vSphere 5 - 6

This paper discusses the benefits of deploying VMware vSphere with HP 3PAR Utility Storage including: greater virtual machine (VM) density, simplifying administration, and realizing significant cost savings in virtualized server environments. The paper also includes best practices for an integrated VMware vSphere and HP 3PAR Utility Storage solution.

- Performance and reliability features
- Queue depth throttling
- Metadata locking with SCSI reservations
- vSphere Storage APIs – Array Integration (VAAI)
- Storage I/O Controls
- vSphere Storage APIs – Storage Awareness (VASA)
- VMFS versus RDM 

3PAR Utility Storage with VMware vSphere

vCenter Infrastructure Navigator automatically discovers application services, visualizes relationships and maps dependencies of applications on virtualized compute, storage and network resources. It's a component of the vCenter Operations Management Suite. vCenter Infrastructure Navigator enables application-aware management of infrastructure and operations to better understand the impact of change, provide more complete disaster recovery protection and minimize downtime.

• Automatically discover and keep up-to-date the names and version numbers of application components and services
• Visualize application relationships, communication paths and backend connections at the infrastructure, guest OS and application level
• Map dependencies of application components on the underlying virtual infrastructure to understand the impact of change and build disaster recovery plans with confidence.

 The voice over of this video is done by Ben Scheerer, follow him on Titter via @benscheerer

This white paper summarizes findings and recommends best practices to tune the different layers of an application’s environment for similar latency-sensitive workloads. By latency-sensitive, VMware means workloads that are looking at optimizing for a few microseconds to a few tens of microseconds end-to-end latencies; they don’t mean workloads in the hundreds of microseconds to tens of milliseconds end-to-end-latencies. In fact, many of the recommendations in this paper that can help with the microsecond level latency can actually end up hurting the performance of applications that are tolerant of higher latency.

- BIOS Settings
- NUMA
- Choice of Guest OS
- Physical NIC Settings
- Virtual NIC Settings
- VM Settings
- Polling Versus Interrupts
- Guest OS Tips and Tricks

VMware also has investigated the performance of two latency micro-benchmarks, one for Infiniband devices and another for networking devices, in VM DirectPath I/O (pass-through) mode, which bypasses most of the virtualization stack except the path for delivering interrupts from the underlying physical devices to the guest OS. Applying the recommendations reduced latency and therefore increased the score of these latency micro-benchmarks in a virtualized environment, bringing it closer to bare metal performance.

With VMware Data Recovery 2.0, VMware has extended the ability to quickly and simply protect and restore virtual machines. Fully integrated with VMware vCenter Server, VMware Data Recovery gives central management of backup and restore operations, and the inherent deduplication of data saves significant disk space and provides flexible options for storage. VMware Data Recovery 2.0 has introduced a number of improvements including performance enhancements, speed, and reliability improvements, as well as capabilities to enhance management with the ability to email reports and schedule maintenance windows.

Several fixes have been included that rectify issues found in VMware Data Recovery 1.2.1. Issues that have been resolved include:

• CIFS target handling and resilience
• Incremental RDM backup
• Backups failing with “not enough disk space” errors
• Backups failing with “disk full” error despite free space being available

What happens during a front-end network outage? This video discusses and demonstrates what happens in a VMware vSphere Storage Appliance (VSA) cluster during a front-end network outage.

What happens during a back-end network outage? This video discusses and demonstrates what happens in a VMware vSphere Storage Appliance (VSA) cluster during a back-end network outage. 

VSA allows features like vMotion, DRS, Storage vMotion, and HA to be possible using only local storage. This enables advanced vSphere capabilities now to be possible for environments as small as just two servers. vSphere provides the VSA environment with tools to monitor and manage performance and understanding the key factors of VSA performance helps drive a successful deployment.

The performance of VSA is directly related to the hardware configuration of the systems used for its cluster. Big differences in capacity, performance, and price exist depending on the exact configuration used. The data replication performed by VSA across its cluster nodes provides high availability, but also has an effect on performance. Testing was done with a mixed workload to examine application performance and infrastructure operations. A set of tests with an I/O generation tool were also run to examine what happens across the hosts in a VSA cluster and to illustrate how to monitor and manage performance.

Performance of VSA in VMware Sphere 5