Re: Houston, I think we have a problem

[Mike Galbraith <efault@gmx.de>]

[-- Attachment #1: Type: text/plain, Size: 1204 bytes --]

At 07:41 AM 4/27/2003 -0700, Martin J. Bligh wrote:
> > To reproduce this 100% of the time, simply compile virgin 2.5.68
> > up/preempt, reduce your ram to 128mb, and using gcc-2.95.3 as to not
> > overload the vm, run a make -j30 bzImage in an ext3 partition on a P3/500
> > single ide disk box.  No, you don't really need to meet all of those
> > restrictions... you'll see the problem on a big hairy chested box as
> > well, just not as bad as I see it on my little box.  The first symptom of
> > the problem you will notice is a complete lack of swap activity along
> > with highly improbable quantities of unused ram were all those hungry
> > cc1's getting regular CPU feedings.
>
>Yes, that's why I don't use ext3 ;-) It's known broken, akpm is fixing it.

He might be interested in the attached then.

(It illustrates the one wakeup thingie I'm muttering and mumbling about 
nicely too.  Both of the players are going to have 3 seconds to ruin 
everyone else's day.  This is why I turned the problem upside-down in my 
experiment... if your shell and it's kids aren't maxed out when this 
happens, interactivity turns el-stinko)

I'll go back to my corner now and play quietly ;-)

         -Mike 

[-- Attachment #2: xx.txt --]
[-- Type: text/plain, Size: 1934 bytes --]

6623:21 starved 1 secs by 6619:21 who last ran 2172 ticks ago.
semaphore downed at fs/namei.c:1249.

6623:20 starved 2 secs by 6619:21 who last ran 3172 ticks ago.
semaphore downed at fs/namei.c:1249.

6623:19 starved 3 secs by 6619:21 who last ran 4172 ticks ago.
semaphore downed at fs/namei.c:1249.

6623:18 starved 4 secs by 6619:21 who last ran 5172 ticks ago.
semaphore downed at fs/namei.c:1249.

6623:17 starved 5 secs by 6619:21 who last ran 6183 ticks ago.
semaphore downed at fs/namei.c:1249.

6623:16 starved 6 secs by 6619:21 who last ran 7203 ticks ago.
semaphore downed at fs/namei.c:1249.

6623:15 starved 7 secs by 6619:21 who last ran 8223 ticks ago.
as            D 00000286 4269393680  6619   6476                     (NOTLB)
Call Trace:
 [<c0116317>] sleep_on+0x5b/0x84
 [<c0115f90>] default_wake_function+0x0/0x1c
 [<c0182430>] start_this_handle+0x140/0x234
 [<c01825ff>] journal_start+0x93/0xc8
 [<c017d64a>] ext3_journal_start+0x2a/0x4c
 [<c017be4d>] ext3_create+0x31/0x198
 [<c015022d>] vfs_create+0xad/0xd4
 [<c01505eb>] open_namei+0x197/0x480
 [<c0142d26>] filp_open+0x3a/0x5c
 [<c014314f>] sys_open+0x37/0x74
 [<c0108ebb>] syscall_call+0x7/0xb

semaphore downed at fs/namei.c:1249.

6623:15 starved 8 secs by 6619:15 who last ran 547 ticks ago.
as            D 000BDE11 4269393680  6619   6476                     (NOTLB)
Call Trace:
 [<c011fd1a>] schedule_timeout+0x7e/0xa8
 [<c011fc8c>] process_timeout+0x0/0x10
 [<c0107d0a>] __down+0x9e/0x1a8
 [<c0115f90>] default_wake_function+0x0/0x1c
 [<c010802b>] __down_failed+0xb/0x14
 [<c01844ca>] .text.lock.transaction+0x5/0x15b
 [<c01825ff>] journal_start+0x93/0xc8
 [<c017d64a>] ext3_journal_start+0x2a/0x4c
 [<c017be4d>] ext3_create+0x31/0x198
 [<c015022d>] vfs_create+0xad/0xd4
 [<c01505eb>] open_namei+0x197/0x480
 [<c0142d26>] filp_open+0x3a/0x5c
 [<c014314f>] sys_open+0x37/0x74
 [<c0108ebb>] syscall_call+0x7/0xb

semaphore downed at fs/namei.c:1249.