[OpenAFS-devel] client freeze while writing large files
Ulrich Schwickerath
ulrich.schwickerath@iwr.fzk.de
Tue, 29 Jun 2004 09:08:24 +0200
Hi,
> Fileserver on same box?
yes, but this does not seem to matter. A client-only also freezes.
>
> does cmdebug (hungclienthostname) show any locks being held?
While writing (filesize still < 2G) I get:
[ulrich@hikiba1 ~]$ cmdebug hikiba1
** Cache entry @ 0xf9b992fc for 1.536870927.6.411 [fzk.de]
locks: (none_waiting, upgrade_locked(pid:2334 at:533))
432271360 bytes DV 914 refcnt 1
callback f6b51200 expires 1088505036
2 opens 2 writers
normal file
states (0x21), stat'd
After the file has grown >2GB, with a
ls -l /afs/fzk.de/scratch2
being stuck I get:
[ulrich@hikiba1 ~]$ cmdebug -long -servers hikiba1
Lock afs_xvcache status: (none_waiting)
Lock afs_xdcache status: (none_waiting)
Lock afs_xserver status: (none_waiting)
Lock afs_xvcb status: (none_waiting)
Lock afs_xbrs status: (none_waiting)
Lock afs_xcell status: (none_waiting)
Lock afs_xconn status: (none_waiting)
Lock afs_xuser status: (none_waiting)
Lock afs_xvolume status: (none_waiting)
Lock puttofile status: (none_waiting)
Lock afs_ftf status: (none_waiting)
Lock afs_xcbhash status: (none_waiting)
Lock afs_xaxs status: (none_waiting)
Lock afs_xinterface status: (none_waiting)
Lock afs_xosi status: (none_waiting)
Lock afs_xsrvAddr status: (none_waiting)
** Cache entry @ 0xf9b98000 for 1.536870912.1.1 [fzk.de]
2048 bytes DV 3 refcnt 1
callback f6b51200 expires 1088505036
0 opens 0 writers
volume root
states (0x1), stat'd
** Cache entry @ 0xf9b9821c for 1.536870912.2.202 [fzk.de]
11 bytes DV 1 refcnt 0
callback f6b51200 expires 1088505036
0 opens 0 writers
mount point
states (0x9), stat'd, mt pt valid
** Cache entry @ 0xf9b98438 for 1.536870915.1.1 [fzk.de]
2048 bytes DV 10 refcnt 1
callback f6b51200 expires 1088505036
0 opens 0 writers
volume root
states (0x1), stat'd
** Cache entry @ 0xf9b98a8c for 1.536870924.1.1 [fzk.de]
2048 bytes DV 47 refcnt 0
callback f6b51200 expires 1088455756
0 opens 0 writers
volume root
states (0x0)
** Cache entry @ 0xf9b98ca8 for 1.536870927.1.1 [fzk.de]
2048 bytes DV 19 refcnt 1
callback f6b51200 expires 1088505036
1 opens 0 writers
volume root
states (0x1), stat'd
** Cache entry @ 0xf9b990e0 for 1.536870927.2.409 [fzk.de]
2143875072 bytes DV 4580 refcnt 1
callback f6b51200 expires 1088492364
0 opens 0 writers
normal file
states (0x1), stat'd
** Cache entry @ 0xf9b98ec4 for 1.536870927.4.410 [fzk.de]
4287750144 bytes DV 9161 refcnt 1
callback f6b51200 expires 1088492364
0 opens 0 writers
normal file
states (0x1), stat'd
** Cache entry @ 0xf9b992fc for 1.536870927.6.411 [fzk.de]
2150301696 bytes DV 4580 refcnt 1
callback f6b51200 expires 1088505036
2 opens 2 writers
normal file
states (0x21), stat'd
** Cache entry @ 0xf9b98654 for 1.536870915.56.66208 [fzk.de]
10 bytes DV 1 refcnt 0
callback f6b51200 expires 1088443212
0 opens 0 writers
mount point
states (0x0)
** Cache entry @ 0xf9b98870 for 1.536870915.58.66209 [fzk.de]
10 bytes DV 1 refcnt 0
callback f6b51200 expires 1088505036
0 opens 0 writers
mount point
states (0x9), stat'd, mt pt valid
In that configuration the client runs on the same node as the server does. As
an additional piece of information: there is no kernel Ooops or anything else
in the syslog file.
Thank's,
Ulrich
--
__________________________________________
Dr. Ulrich Schwickerath
Forschungszentrum Karlsruhe
GRID-Computing and e-Science
Institut for Scientific Computing (IWR)
P.O. Box 36 40
76021 Karlsruhe, Germany
Tel: +49(7247)82-8607
Fax: +49(7247)82-4972
e-mail: ulrich.schwickerath@iwr.fzk.de
WWW: http://www.fzk.de
__________________________________________