Grid GPUs – ESX Test

GPU-accelerated computing is the use of a graphics processing unit (GPU) together with a CPU to accelerate scientific, analytics, engineering, consumer, and enterprise applications. GPU-accelerated computing enhances application performance by offloading compute-intensive portions of the application to the GPU, while the remainder of the code still runs on the CPU. Architecturally, while a CPU has only few cores and handles few hundred threads at a time, a GPU is composed of hundreds of cores that can handle thousands of threads simultaneously and render a flawless rich graphics experience.

Now, imagine if you could access your GPU-accelerated applications, even those requiring intensive graphics power, anywhere on any device. NVIDIA GRID makes this possible. With NVIDIA GRID, a virtualized GPU designed specifically for virtualized server environments, data center managers can bring true PC graphics-rich experiences to users.

The NVIDIA GRID GPUs will be hosted in enterprise data centers and allow users to run virtual desktops or virtual applications on multiple devices connected to the internet and across multiple operating systems, including PCs, notebooks, tablets and even smartphones. Users can utilize their online-connected devices to enjoy the GPU power remotely.

In VDI/virtualized server environments, the NVIDIA GRID delivers GPU resources to virtual desktops/VMs. This way, graphics can be rendered on a virtual machine’s (VM’s) host server rather than on a physical end-point device. This technology now makes it possible to use virtual desktop technology to support users accessing graphics intensive workloads. There are two modes of making GPU resources available to virtual desktops:

Dedicated GPU or GPU Pass-through Technology: NVIDIA GPU pass-through technology lets you create a virtual workstation that gives users all the benefits of a dedicated graphics processor at their desk. By directly connecting a dedicated GPU to a virtual machine through the hypervisor, you can now allocate the full GPU and graphics memory capability to a single virtual machine without any resource compromise.

Figure 1 : Dedicated GPU Technology
Shared GPU or Virtual GPU (vGPU) Technology: GRID vGPU is the industry’s most advanced technology for sharing true GPU hardware acceleration between multiple virtual desktops—without compromising the graphics experience. With GRID vGPU technology, the graphics commands of each virtual machine are passed directly to the GPU, without translation by the hypervisor. This allows the GPU hardware to be time-sliced to deliver improved shared virtualized graphics performance. The GRID vGPU manager allows for management of user profiles. IT managers can assign the optimal amount of graphics memory and deliver a customized graphics profile to meet the specific needs of each user. Every virtual desktop has dedicated graphics memory, just like they would at their desk, so they always have the resources they need to launch and run their applications.

Figure 2 : Shared vGPU Technology

In GPU-enabled VMware vSphere environments, if users to VMs/virtual desktops complain of slowness when accessing graphic applications, administrators must be able to instantly figure out what is causing the slowness – is it because adequate GPU resources are not available to the host? Or is it because of excessive utilization of GPU memory and processing resources by a few VMs/virtual desktops on the host? Accurate answers to these questions can help administrators determine whether/not:
The host is sized with sufficient GPU resources;
The GPUs are configured with enough graphics memory;
The GPU technology in use – i.e., the GPU Pass-through technology or the Shared vGPU technology – is ideal for the graphics processing requirements of the environment;

Measures to right-size the host and fine-tune its GPU configuration can be initiated based on the results of this analysis. This is exactly what the Grid GPUs - ESX test helps administrators achieve!

This test supports GPU monitoring for NVIDIA K1 and K2 Grids installed on a VMware vSpere server. Using the test, administrators can monitor each physical GPU card installed on the server and can determine how actively memory on that card is utilized, thus revealing the card on which memory is used consistently. In addition, the test also indicates how busy each GPU card is, and in the process pinpoints those GPU cards that are being over-utilized by the VMs/virtual desktops on the host. The adequacy of the physical GPU resources is thus revealed. Moreover, detailed diagnostics provided by the test also lead you to those VMs/virtual desktops that are using each card. In addition, the power consumption and temperature of each GPU card is also monitored, so that its current temperature and power usage can be ascertained; administrators are thus alerted to abnormal power usage of the GPU and unexpected fluctuations in its temperature. The power limit set and the clock frequencies configured are also revealed, so that administrators can figure out whether the GPU is rightly configured for optimal processing or is any fine-tuning required.

Note:

This test will report metrics for NVIDIA GPUs only if the requirements detailed in the Pre-requisites for Monitoring NVIDIA GPUs topic are fulfilled.

Target of the test : A VMware vSphere host

Agent deploying the test : An internal/remote agent

Outputs of the test : One set of results for each GRID physical GPU assigned to the XenServer host being monitored

Configurable parameters for the test:
Parameter	Description
Test Period	How often should the test be executed
Host	The host for which the test is to be configured
Port	The port at which the specified HOST listens. By default, this is NULL.
ESX User and ESX Password	In order to enable the test to extract the desired metrics from a target ESX server, you need to configure the test with an ESX USER and ESX PASSWORD. The user credentials to be passed here depend upon the mechanism used by the eG agent for auto-discovering the VMs on the target vSphere server and monitoring the server and its VMs. These discovery/monitoring methodologies and their corresponding configuration requirements have been discussed hereunder: Discovering and monitoring by directly connecting to the target vSphere server: Starting with ESX server 3.0, a VMware ESX server offers a web service interface using which the eG agent discovers the guest operating systems on a physical ESX host. The VMware VI SDK is used by the agent to implement the web services interface. To use this interface for discovering the VMs and for monitoring, the eG agent should directly connect to the monitored vSphere/ESX server as an ESX USER with root privileges. However, if, owing to security constraints, you cannot use root user permissions, you can alternatively configure the tests with the credentials of a user who has been assigned the following permissions: Diagnostics TerminateSession To see how you can create such a user on the ESX server, refer to theCreating a Special Role on an ESX Server and Assigning the Role to a New User topic Discovering and monitoring using vCenter: By default, the eG agent connects to each ESX server and discovers the VMs executing on it. While this approach scales well, it requires additional configuration for each server being monitored. For example, separate user accounts may need to be created on each server for accessing VM details. While monitoring large virtualized installations however, the agents can be optionally configured to perform guest discovery using the VM information already available in vCenter. The same vCenter can also be used to monitor the vSphere server and its VMs. In this case therefore, the ESX USER and ESX PASSWORD that you specify should be that of an Administrator or Virtual Machine Administrator in vCenter. However, if, owing to security constraints, you prefer not to use the credentials of such users, then, you can create a special role on vCenter with the following privileges: Diagnostics Change settings View and stop sessions To know how to grant the above-mentioned permissions to a vCenter user, refer to Creating a Special Role on vCenter and Assigning the Role to a New User . If the ESX server for which this test is being configured had been discovered via vCenter, then the eG manager automatically populates the ESX USERand ESX PASSWORD text boxes with the vCenter user credentials using which the ESX discovery was performed.
Confirm Password	Confirm the specified ESX PASSWORD by retyping it here.
SSL	By default, the ESX server is SSL-enabled. Accordingly, the SSL flag is set to Yes by default. This indicates that the eG agent will communicate with the ESX server via HTTPS by default. On the other hand, if the eG agent has been configured to use the VMPerl API or CLI for monitoring (i.e., if the ESX USER parameter is set to none), then the status of the SSL flag is irrelevant. Like the ESX sever, the vCenter is also SSL-enabled by default. If you have chosen to use the vCenter for monitoring all the ESX servers in your environment, then you have to set the SSL flag to Yes.
Webport	By default, in most virtualized environments, the ESX server and vCenter listen on port 80 (if not SSL-enabled) or on port 443 (if SSL-enabled). This implies that while monitoring an SSL-enabled ESX server directly, the eG agent, by default, connects to port 443 of the ESX server to pull out metrics, and while monitoring a non-SSL-enabled ESX server, the eG agent connects to port 80. Similarly, while monitoring an ESX server via an SSL-enabled vCenter, the eG agent connects to port 443 of vCenter to pull out the metrics, and while monitoring via a non-SSL-enabled vCenter, the eG agent connects to port 80 of vCenter. Accordingly, the WEBPORT parameter is set to 80 or 443 depending upon the status of the SSL flag. In some environments however, the default ports 80 or 443 might not apply. In such a case, against the WEBPORT parameter, you can specify the exact port at which the ESX server or vCenter in your environment listens so that the eG agent communicates with that port.
Virtual Center	If the eG manager had discovered the target ESX server by connecting to vCenter, then the IP address of the vCenter server used for discovering this ESX server would be automatically displayed against the VIRTUAL CENTER parameter; similarly, the ESX USER and ESX PASSWORD text boxes will be automatically populated with the vCenter user credentials, using which ESX discovery was performed. If this ESX server has not been discovered using vCenter, but you still want to discover the guests on the ESX server via vCenter, then select the IP address of the vCenter host that you wish to use for guest discovery from the VIRTUAL CENTER list. By default, this list is populated with the IP address of all vCenter hosts that were added to the eG Enterprise system at the time of discovery. Upon selection, the ESX USERand ESX PASSWORD that were pre-configured for that vCenter server will be automatically displayed against the respective text boxes. On the other hand, if the IP address of the vCenter server of interest to you is not available in the list, then, you can add the details of the vCenter server on-the-fly, by selecting the Other option from the VIRTUAL CENTER list. This will invoke the ADD VCENTER SERVER DETAILS page. Refer to Adding the Details of a vCenter Server for VM Discoverysection to know how to add a vCenter server using this page. Once the vCenter server is added, its IP address, ESX USER, and ESX PASSWORD will be displayed against the corresponding text boxes. On the other hand, if you want the eG agent to behave in the default manner -i.e., communicate with each ESX server for monitoring and VM information - then set the VIRTUAL CENTER parameter to ‘none’.
DD Frequency	Refers to the frequency with which detailed diagnosis measures are to be generated for this test. The default is 1:1. This indicates that, by default, detailed measures will be generated every time this test runs, and also every time the test detects a problem. You can modify this frequency, if you so desire. Also, if you intend to disable the detailed diagnosis capability for this test, you can do so by specifying none against DD FREQUENCY.
Detailed Diagnosis	To make diagnosis more efficient and accurate, eG Enterprise embeds an optional detailed diagnostic capability. With this capability, the eG agents can be configured to run detailed, more elaborate tests as and when specific problems are detected. To enable the detailed diagnosis capability of this test for a particular server, choose the On option. To disable the capability, click on the Off option. The option to selectively enable/disable the detailed diagnosis capability will be available only if the following conditions are fulfilled: The eG manager license should allow the detailed diagnosis capability Both the normal and abnormal frequencies configured for the detailed diagnosis measures should not be 0.

Measurements made by the test

Measurement

Description

Measurement Unit

Interpretation

GPU memory utilization:

Indicates the proportion of time over the past sample period during which global (device) memory was being read or written on this GPU.

Percent

A value close to 100% is a cause for concern as it indicates that graphics memory on a GPU is almost always in use.

In a Shared vGPU environment on the other hand, memory may be consumed all the time, if one/more VMs/virtual desktops on the host utilize the graphics memory excessively and constantly. If you find that only a single VM/virtual desktop has been consistently hogging the graphic memory resources, you may want to switch to the Dedicated GPU mode, so that excessive memory usage by that VM/virtual desktop has no impact on the performance of other VMs/virtual desktops on that host.

If the value of this measure is high almost all the time for most of the GPUs, it could mean that the host is not sized with adequate graphics memory.

Used frame buffer memory:

Indicates the amount of frame buffer memory on-board this GPU that is being used by the host.

MiB

Frame buffer memory refers to the memory used to hold pixel properties such as color, alpha, depth, stencil, mask, etc.

Properties like the screen resolution, color level, and refresh speed of the frame buffer can impact graphics performance.

Also, if Error-correcting code (ECC) is enabled on a host, the available frame buffer memory may be decreased by several percent. This is because, ECC uses up memory to detect and correct the most common kinds of internal data corruption. Moreover, the driver may also reserve a small amount of memory for internal use, even without active work on the GPU; this too may impact frame buffer memory.

For optimal graphics performance therefore, adequate frame buffer memory should be allocated to the host.

Free frame buffer memory:

Indicates the amount of frame buffer memory on-board this GPU that is yet to be used by the host.

MiB

Frame buffer memory utilization:

Indicates the percentage of frame buffer memory on-board this GPU that is being utilized by the host.

Percent

A value close to 100% is indicative of excessive frame buffer memory usage.

Properties like the screen resolution, color level, and refresh speed of the frame buffer can impact graphics performance.

For optimal graphics performance therefore, adequate frame buffer memory should be allocated to the host.

GPU compute utilization:

Indicates the proportion of time over the past sample period during which one or more kernels was executing on this GPU.

Percent

A value close to 100% indicates that the GPU is busy processing graphic requests almost all the time.

In a Shared vGPU environment on the other hand, a GPU may be in use almost all the time, if one/more VMs/virtual desktops on the host are running highly graphic-intensive applications. If you find that only a single VM/virtual desktop has been consistently hogging the GPU resources, you may want to switch to the Dedicated GPU mode, so that excessive GPU usage by that VM/virtual desktop has no impact on the performance of other VMs/virtual desktops on that host.

If all GPUs are found to be busy most of the time, you may want to consider augmenting the GPU resources of the host.

Compare the value of this measure across physical GPUs to know which GPU is being used more than the rest.

Power consumption:

Indicates the current power usage of this GPU.

Watts

A very high value is indicative of excessive power usage by the GPU.

In such cases, you may want to enable Power management so that the GPU limits power draw under load to fit within a predefined power envelope by manipulating the current performance state.

Core GPU temperature:

Indicates the current temperature of this GPU.

Celsius

Ideally, the value of this measure should be low. A very high value is indicative of abnormal GPU temperature.

Total framebuffer memory:

Indicates the total size of frame buffer memory of this GPU.

Frame buffer memory refers to the memory used to hold pixel properties such as color, alpha, depth, stencil, mask, etc.

Total BAR1 memory:

Indicates the total size of the BAR1 memory of this GPU.

MiB

BAR1 is used to map the frame buffer (device memory) so that it can be directly accessed by the CPU or by 3rd party devices (peer-to-peer on the PCIe bus).

Used BAR1 memory:

Indicates the amount of BAR1 memory on this GPU that is being used by to the host.

MiB

For better user experience with graphic applications, enough BAR1 memory should be available to the host.

Free BAR1 memory:

Indicates the total size of BAR1 memory of this GPU that is still not used by the host.

MiB

BAR1 memory utilization:

Indicates the percentage of the total BAR1 memory on this GPU that is currently being utilized by the host.

Percent

A value close to 100% is indicative of excessive BAR1 memory usage by the host.

For best graphics performance, sufficient BAR1 memory resources should be available to the host.

Power management:

Indicates whether/not power management is enabled for this GPU.

Many NVIDIA graphics cards support multiple performance levels so that the server can save power when full graphics performance is not required.

The default Power Management Mode of the graphics card is Adaptive. In this mode, the graphics card monitors GPU usage and seamlessly switches between modes based on the performance demands of the application. This allows the GPU to always use the minimum amount of power required to run a given application. This mode is recommended by NVIDIA for best overall balance of power and performance. If the power management mode is set to Adaptive, the value of this measure will be Supported.

Alternatively, you can set the Power Management Mode to Maximum Performance. This mode allows users to maintain the card at its maximum performance level when 3D applications are running regardless of GPU usage. If the power management mode of a GPU is Maximum Performance, then the value of this measure will be Maximum.

The numeric values that correspond to these measure values are discussed in the table below:

Measure Value	Numeric Value
Supported	1
Maximum	0

Note:

By default, this measure will report the Measure Values listed in the table above to indicate the power management status. In the graph of this measure however, the same is represented using the numeric equivalents only.

Power limit:

Indicates the power limit configured for this GPU.

Watts