Today’s virtualized datacenters consist of several servers connected to shared storage, and this configuration has been necessary to enable the flexibility that virtualization provides and still allow for high performance. However, the power consumption of this setup is a major concern because shared storage can consume as much as 2-3x the power of a single, mid-ranged server. In this blog, we look at the performance impact of replacing shared storage with local disks and PCIe flash storage in a vSphere 5.5 datacenter to save power.
We leverage two innovative vSphere features in this performance test:
- Unified live migration, first introduced with vSphere 5.1, removes the shared storage requirement for vMotion and allows combining traditional vMotion and Storage vMotion into one operation. This combined live migration copies both the virtual machine’s memory and storageover the network to the destination vSphere host. This feature offers administrators significantly more simplicity and flexibility in managing and moving virtual machines across their virtual infrastructures compared to the traditional vMotion and Storage vMotion migration solutions. More information about vMotion can be found in the VMware vSphere 5.1 vMotion Architecture, Performance, and Best Practices white paper.
- vSphere 5.5 improves server power management by enabling processor C-states, in addition to the previously-used P-states, to improve power savings in the Balanced policy setting. More information about these improvements can be found in the Host Power Management in vSphere 5.5 white paper.
We measure the performance and power savings of these features when replacing shared storage with local disks and PCIe flash storage using a modified version of VMware VMmark 2.5. VMmark is a multi-host virtualization benchmark that uses varied application workloads, as well as common datacenter operations to model the demands of the datacenter. Each VMmark tile contains a set of VMs running diverse application workloads as a unit of load. For more details, see the VMmark 2.5 overview. The benchmark was modified to replace the traditional vMotion workload component with the new shared-nothing, unified live migration.
VMmark 2.5 was modified to convert the vMotion workload into a migration without shared storage. All other workloads were unchanged. This allowed a comparison of local, direct attached storage to a traditional Fibre Channel SAN. We measured the power consumption of each configuration using a pair of Yokogawa WT210 power meters, one attached to the servers and the other attached to the external storage.
- Systems Under Test: 2x Dell PowerEdge R710 servers
- CPUs (per server): 2x Intel Xeon X5670 @ 2.93 GHz
- Memory (per server): 96 GiB
- Hypervisor: VMware vSphere 5.5
- Local Storage (per server): 1x 785GB Fusion-io ioDrive2, 2x 300GB 10K RPM SAS drives in RAID 0
- SAN: 8Gb Fibre Channel, 30x 200GB SATA Flash drives, 30x 600GB 15K RPM SAS drives
- Benchmarking software: VMware VMmark 2.5
All I/O-intensive virtual disks were stored on the Fusion-io devices for local storage tests or the SATA flash drives for the SAN tests. This included the DVD Store database files, the mail server database, and the Olio database. All remaining virtual machine data was stored on the local SAS drives for the local storage tests and the SAN SAS drives for the SAN tests.
VMmark performance using shared-nothing, unified live migration backed by fast local storage showed only minor differences compared to the results with shared storage. The largest variance was seen in the infrastructure operations, which was expected as the vMotion workload was modified to include a storage migration. The chart below shows the scores normalized to the 3-tile SAN test results.
When we add the power data to these results, and compare the Performance Per Killowatt (PPKW), we see a much different picture. The local storage-based PPKW score is much higher than shared storage due to higher power efficiency.
We can see the reason for this difference is due to the power consumption of each configuration. The SAN is consuming over 1000 watts, which is typical of this storage solution. Replacing that power-hungry component with local storage greatly reduces vSphere datacenter power consumption while maintaining good performance.
This SAN should be able to support approximately 25 VMmark tiles (based on the storage capacity of the SSDs), roughly five times the load being supported by the two servers we had available for testing in our lab. However, it should be noted that these servers are two generations old. Current-generation two-socket servers with a comparable power usage can support 2-3x the number of tiles based on published VMmark results. This would imply that the SAN could support at most four current-generation servers. While an additional two servers will further amortize the power cost of the SAN, significant power savings would still be achieved with an all-local storage architecture.
This is not without a cost. Removing shared storage reduces the functionality of the datacenter because there are a number of vSphere features which will no longer function, such as DRS and traditional vMotion. The reduction in the infrastructure performance due to no shared storage will limit the workloads that can be run in this manner to virtual machines with smaller disks which can be moved between hosts without shared storage fairly quickly. Virtual machines with large disks would take much longer to move and would be better suited to a shared storage environment.
We have shown that it is possible to significantly reduce datacenter power consumption without significantly reducing performance by replacing shared storage with local storage solutions. Unified live migration enables the use of local storage without a significant infrastructure performance penalty while maintaining application performance comparable to traditional environments using shared storage for the server workloads represented in VMmark. The resulting elimination of shared storage creates significant power savings and lower operations costs.