Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-5421

MGS and MDT with dual ib port

    XMLWordPrintable

Details

    • Task
    • Resolution: Unresolved
    • Critical
    • None
    • Lustre 2.5.2
    • None
    • Lustre 2.5.2, Cent OS 6.5, Dual IB port.
      DRBD, Heartbeat

    Description

      Dear Team,

      We are looking for HA in terms of IO node, IB port failure.

      In our setup
      IO1 Role MGS, MDT and OST
      IO2 Role MGS, MDT and OST

      2 IB switch independently connected with IO1 and IO2 server.

      IO1-ib0 192.168.2.101
      IO1-ib1 192.168.2.102
      IO2-ib0 192.168.3.101
      I02-ib1 192.168.3.102

      LNET options lnet networks=o2ib0(ib0),o2ib1(ib1)
      Lustre setup
      Prebuilt server rpm
      IO1 and IO2 servers would be on both core networks, o2ib0 and o2ib1

      ssh IO2 "mkfs.lustre --reformat --fsname=lustre --mdt --mgs --index=0 --failnode=192.168.3.101@o2ib1 --failnode=192.168.2.102@o2ib0 --failnode=192.168.3.102@o2ib1 /dev/drbd0"

      ssh IO2 "mkfs.lustre --reformat --fsname=lustre --ost --index=0 \
      --mgsnode=192.168.2.101@o2ib0 \
      --mgsnode=192.168.3.101@o2ib1 \
      --mgsnode=192.168.2.102@o2ib0 \
      --mgsnode=192.168.3.102@o2ib1 \
      --failnode=192.168.2.101@o2ib0 \
      --failnode=192.168.3.101@o2ib1 \
      /dev/mapper/ost-0"
      ssh IO2 "mount -t lustre /dev/mapper/ost-0 /OST0"
      ssh IO2 "mkfs.lustre --reformat --fsname=lustre --ost --index=1 \
      --mgsnode=192.168.2.101@o2ib0 \
      --mgsnode=192.168.3.101@o2ib1 \
      --mgsnode=192.168.2.102@o2ib0 \
      --mgsnode=192.168.3.102@o2ib1 \
      --failnode=192.168.2.101@o2ib0 \
      --failnode=192.168.3.101@o2ib1 \
      /dev/mapper/ost-1"
      ssh IO2 "mount -t lustre /dev/mapper/ost-1 /OST1"

      ssh IO2 "mkfs.lustre --reformat --fsname=lustre --ost --index=2 \
      --mgsnode=192.168.2.101@o2ib0 \
      --mgsnode=192.168.3.101@o2ib1 \
      --mgsnode=192.168.2.102@o2ib0 \
      --mgsnode=192.168.3.102@o2ib1 \
      --failnode=192.168.2.101@o2ib0 \
      --failnode=192.168.3.101@o2ib1 \
      /dev/mapper/ost-2"

      ssh IO2 "mount -t lustre /dev/mapper/ost-2 /OST2"

            1. The Failover will be IO2
              ssh IO1 "mkfs.lustre --reformat --fsname=lustre --ost --index=3 \
              --mgsnode=192.168.2.101@o2ib0 \
              --mgsnode=192.168.3.101@o2ib1 \
              --mgsnode=192.168.2.102@o2ib0 \
              --mgsnode=192.168.3.102@o2ib1 \
              --failnode=192.168.2.102@o2ib0 \
              --failnode=192.168.3.102@o2ib1 \
              /dev/mapper/ost-3"
              ssh IO1 "mount -t lustre /dev/mapper/ost-3 /OST3"

      ssh IO1 "mkfs.lustre --reformat --fsname=lustre --ost --index=4 \
      --mgsnode=192.168.2.101@o2ib0 \
      --mgsnode=192.168.3.101@o2ib1 \
      --mgsnode=192.168.2.102@o2ib0 \
      --mgsnode=192.168.3.102@o2ib1 \
      --failnode=192.168.2.102@o2ib0 \
      --failnode=192.168.3.102@o2ib1 \
      /dev/mapper/ost-4"
      ssh IO1 "mount -t lustre /dev/mapper/ost-4 /OST4"

      Is the above configuration is correct

      Thank You
      Atul Yadav

      Attachments

        Activity

          People

            wc-triage WC Triage
            atulyadavtech Atul Yadav
            Votes:
            0 Vote for this issue
            Watchers:
            2 Start watching this issue

            Dates

              Created:
              Updated: