BUSINESS VOLUME QUALICISION (BVQ)


Content


Brief description

The BVQ VMware platform is the continuation of the existing BVQ VMware package. It introduces support for VMware performance metrics and enables you to interactively explore your VMware configuration, check all kind of performance metrics and alert on metrics, create reports and drill through all the layers between SVC, BVQ, and VMware objects in end to end views.

As BVQ will now support a 'new' platform completely, customers will be able to use this VMware platform as a standalone solution. So you don't need to license IBM Spectrum Virtualize or Storwize (but a combination of both platforms are possible to get an end to end view of the environment). A combination of the SAN package with the new VMware platform is also possible.

Licensing

Customers using the current VMware package (topology & capacity data) will be able to upgrade to the new VMware platform now including performance data as well.

The VMware platform is licensed by the number of Virtual machines (VMs) running in the environment. Customers will have to license packs of 25 VMs (sum of VMs in the envrionment divided by 25 = number of packs to license) 

Please contact your SVA sales representative for pricing information.

Information gathering

To collect information a BVQ VMware scanner needs to be configured to connect to a vCenter. If a VMware scanner already exists to scan topology data, performance data collection can be enabled easily in the scanner configuration.


Important

During the BVQ performance scan of a vCenter server the CPU usage of the vCenter server will increase. Please monitor the vCenter server utilization depending on the workload to avoid performance degradation.
Maybe CPU or memory expansion is needed to be able to scan VMware performance data properly.
BVQ Installation: Preparation#VMwarevCenterSystemsVMwarevCentersystems


See Supported environments and BVQ server requirements for more details and the supported versions of the VMware vCenter versions.


Supported VMware objects

The first version of the BVQ VMware Performance supports most elements of a VMware environment. The following overview depicts the elementary relationships of these objects and their link to connected BVQ objects:

BVQ VMware performance stats object-types V1

Where to find VMware objects?

Similar to the already known VMware Topology package all available objects show up in the BVQ Path browser inside the view property panel or can be opened as a table from the favorite browser. All VMware objects can be combined in an end to end relation to all other objects.

VMware objects in view Path browserVMware object Table views in BVQ Favorites


 BVQ VMware object details
VMware










Resource consumer


VM Virtual machine
VM Virtual disk
VM LUN
Virtualization layer



VM vCenter
VM Datacenter
VM Cluster
VM Host
Resource Provider


VM Datastore cluster
VM Datastore
VM SCSI volume 2 Host
VM Disk group
VM SCSI volume

Performance metrics

The BVQ VMware Performance Package gathers statistics delivered from the VMware performance API. Similar to all other statistics, you can simply drill into a chart with the statistics related to an object with a simple click on the VMware entry in the context menu of this object:


That opens our well known BVQ Chart view, where you can select metrics in the selection panel. The following screenshots shows the full set of available metrics in the expert tab for each object type:


VM Host

 VM Host metric details

These are the available VM Host metrics in more detail:

GroupMetricUnitDescription

CPU

% UtilizationPhysical%CPU usage as a percentage during the interval
% UtilizationLogical%CPU utilization as a percentage during the interval
(CPU usage & CPU utilization might be different due to
power management technologies or hyper-threading)
ms per stateWaitms/intervalTotal CPU time spent in wait state
ms per stateSwap waitms/intervalCPU time spent waiting for swap-in
ms per stateCo-stopms/intervalTime the host is ready to run, but is unable to run
due to co-scheduling constraints
ms per stateIdlems/intervalTotal time that the CPU spent in idle state
ms per stateReadyms/intervalTime that the host was ready, but could not get scheduled to run
on the physical CPU during last measurement interval

VM assigned MHzTotalMHzTotal CPU capacity reserved by and available for virtual machines
VM assigned MHzUsageMHzCPU usage in megahertz during the interval
VM assigned MHzReservedMHzTotal CPU capacity reserved by virtual machines

Memory
Utilization%%Percentage of host physical memory that has been consumed
UtilizationGiBGiBTotal amount of physical memory consumed by the host




By typeGrantedGiBAmount of host physical memory or physical memory that is
mapped for a virtual machine or a host
By typeSharedGiBAmount of guest physical memory that is shared with other
virtual machines, relative to a single virtual machine or to all
powered-on virtual machines on a host
By typeActiveGiBAmount of guest physical memory that is being actively read or
written by guest. Activeness is estimated by ESXi
By typeActive writeGiBEstimate for the amount of memory actively being written to
by the virtual machine
By typeActive write %%Estimate for the amount of memory actively being written to
by the virtual machine




VM memory reservation

ReservedGiBTotal amount of memory reservation used by powered-on
virtual machines and vSphere services on the host
VM memory reservationUnreservedGiBAmount of memory that is unreserved
VM memory reservationTotalGiBTotal amount of memory reservation used by and available
for powered-on virtual machines and vSphere services on the host
VM memory reservationReserved %%
VM memory reservationUnreserved %%

SwapSwap inMiBAmount swapped-in to memory from disk
SwapSwap outMiBAmount of memory swapped-out to disk
SwapSwap usedMiBAmount of memory that is used by swap
Swap% Swap in%
Swap% Swap out%

% WaitComp/Swap%Percentage of time the virtual machine is waiting to access swapped or
compressed memory

TresholdLow free

GiB

Threshold of free host physical memory below which ESX/ESXi
will begin reclaiming memory from virtual machines
through ballooning and swapping
Storage
Latency worstDatastoremsHighest latency value across all datastores used by the host
Latency worstDiskmsHighest latency value across all disks used by the host
Latency worstStorage adaptermsHighest latency value across all storage adapters used by the host
Latency worstStorage pathmsHighest latency value across all storage paths used by the host

SCSi Disk data rateRMiB/sAverage number of kilobytes read from the disk each second
during the collection interval
SCSi Disk data rateWMiB/sAverage number of kilobytes written to disk each second
during the collection interval
SCSi Disk data rateR+W (Usage)MiB/sAggregated disk I/O rate. For hosts, this metric includes the rates
for all virtual machines running on the host during the collection interval
SCSi Disk data rate% R%
VM Virtual machine

 VM Virtual machine metric details

These are the available VM Virtual machine metrics in more detail:

GroupMetricUnitDescription

CPU

ms per stateWaitms/intervalTotal CPU time spent in wait state
ms per stateSwap waitms/intervalCPU time spent waiting for swap-in
ms per stateCo-stopms/intervalTime the virtual machine is ready to run,
but is unable to run due to co-scheduling constraints
ms per stateIdlems/intervalTotal time that the CPU spent in an idle state
ms per stateReadyms/intervalTime that the virtual machine was ready, but could
not get scheduled to run on the physical CPU during
last measurement interval

Utilization%%CPU usage as a percentage during the interval
UtilizationMHzMHzCPU usage in megahertz during the interval
Memory
Utilization%%Memory usage as percentage of total configured or
available memory
UtilizationGiBGiBAmount of host physical memory consumed by the
virtual machine.

By typeGrantedGiBAmount of host physical memory or physical memory
that is mapped for a virtual machine or a host
By typeSharedGiBAmount of guest physical memory that is shared with other
virtual machines, relative to a single virtual machine or
to all powered-on virtual machines on a host
By typeActiveGiBAmount of memory that is actively used, as estimated by
VMkernel based on recently touched memory pages
By typeActive writeGiBEstimate for the amount of memory actively being written to
by the virtual machine
By typeActive write %%

SwapSwap inMiBAmount swapped-in to memory from disk
SwapSwap outMiBAmount of memory swapped-out to disk
SwapSwap usedMiBCurrent amount of guest physical memory swapped out to
the virtual machine swap file by the VMkernel
SwapSwap in %%
SwapSwap out %%

% WaitComp/Swap%Percentage of time the virtual machine is waiting to access swapped
or compressed memory

Balloon targetBalloon target

MiB

Target value set by VMkernal for the virtual machine's
memory balloon size

Storage
Latency worstDatastoremsHighest latency value across all datastores used by the host
Latency worstDiskmsHighest latency value across all disks used by the host

Virtual Disk data rateRMiB/s

Average number of kilobytes read from the disk
each second during the collection interval

Virtual Disk data rateWMiB/s

Average number of kilobytes written to disk
each second during the collection interval

Virtual Disk data rateR+W (Usage)MiB/s
Virtual Disk data rate% R%
VM LUN

 VM LUN metric details

These are the available VM LUN metrics in more detail:

GroupMetricUnitDescription
Traffic

IO rate

RIO/s

Average number of read commands issued per second
to the virtual disk during the collection interval

IO rate

WIO/s

Average number of write commands issued per second
to the virtual disk during the collection interval

IO rate

R+WIO/s

IO rate

R%%

Data rateRMiB/sRate of reading data from the virtual disk
Data rateWMiB/sRate of writing data to the virtual disk
Data rateR+WMiB/s
Data rateR%%

LatencyRms/IOThe average time a read from the virtual disk takes
LatencyWms/IOThe average time a write to the virtual disk takes
LatencyR&Wms/IO

Transfer sizeRKiB/IO
Transfer sizeWKiB/IO
Transfer sizeR&WKiB/IO

Outstanding requestsRcountAverage number of outstanding read requests to the virtual disk
during the collection interval
Outstanding requestsWcountAverage number of outstanding write requests to the virtual disk
during the collection interval
Outstanding requestsR+Wcount
Outstanding requestsR%%
VM vCenter

 VM vCenter metric details

These are the available VM vCenter metrics in more detail:

GroupMetricUnitDescription

System

UtilizationCPU %%CPU used by vCenter Server in user mode
UtilizationMiB MemoryMiBVirtual memory used by vCenter Server
VM Cluster

 VM Cluster metric details

These are the available VM Cluster metrics in more detail:

GroupMetricUnitDescription

System

CPUTotalMHzTotal amount of CPU resources of all hosts in the cluster
CPUAvailableMHzTotal available CPU resources of all hosts within a cluster
CPUAvailable %%

MemoryTotalGiBTotal amount of host physical memory of all hosts in the cluster
that is available for virtual machine memory (physical memory for use by
the guest OS) and virtual machine overhead memory
MemoryAvailableGiBTotal amount of machine memory of all hosts in the cluster that is available
for use for virtual machine memory and overhead memory
MemoryAvailable %%
VM SCSI volume 2 Host

 VM SCSI volume 2 Host metric details

These are the available VM SCSI volume 2 Host metrics in more detail:

GroupMetricUnitDescription
Traffic

IO rate

RIO/sAverage number of disk reads per second during the collection interval

IO rate

WIO/sAverage number of disk writes per second during the collection interval

IO rate

R+WIO/s

IO rate

R%%

Date rateRMiB/sAverage number of kilobytes read from the disk each second during the collection interval
Date rateWMiB/sAverage number of kilobytes written to disk each second during the collection interval
Date rateR+WMiB/s
Date rateR%%




LatencyRms/IOAverage time a read from the disk takes
LatencyWms/IOAverage time a write to the disk takes
LatencyR&Wms/IOAverage time a read/write from the disk takes
LatencyR%%

Transfer sizeRKiB/s
Transfer sizeWKiB/s
Transfer sizeR&WKiB/s

BusBus resetscountNumber of SCSI bus reset commands issued during the collection interval


Performance Indicators (PI)

The VMware Performance Package also take full advantage of the new BVQ Feature: "Performance Indicators for all performance metrics" which enables the use of all performance metrics as PI.

This finally allows a PI based treemap sizing as well as the usage of PI in a table for VMware objects.


Thereby it is much easier to find "High Performer" and Bottlenecks.



  • No labels