[Linux-cluster] GFS umount hang after heavy read/write from NFS client

[孙俊伟]

Hello,all

I got messages as follows:
	
GFS: fsid=MyTest:vgtest.2: Unmount seems to be stalled. Dumping lock state...
Glock (2, 26)
  gl_flags =
  gl_count = 2
  gl_state = 0
  req_gh = no
  req_bh = no
  lvb_count = 0
  object = yes
  new_le = no
  incore_le = no
  reclaim = no
  aspace = 0
  ail_bufs = no
  Inode:
    num = 26/26
    type = 2
    i_count = 1
    i_flags =
    vnode = yes
Glock (5, 26)
  gl_flags =
  gl_count = 2
  gl_state = 3
  req_gh = no
  req_bh = no
  lvb_count = 0
  object = yes
  new_le = no
  incore_le = no
  reclaim = no
  aspace = no
  ail_bufs = no
  Holder
    owner = -1
    gh_state = 3
    gh_flags = 5 7
    error = 0
    gh_iflags = 1 6 7

What's the meaning ? GFS lock out,or NFS lock out?

And the "umount" process occupied 99.9% of CPU.
The status of the "umount" process was 
"29121 ?        R     74:08 umount /mnt/gfs/10".

I use the kernel 2.6.9.

Thanks for any reply!
Best regards!
Luckey