100% cpu utilization

Jeremy Allison jra at samba.org
Mon Nov 5 19:16:02 GMT 2001


On Mon, Nov 05, 2001 at 05:17:28PM -0500, David Collier-Brown wrote:
> Scott Moomaw wrote:
> > __fcntl(0xd,0x23,0x80474c4) + c
> > fcntl(0xd,0x23,0x80474c4,0x2c13c) + 1f
> > tdb_brlock(0x81ec8f8,0xa8,0x2,0x23,0x0,0xdfa65b2b,0xd,0x23) + 68
> > tdb_lock(0x81ec8f8,0x0,0x2,0x16,0x1,0x81e9088) + a2
> > tdb_chainlock(0x81ec8f8,0x81e8f70,0xc,0x810d0e8,0x81e8f70,0xc) + 2a
> > delete_fn(0x81ec8f8,0x81e8f70,0xc,0x81e8f7c,0x8a,0x804764c,0x2,0x83) + 3d
> > tdb_traverse(0x81ec8f8,0x810d0d0,0x804764c,0x806e467) + 9b
> > locking_end(0xdfa83000,0x80476c0,0x0,0x0,0x0,0x804768c,0x8047690,0x806da8b) + 47
> > exit_server(0x8144c80,0x0,0x0,0x0,0x0,0x8047abc) + 160
> > dflt_sig(0xf,0x0,0x80476c0) + 13
> > sigacthandler() + 25
> > dbg_mask(0x15,0x8047a3c,0x0,0x0,0x8047a34,0x5) + 2044f887
> > sys_select(0xd,0x8047a3c,0x8047a34,0x80a12f9) + c7
> > receive_message_or_smb(0x8210991,0x10040,0xea60,0x80a25e0) + 169
> > smbd_process(0xdfbed1e8,0x8047b10,0x8047bf8,0x210,0xdfa0d67f,0xdfa0d6a3,0xdfbe13
> > 7f,0x8047b10,0x8b,0x1,0x8047b48,0x806d94f,0x2,0x8047b54,0x8047b60,0x8144c30) + 11e
> > main(0x2,0x8047b54,0x8047b60) + 6d9
> 
> 	Ok Sambae, I don't know the tdb code, but fcntl 
> 	appears to be doing
> 
>         int fcntl(int fildes, int cmd, void *arg)
> 
> 	Therefor fd 13 is being operated on with
>         operation 35. This is F_SETLKW.
> 
> 	What in the tdb would spin on this fcntl?. Looking
> 	at the source, it seem to be used in tdb_brlock,
> 	which does fcntl(tdb->fd,lck_type,&fl)
> 	and only uses F_SETLKW and F_SETLK.

It's waiting to get access to a chain. It is in the locking_end()
function trying to enumerate the locking database and delete any
entries that are tagged with its own pid_t.

What is in the log for this smbd ? Why is it shutting down ?

Jeremy.




More information about the samba-technical mailing list