GitHub user nickaccuweb added a comment to the discussion: High Latency Between 
Two VMs In a L2 Private Guest Network

@fnavidan 

Are you still experiencing high latency between the 2 VMs in the L2 Network?

If yes, I would suggest checking a few things:

1. Run an iperf3 test between the VMs to check the actual network throughput.
2. Confirm that all VM NICs are using VirtIO.
3. Check CPU usage and network bridge configuration on the KVM host.
4. Since your VMs are using the same NFS primary storage, check for storage I/O 
latency or contention.
5. Check GlusterFS performance using gluster volume profile to identify any 
storage bottlenecks.

Also, are all three GlusterFS VMs running on the same physical KVM host, or are 
they distributed across multiple KVM hosts?

The difference between 350–400 MB/s local writes and 30 MB/s GlusterFS writes 
is quite high. However, GlusterFS replication adds additional network and 
storage operations, so we should first check whether the bottleneck is on the 
network or storage side.

You can also refer to the official GlusterFS documentation:

- https://docs.gluster.org/en/latest/Administrator-Guide/Performance-Testing
- https://docs.gluster.org/en/latest/Administrator-Guide/Performance-Tuning

Please share the iperf3 results and confirm the KVM host placement. This will 
help us narrow down the issue.

Regards,
Nick R 
AccuWeb.Cloud 

GitHub link: 
https://github.com/apache/cloudstack/discussions/14380#discussioncomment-18973213

----
This is an automatically sent email for [email protected].
To unsubscribe, please send an email to: [email protected]

Reply via email to