Services Virtual HealthCheck and Services
Broad deployment of virtualization in business-critical applications has been limited by poor visibility into how the SAN I/O infrastructure affects the performance of applications deployed on Virtual Machines. The complexity of the virtualized environment coupled with frequently changing infrastructure has made "Fabric Blindness" a growing threat to information availability.
The Virtual Infrastructure HealthCheck and Performance Scan Service is designed for customers who have deployed virtualized infrastructure and need visibility into how the SAN I/O infrastructure affects the performance of applications deployed on Virtual Machines. The service provides real-time performance information from the Virtual Machine on the server through the host bus adapter (HBA), out through the SAN switch and right to the LUN on the storage array.
This provides the ability to quickly identify performance and behavior anomalies and trouble spots on any Virtualized environment. The service scans all levels of connectivity to identify potential communication issues from the Virtual Machine through the Fibre Channel network and points out potential issues that are on the verge of or have exceeded the “rules of thumb” infrastructure behavior. A comprehensive report of analysis and findings is provided at the conclusion of the service. The customer may then choose to request additional services to provide detailed capacity planning or to assist in the resolution of issues found during the Virtual Infrastructure HealthCheck and Performance Scan Service.
What We Deliver
- Identify performance and behavior anomalies and potential trouble spots
- A list of industry accepted "Fibre Channel rules of thumb" used to judge the results
- Point out potential issues that are on the verge of or have exceeded the "rules of thumb" SAN infrastructure behavior.
- Recommendations for future actions
What You Get
- Quickly identify any potential Virtual Infrastructure performance or availability issues
- Identify any evolving issues before they become real problems
- Thorough report and analysis
What is Measured
- Connectivity - Physical layer errors, frame errors, loss of sync or signal, canceled transactions and associated devices, failed communications, communication aborted by servers, canceled transactions and associated devices, other events, server reboots, fabric logins/logouts and resets, code violations, check conditions
- Performance - Latencies, read data access times (worst and average), write data times (worst and average), latency time-of-day trends, latency-to-load relationships, responsiveness, array response times to read requests – worst, and average, performance time-of-day trends, applications, i/o read & write request sizes
- Capacity Planning - Server and virtual machine assessment, most demanding servers and virtual machines, least active servers and virtual machines storage array port assessment, most active storage ports, underutilized storage ports, storage lun assessment, most active and least active luns
- Configurations - Load balancing, active/active load comparison, active/passive link failovers, queue depth settings, server queue depth configuration optimization, storage array resource level port analysis, storage lun resource level assessment