Versions Compared

Key

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

...

  1. check the current transfer load on the gateways trough the grafana dashboard.

  2. If the troughput average is more than 22Gb/s (>90% of maximum network capacity) do not proceed

  3. For each host or batch of hosts that is currently in production use:

    1. run the following command. hostname_prefix is the part before .gridpp.rl.ac.uk, for example ceph-svc01

      Code Block
      bash blacklist.sh <hostname_prefix>
    2. wait till the traffic drops (usually 5 15 min).

    3. ssh into the host and run “reboot“

    4. wait for the host to come back (10-20min)

    5. check the systemd services xrootd@{unified,tpc} and cmsd@unified are running and active

    6. run

      Code Block
      bash unblacklist.sh <hostname_prefix>

...