Optimizing GPU resource metric collection

LSF optimizes resource metric collection to improve LSF performance.

Note: Optimized GPU resource metric collection is now enabled and fixed at LSF_GPU_RESOURCE_IGNORE=Y.

The mbatchd does not collect GPU resource information from the management host LIM. This means that the lsload -s, lsload -l, and bhosts -l commands, which display LSF resources, no longer display information about GPU resources. That is, this option does not display gpu_<num>n resources. This improves LSF response time because there are fewer LSF resources to manage and display.

In addition, all built-in GPU resources (gpu_<num>n) are completely removed from the management host LIM. LSF uses a different method for the management host LIM and server host LIMs to collect GPU information. This further improves performance by having fewer built-in LSF resources.

Note:
  1. If you are using LSF RTM, Version 10.2 Fix Pack 11 or later, you can configure LSF_GPU_RESOURCE_IGNORE to either Y or N.
  2. If you are using LSF RTM, Version 10.2 Fix Pack 1 or earlier, configure LSF_GPU_RESOURCE_IGNORE to N.