[Linux-cluster] GFS umount hang after heavy read/write from NFS client
孙俊伟
sunjw at onewaveinc.com
Mon Feb 28 08:37:03 UTC 2005
>> .concurrently read from NFS
>
>What do you mean by this?
My test program is something like iozone, but is multithreading.
On each thread, it reads one file with speed limit about 1MB/s.
And all threads start reading at the same time, so I refer it as concurrent read.
By the way, in spite of how I get it,
every time the umount hangs, I get the same message as:
Glock (2, 26) <<the same
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) <<the same
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
More information about the Linux-cluster
mailing list