EMC VxRack Node powered by ScaleIO: Synthetic Performance Review (2-layer)
We’ve been working with the all-flash performance #EMC #VxRack Nodes for some time now, previously looking at the system configured in two-layer in our SQL Server, #MySQL and #VMmark application benchmarks. In this last segment of two-layer testing before turning to HCI, we put the storage to work in HCIbench to gather synthetic performance numbers.
#VCE VxRack Node (Performance Compute All Flash PF100) Specifications
Chassis – # of Node: 2U-4 nodeProcessors Per Node: Dual #Intel E5-2680 V3, 12c, 2.5GHzChipset: Intel 610DDR4 Memory Per Node: 512GB (16 x 32GB)Embedded NIC Per Node: Dual 1-Gbps Ethernet ports + 1 10/100 management portRAID Controller Per Node: 1x LSI 3008SSDs Per Node: 4.8TB (6x 2.5-inch 800GB eMLC)SATADOM Per Node: 32GB SLC10GbE Port Per Node: 4x 10Gbps ports SFP+Power Supply: Dual 1600W platinum PSU AC
Dell PowerEdge LoadGen Specifications
Dell PowerEdge R730 Servers (x4)CPUs: Eight Intel Xeon E5-2690 v3 2.6GHz (12C/28T)Memory: 64x 16GB DDR4 RDIMMNetworking: 4x Emulex dual-port 10G NIC
HCIbench Test Configuration
16 VMs10 VMDK per VM40GB VMDK (6.4TB footprint)Full-write storage initialization1.5 hour test intervals (30 minute preconditioning, 60 minute test sample period)
For testing the two-layer ScaleIO storage cluster we deployed one heavy-weight configuration for our workload profiles. This consisted of a 6.4TB data footprint out of 8TB usable.