Open topic with navigation
The following table provides the minimum and recommended hardware specifications for running Media Server. The recommended specifications are only a guide, because actual requirements depend on the data that is being ingested and the processing tasks that you configure.
The minimum number of CPU cores can be calculated as follows:
Number of concurrent
For example, if you want to process video from three cameras simultaneously, and you want to run three analysis tasks on each stream and some type of encoding, the server should have a minimum of 16 cores:
3 x (1 + 3 + 1) + 1 = 16.
|HPE recommends Intel Xeon CPUs, because Media Server has been optimized for Intel processors.|
|Memory||4 GB||16 GB|
To run tasks that use convolutional neural networks on a machine that has a processor from the AMD Bulldozer series, download
libopenblas_AMD_Bulldozer.dll from the Big Data Download Center, and rename it such that it replaces the file
libopenblas.dll that is included in the Media Server installation. This is necessary to work around a known issue with these processors.
If you deploy multiple Media Servers across multiple machines, ensure that all of the machines synchronize their clocks with a time server.
If you are running antivirus software on the Media Server host machine, you must ensure for performance reasons that it does not monitor the Media Server directories.
Some advanced antivirus software can scan the network and might block some Media Server traffic, which can cause errors. Where possible, exempt the Media Server processes from this kind of network traffic analysis.
To accelerate processing by using a GPU, your system must have a NVIDIA graphics card with CUDA compute capability version 3.0 to 5.2 (Kepler and Maxwell micro-architecture). All Quadro, Tesla, and GeForce GTX series cards that meet this requirement are supported. Tegra series cards are not supported, but support can be requested by contacting HPE. Media Server has been tested with NVIDIA Quadro K6000 and NVIDIA Quadro M6000 graphics cards. The number and size of concurrent tasks that you can run on the GPU is constrained by the amount of memory available on the graphics card.
Only one Media Server can use each GPU. To run several instances of Media Server with GPU support on the same physical machine, the machine must have multiple GPUs. In the configuration file for each Media Server, you must set the
GPUDeviceID parameter to specify which GPU to use (set this parameter to a different value for each Media Server).
If you are installing Media Server on a virtual machine, the virtual machine might need additional configuration to use the GPU successfully.
To achieve the best performance, the amount of memory in the machine must match or exceed the amount of RAM available on the GPU(s). For example, if you have two GPUs and each has 12 GB RAM, the machine must have at least 24 GB RAM to use the full performance of the GPUs.