Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  • ABI 1 (NMIS 8)
    • In omk/conf/opCommon.nmis:
      • omkd_workers is set at 10 by default. Try reducing this number to 2 and then restart the omkd service.
        If you THEN find YOU need more omkd_workers, increment this value by one and test again until you get to a suitable value for omkd_workers
      • /omkd/omkd_max_requests: 100 to 500 (start at 100 and increase from this value if needed)

  • ABI 2 (NMIS 9)
    • In omk/conf/opCommon.json:
      • omkd_workers is set at 10 by default. Try reducing this number to 2 and then restart the omkd service.
        If you THEN find YOU need more omkd_workers, increment this value by one and test again until you get to a suitable value for omkd_workers
      • /omkd/omkd_max_requests: 100 to 500 (start at 100 and increase from this value if needed)
    • in nmis9/conf/Config.nmis:
      • /system/nmisd_worker_max_cycles: 100

  • Consider installing and using zswap, with its default settings, provided the server has more than 1GB RAM:
    • Please read https://www.kernel.org/doc/html/latest/vm/zswap.html where it is provided that:
      • Overcommitted guests that share a common I/O resource can dramatically reduce their swap I/O pressure, avoiding heavy handed I/O throttling by the hypervisor.
        This allows more work to get done with less impact to the guest workload and guests sharing the I/O subsystem.
      • Users with SSDs as swap devices can extend the life of the device by drastically reducing life-shortening writes.
    • Please read Performance Analysis of Compressed Caching Technique where it is provided that
      • During the testing procedure LZO (default) algorithm was used for compression and maximum pool percent was set to 20; and.
      • Read the CONCLUSION of this paper for insights as to why zswap should not be used on a server with less than 1GB RAM.
      • See TABLE I. EFFICIENCY OF ZSWAP MODULE FOR VARIOUS SIZES OF RAM to estimate the extra headroom using zswap with default settings may provide for a server with a given RAM size:
        • From this paper we get that a server with 6GB RAM achieves above 68% efficiency, from which it can be interpreted that the 6GB RAM behaves as if it were 10GB RAM.almost 7GB RAM.
          • Calculated as follows:
            • 6GB RAM * 20% maximum pool percent = 1.25GB zswap pool
            • 1.25GB zswap pool * 69.5% efficiency = 0.86875GB  zswap gain
            • 0.86875GB  zswap gain + 6GB RAM = 6.86875GB RAM
        • Be aware though that this is no free lunch: Zswap will use cpu in achieving these gains, so monitoring cpu usage is essential when installing and enabling zswap.
        Read the conclusion of this paper for insights as to why zswap should not be used on a server with less than 1GB RAM
        • .
    • Don't be tempted to increase maximum pool percent from the default setting of 20: this will affect performance adversely.

...