How can I optimize the disk subsystem for performance with Windows Server 2012 R2?
Local disk access can seriously impede Windows Server 2012 R2 and workload performance. Apply these strategies to improve the situation.
One of the biggest limitations to disk performance is read/write concurrency. A single disk can offer tremendous storage capacity, but read/write latencies of a single disk target can add up and cause noticeable delays. The best way to offset disk latencies is to use the concurrency of multiple simultaneous spindles found in a disk group such as RAID 0 (disk striping). With disk striping, data is spread across multiple disks, which seek their portion of a file simultaneously. Ideally, a RAID 1+0 disk configuration provides the redundancy of disk mirroring (RAID 1), plus the performance of RAID 0. If there are not enough physical disks to adequately support RAID 1+0, adopt RAID 5.
Disk caching can improve read performance, but it isn't always used for writing. System failures can cause data loss if a write cache isn't completely backed up with battery power; this usually involves an expensive write cache module or upgrade to the server. Read cache contents also can be lost, but there is no data loss because you can restore read cache contents from disk as the data is reread. If you're not using write caching, add write cache capability for write-intensive workloads.
New hardware is beneficial for new operating systems like Windows Server 2012 R2, but simply investing in a new server is no guarantee of improved performance. It's important to gather objective benchmarks of performance before deploying new hardware and then again after implementing hardware or configuration changes. Even basic tools like Performance Monitor (Perfmon) will suffice. Comparing benchmark results will offer valuable guidance about the effectiveness of any changes -- capitalizing on dramatic improvements while possibly avoiding wasted time or capital when results are not as effective.
Dig Deeper on Enterprise infrastructure management
Related Q&A from Stephen J. Bigelow
Get to know VMware vSphere's Admission Control tool and use it to reserve the resources necessary for VM failover with cluster resource calculations ... Continue Reading
Use heartbeats, VM monitoring and application monitoring to fully examine the causes of VM unresponsiveness. Adjust sensitivity levels to focus on ... Continue Reading
Combine Distributed Resource Scheduler and vSphere High Availability to design balanced failover clusters. Pay attention to affinity rules, which can... Continue Reading
Have a question for an expert?
Please add a title for your question
Get answers from a TechTarget expert on whatever's puzzling you.