM, Host, Storage. I hope this helps.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I would recommend to look at ESXTOP first to identify where the issue is occuring:
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content