-
Recovery Write
-
Unmap
-
Recovery Unmap
For each, it provides the IOPS, bandwidth, average latency (ms) and standard deviation latency (ms). Take note that some use MB, while others use GB.
| ROLE | The Distributed Object Manager (DOM) role of that component, such as client, owner, and component manager. |
READS/s MBREAD/s AVGLAT SDLAT | Reads/second is the number of reads operations. This is IOPS. MBReads/s is read throughput in Megabytes/second. AvgLat is the average latency. Standard deviation of latency, when above 10ms latency. |
WRITES/s MBWRITE/s AVGLAT SDLAT | Same set of metrics, like above, but for write |
RECOWR/s MBRECOWR/s AVGLAT SDLAT | Same set of metrics, like above, but for Recovery Write. Recovery covers component rebuild task (e.g. from disk failure). Read the string MBRECOWR as MB Reco Wr. |
UNMAPS/s GBUNMAP/s AVGLAT SDLAT | Same set of metrics, like above, but for unmap operations. I think this number should be within your expectation, as excessive unmap can impact performance. GBUNMAP/s = Unmapped rates in Gigabytes/second Read the string GBUNMAP as GB Unmap |
RECOUN/s GBRECOUN/s AVGLAT SDLAT | Same set of metrics, but for Recovery Unmap operations. Read the string GBRECOUN as GB Reco Un. RecoUn/s is the number of recovery unmapped operations per second. GBRecoUn/s is the amount of disk space in GB/second by Recovery Unmapped. |
Network
Take note that the network panels mix the virtual and physical networks.
Focus on the virtual network first as that’s closer to the VM and kernel.