Identifying Disk Performance Bottlenecks
I've been noticed that the concentrator service on our endpoint log hybrid falls behind at roughly the same time each day, the Endpoint log hybrid is a virtual machine which is running on Fibre Attached SAN storage.
our IT Ops tell me that they can't see anything wrong at the Hypervisor or SAN level.
What mechanisms can I use at the Linux layer to collect and analyse data to determine if the system is experiencing bottlenecks due to resource contention of disk subsystems, etc.
Jeremy, are you using the new health and wellness dashboards? These are exceptional at viewing all the statistics around any service. It also provides historical data as well as trending. This should make it easier to see what the concentrator is doing over time. Have you reached out to support for their assistance?
I have looked at the new health and wellness but it doesn't really answer the question I'm trying to, plus I don't think they're properly working.
I have reached out to support but the process is slow and very asynchronous and I have to wait until support are almost out of my timezone.