VirtualInstruments

VirtualWisdom^® Virtual Server Probe Features

VirtualWisdom Virtual Server Probe is a virtual software probe that automatically discovers and monitors 120+ CPU, memory, network and disk I/O metrics for VMware ESX virtual machines, physical servers, and clusters. Some of the features include:

• Agent-less architecture enables quick deployment with real-time monitoring of virtual machines, physical servers, and clusters
• Collects data on and calculates 120+ different metrics including CPU utilization and status, memory utilization, disk I/O requests and capacity, network requests and utilization.
• Enables monitoring, modeling, and optimization of VMware VMotion and Distributed Resource Scheduler for performance and availability based on historical data and trends
• User definable data collection frequency from VMware vCenter – as low as every 20 seconds
• Policy-based event notifications
• Simple dashboard-view of virtual to physical server I/O from server to storage arrays with drill-down reports for quick problem resolution
• Simple installation into any VMware virtualized environment

VirtualWisdom’s configurable dashboard provides a simple, customizable view of I/O from the application on the virtual machine and server to the LUNSs on the storage arrays. Metrics, fault warnings and policy deviations are continually updated with quick drill-down reports. SNMP traps can be configured on nearly all of the leading management platforms to receive alarms from VirtualWisdom to ensure maximum performance on mission-critical applications. Finally, alarms can be configured within VirtualWisdom to e-mail reports triggered by an alarm.

Technical Specifications and Metrics

VirtualWisdom's configurable dashboard provides a simple, customizable view of I/O from the application on the virtual machine and server to the LUNSs on the storage arrays. Metrics, fault warnings and policy deviations are continually updated with quick drill-down reports.

The metrics collected or generated by Virtual Server Probe include:

• Total NIC Capacity (Mb/s): The total Network Interface Card capacity, used to calculate Network Utilization %.
• Disk IO Utilization %: The average Disk IO utilization percentage of total server HBA capacity.
• Network Utilization %: The average network utilization percentage of total server NIC capacity.
• Composite Utilization %: A combination index that shows the average percentage of total server capacity for four dimensions of resource usage including CPU, Memory, Disk IO and Network.
• Max Composite Utilization %: The maximum total server capacity resource observed for the four dimensions of resource usage including CPU, Memory, Disk IO and Network.
• Total HBA Link Capacity (Gb/s): The total Host Bus Adapter link capacity, also used to calculate Disk IO Utilization %.

CPU Metrics

• CPU Usage %: CPU usage as a percentage over the collected interval
• CPU Usage (MHz): CPU usage in MHz over the collected interval. For hosts this can be represented on a per Virtual Machine basis as a stacked graph
• CPU Extra (ms): CPU time that is extra
• CPU Guaranteed (ms): CPU time that is guaranteed
• CPU Ready (ms): CPU time spent in ready state
• CPU System (ms): CPU time spent on system processes
• CPU Used (ms): CPU time that is used
• CPU Reserved Capacity (MHz): Total CPU capacity reserved by the virtual machines
• CPU Wait (ms): CPU time spent in wait state
• CPU Idle (ms): CPU time spent in idle state
• Avg CPU Active (1 min): CPU active average over 1 minute
• Max CPU Active % (1 min): CPU active peak over 1 minute
• Max CPU Throttled % (1 min): Amount of CPU resources over the limit that are refused, average over 1 minute
• Avg CPU Running % (1 min): CPU running average over 1 minute
• Max CPU Running % (1 min): CPU running peak over 1 minute
• Group CPU Sample Count: Group CPU sample count
• Group CPU Sample Period (ms): Group CPU sample period
• Heartbeat: Number of heartbeats in this period
• Resource CPU Usage (MHz): Resource CPU usage
• Uptime (sec): Total time elapsed since last startup

Memory Metrics

• Memory Overhead (KB): Amount of additional host memory allocated to the virtual machine
• Memory Shared (KB): Amount of memory that is shared
• Memory Swap In (KB): Amount of memory that is swapped in
• Memory Swap Out (KB): Amount of memory that is swapped out
• Memory Swapped (KB): Amount of memory that is swapped
• Memory Swap Target (KB): Amount of memory that can be swapped
• Memory Usage %: Memory usage as percentage of total configured or available memory
• Memory Balloon (KB): Amount of memory used by memory control
• Memory Balloon Target (KB): Amount of memory that can be used by memory control
• Memory Zero (KB): Amount of memory that is zeroed out
• Avg Memory Active (KB): Amount of memory that is actively used
• Avg Memory Granted (KB): Amount of memory granted. For hosts this can be represented on a per Virtual Machine basis as a stacked graph.
• Avg Memory Heap (KB): Amount of memory allocated for heap
• Avg Memory Heap Free (KB): Free space in memory heap
• Avg Memory Overhead (KB): Amount of additional host memory allocated to the virtual machine
• Memory Reserved Capacity (KB): Amount of memory reserved by the virtual machines
• Avg Memory Shared (KB): Amount of memory that is shared
• Avg Memory Shared Common (KB): Amount of memory that is shared by common Memory state
• Avg Memory Swap In (KB): Amount of memory that is swapped in
• Avg Memory Swap Out (KB): Amount of memory that is swapped out
• Avg Memory Swap Used (KB): Amount of memory that
• Memory Used by VMKernel (KB): Amount of memory used by the VMKernel
• Avg Memory Unreserved (KB): Amount of memory that is unreserved
• Avg Memory Zero (KB): Amount of memory that is zeroed out
• Avg Agent Memory Used %: Memory Used as percentage of total configured or available memory
• Avg Agent Memory Swap In (KB): Amount of memory that is swapped in
• Avg Agent Memory Swap Out (KB): Amount of memory that is swapped out
• Avg Agent Memory Swap Used (KB): Amount of memory that is used by swap

Disk Metrics

• Memory Overhead (KB): Amount of additional host memory allocated to the virtual machine
• Disk Bus Resets: Number of bus resets in the period
• Disk Commands Issued: Number of disk commands issued in the period
• Disk Command Aborts: Number of disk commands aborted in the period
• Disk Read Requests: Number of disk reads in the period
• Disk Write Requests: Number of disk writes in the period
• Disk Read Rate (KB/s): Rate of reading data from the disk
• Disk Usage (KB/s): Aggregated storage performance statistics. For hosts this can be represented on a per Virtual Machine basis as a stacked graph
• Disk Write Rate (KB/s): Rate of writing data to the disk
• Avg Physical Device Command Latency (ms): Average time taken to complete a command from the physical device.
  Avg Physical Device Read Latency (ms): Average time taken to complete a read from the physical device.
• Avg Physical Device Write Latency (ms): Average time taken to complete a write from the physical device.
• Avg Kernel Disk Command Latency (ms): Average time spent in ESX Server VMKernel per command.
• Avg Kernel Disk Read Latency (ms): Average time spent in ESX Server VMKernel per read.
  Avg Kernel Disk Write Latency (ms): Average time spent in ESX Server VMKernel per write.
• Avg Queue Command Latency (ms): The average time spent in the ESX Server VMKernel queue per command.
• Avg Queue Read Latency (ms): The average time spent in the ESX Server VMKernel queue per read.
• Avg Queue Write Latency (ms): The average time spent in the ESX Server VMKernel queue per write.
• Avg Disk Command Latency (ms): The average amount of time taken for a command from the perspective of a Guest OS. This is the sum of Kernel Command Latency and Physical Device Command Latency.
• Avg Disk Read Latency (ms): The average amount of time taken for a read from the perspective of a Guest OS. This is the sum of Kernel Read Latency and Physical Device Read Latency.
• Avg Disk Write Latency (ms): The average amount of time taken for a write from the perspective of a Guest OS. This is the sum of Kernel Write Latency and Physical Device Write Latency.

Network Metrics

• Network Packets Received: Number of packets received in the period
• Network Packets Transmitted: Number of packets transmitted in the period
• Network Data Receive Rate (KB/s): Rate at which data is received
• Network Data Transmit Rate (KB/s): Rate at which data is transmitted
• Network Usage (KB/s): Aggregated network performance statistics. For hosts this can be represented on a per Virtual Machine basis as a stacked graph

   

Product Datasheets

• VirtualWisdom Virtual Server Probe | Virtual Server Probe collects information specifically about the utilization and performance of virtual machines within the VMware environment via the VMware vCenter server API. It is a virtual software probe that automatically discovers and monitors 120+ CPU, memory, network and disk I/O metrics for VMware ESX virtual machines, physical servers, and clusters. Actual measured data from VirtualWisdom enables IT managers to proactively balance the provisioning of applications on virtual machines for maximum application performance with the confidence that systems will not slow down or fail.

Related Product Datasheets

VirtualWisdom Solution Components

• VirtualWisdom Overview | VirtualWisdom provides comprehensive instrumentation and I/O measurement capabilities that reduce application response time, increase availability, and improve resource utilization. VirtualWisdom is the only product that can non-intrusively improve the performance of applications and increase the benefits of cloud-driven virtualization in real time by analyzing actual I/O traffic data.

• VirtualWisdom SAN Availability Probe | As a component of the Virtual Instruments’ VirtualWisdom solutions, the SAN Availability Probe is a non-agent based software probe that utilizes the MIB (management information block) from Fibre Channel switches via SNMP to gather switch performance and link error statistics in a non-intrusive manner. These critical switch statistics are collected by VirtualWisdom’s Server software and presented to the user in an easy to use configurable, graphical user interface.

•  VirtualWisdom SAN Performance Probe | The Virtual Instruments VirtualWisdom SAN Performance Probe analyzes every packet on a fibre channel SAN. A SAN Performance Probe can be dedicated to a single SAN link or, using a SANInsight Rover, can rove among many SAN links to provide statistics about storage I/O traffic as it relates to an application server, storage subsystem, remote replication, virtualization or other key SAN device or application.

SANInsight Hardware

• SANInsight Fibre TAP Patch Panel System | Virtual Instrument’s new SANInsight TAP Patch Panel System provides a range of options for integrating the unique, patented technology into patch panels. By unifying TAP and patch functions into a single layer of physical infrastructure, SANInsight significantly reduces the cost, complexity, and infrastructure impact of TAP deployment. SANInsight facilitates the broad installation of TAPs into both new and existing physical infrastructures, fully addressing the best practices monitorability requirement and enabling complete SAN optimization.

• SANInsight Enterprise Rover | The Virtual Instruments’ SANInsight Rover provides advanced capabilities to VirtualWisdom by maximizing the number of SAN links monitored by a SAN Performance Probe. The Rover extends the reach of VirtualWisdom in large enterprise SANs and lowers the cost of SAN monitoring and analysis.

• SANInsight Protocol Analyzer | The Virtual Instruments SANInsight Protocol Analyzer is a critical tool for IT personnel to troubleshoot component and systems utilizing the Fibre Channel protocol. It captures traffic and graphically reports performance metrics and data errors in real time whenever there is live Fibre Channel traffic over any monitored link. In addition, users can view MB/s, Kframes/sec, utilization, frame errors, and physical layer errors from each direction of the link.

• SANInsight Mobile Monitoring Option | As a member of the Virtual Instruments’ VirtualWisdom solutions family, the Mobile Monitoring Option (MMO) is designed to provide all of the features and benefits of VirtualWisdom-based instrumentation, monitoring, and measurement in a purpose-built, mobile cabinet, designed to house SANInsightTM Fibre Channel monitoring equipment. Use of the MMO enables IT staff to easily and quickly deploy an infrastructure optimizing VirtualWisdom solution anywhere in the datacenter.