July 30, 201411 yr I'm seeing the following in the Events for a couple of my SSD's: Device t10.ATA_____INTEL_SSDXXXXXXX__ _____________________ performance has deteriorated. I/O latency increased from average value of 5514 microseconds to 119963 microseconds. warning Device t10.ATA_____Samsung_SSD_840_Series_ _________________S19XXXXXX_____ performance has deteriorated. I/O latency increased from average value of 16504 microseconds to 443068 microseconds. warning The Samsung is an RDM disk that I'm passing into a VM and the Intel a local datastore. I did a quick dd on the Samsung from within the VM and speeds are slow ~60-80MB/s. Could this be something to do with garbage collection? I'm not whether TRIM it's supported in ESXi or not. I believe the Samsung has native TRIM support but not the Intel. Should I be concerned?
July 30, 201411 yr I've heard reports of spinrite run at level 2 fixing this kind of issue. It's $89, but a worthwhile tool IMHO.
Archived
This topic is now archived and is closed to further replies.