Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-12284

Inactive OST doesn't block client without lazystatfs feature

    XMLWordPrintable

Details

    • Improvement
    • Resolution: Unresolved
    • Minor
    • None
    • Lustre 2.12.1
    • None
    • 9223372036854775807

    Description

      On a server, I umounted the OST, and mount the clietn using “nolazystatfs ” option, expecting df to be blocked. However:

      [root@el7-vm1 ~]# umount /mnt/lustre_ost0
      [root@el7-vm2 ~]# mount -t lustre 10.0.1.148@tcp:/global -o nolazystatfs /mnt/global/
      

      However, only the first "df" is blocked at all. Other "df" can be run without any block at all

      [root@server17-el7-vm2 ~]# df
      ^C^C
      [root@server17-el7-vm2 ~]# df
      Filesystem             1K-blocks    Used Available Use% Mounted on
      /dev/sda1               10189076 1632284   8016172  17% /
      devtmpfs                  931196       0    931196   0% /dev
      tmpfs                     941176       0    941176   0% /dev/shm
      tmpfs                     941176    8496    932680   1% /run
      tmpfs                     941176       0    941176   0% /sys/fs/cgroup
      tmpfs                     188236       0    188236   0% /run/user/0
      10.0.1.148@tcp:/global  14495148  107992  13551572   1% /mnt/global
      [root@server17-el7-vm2 ~]# df
      Filesystem             1K-blocks    Used Available Use% Mounted on
      /dev/sda1               10189076 1632284   8016172  17% /
      devtmpfs                  931196       0    931196   0% /dev
      tmpfs                     941176       0    941176   0% /dev/shm
      tmpfs                     941176    8496    932680   1% /run
      tmpfs                     941176       0    941176   0% /sys/fs/cgroup
      tmpfs                     188236       0    188236   0% /run/user/0
      10.0.1.148@tcp:/global  14495148  107992  13551572   1% /mnt/global
      [root@server17-el7-vm2 ~]# df
      Filesystem             1K-blocks    Used Available Use% Mounted on
      /dev/sda1               10189076 1632284   8016172  17% /
      devtmpfs                  931196       0    931196   0% /dev
      tmpfs                     941176       0    941176   0% /dev/shm
      tmpfs                     941176    8496    932680   1% /run
      tmpfs                     941176       0    941176   0% /sys/fs/cgroup
      tmpfs                     188236       0    188236   0% /run/user/0
      10.0.1.148@tcp:/global  14495148  107992  13551572   1% /mnt/global
      

      This might not a big deal because I guess almost nobody wants to be blocked when running "df". However, it is not the expected behavior anyway. Am I misunderstanding the behavior of no-lazystatfs?

      Attachments

        Activity

          People

            wc-triage WC Triage
            lixi_wc Li Xi
            Votes:
            0 Vote for this issue
            Watchers:
            2 Start watching this issue

            Dates

              Created:
              Updated: