I’ve recently made an all flash cluster vSAN with the following components:
- HPE Apollo r2600 Gen 9 with 3x xl170r Gen 9, each configured with:
- 2x Xeon E5-2680 v3 @ 2.50GHz
- 256GB of RAM
- 2x 1Gbps embedded NIC
- 2x HP 533FLR-T Dual Port – 10GbE RJ45 FlexibleLOM (one of them used for vSAN traffic)
- HPE P440 4GB Smart Controller (Firmware version 7.0, driver 2.0.44, HBA mode enabled)
- 6x SAMSUNG SSD SATA Drives
- NETGEAR XS728T
I’ve created 4 vLans on the switch:
Esxi version is 6.7 U3 HPE Branded, and I’ve run the SSP from HP 2020.3, so latest drivers are in use.
“Skyline healt” is all green, and everything seems perfect, but, despite the read performance that are perfect, I notice a huge write lantency that affect any kind of operation.
Attached you can find the output of healt check on the first node.
Any help would be greatly appreciated.