Icecast - Aug 2004 - ices crash

Dear List,

Running icecast 1.3.11, ices 0.2.2, 

I've been running six streams on one server, PII 333 mhz intel / linux
kernel 2.2.17 .  (icecast and six instances of ices, all are 32kb streams)

Most of the time things work but occasionally, the following happens and
one or more ices streams crash --

<p>Feb  6 14:26:47 bauhaus kernel: Unable to handle kernel paging request
at virtual address 00090020
Feb  6 14:26:47 bauhaus kernel: current->tss.cr3 = 01a61000, %%cr3 = 01a61000
Feb  6 14:26:47 bauhaus kernel: *pde = 00000000
Feb  6 14:26:47 bauhaus kernel: Oops: 0000
Feb  6 14:26:47 bauhaus kernel: CPU:    0
Feb  6 14:26:47 bauhaus kernel: EIP:    0010:[try_to_free_buffers+16/180]
Feb  6 14:26:47 bauhaus kernel: EFLAGS: 00010296
Feb  6 14:26:47 bauhaus kernel: eax: 00009470   ebx: c037fc18   ecx: 0000cbc0  
edx: 00000000
Feb  6 14:26:47 bauhaus kernel: esi: 00090000   edi: 00090000   ebp: c037fc18  
esp: c1c67e1c
Feb  6 14:26:47 bauhaus kernel: ds: 0018   es: 0018   ss: 0018
Feb  6 14:26:47 bauhaus kernel: Process ices (pid: 6071, process nr: 114,
stackpage=c1c67000)
Feb  6 14:26:47 bauhaus kernel: Stack: c1c66000 00000013 00000801 00000001
c17e2180 c011e102 c037fc18 00000013
Feb  6 14:26:47 bauhaus kernel:        00000013 00215000 0000000f 00000005
00000013 c1c66000 c1c67e5c c65a6600
Feb  6 14:26:47 bauhaus kernel:        00000014 c0122cb9 00000005 00000013
00000801 c1c67ea8 c1c66000 00000000
Feb  6 14:26:47 bauhaus kernel: Call Trace: [shrink_mmap+278/372]
[try_to_free_pages+57/164] [__get_free_pages+282/1116]
[try_to_read_ahead+47/272] [do_generic_file_read+640/1272] [unmap_fixup+291/304]
[generic_file_read+91/116]
Feb  6 14:26:47 bauhaus kernel:        [file_read_actor+0/80] [sys_read+178/208]
[common_interrupt+24/32] [error_code+45/64] [system_call+52/64]
[startup_32+43/285]
Feb  6 14:26:47 bauhaus kernel: Code: 83 7e 20 00 75 62 f6 46 18 46 75 5c 8b 76
14 39 fe 75 ed 90

<p>Would it matter that some of the playlists are located on SCSI rather
than IDE ?

Also - this is using mp3 not ogg.  lame is compiled in, but I am not 
re-encoding, load avg's have been in the 0.10 - 0.40 range, this is
also due to this being an X desktop box as well as icecast server.
(so load doesnt seem to be inordinately high with ices prior to these crashes)

<p>Thanks,

-Dave D

<p>--- >8 ----
List archives:  http://www.xiph.org/archives/
icecast project homepage: http://www.icecast.org/
To unsubscribe from this list, send a message to
'icecast-request@xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is
needed.
Unsubscribe messages sent to the list will be ignored/filtered.

> Feb  6 14:26:47 bauhaus kernel: Oops: 0000
This is not an ices problem. :)

A few things might be the cause:

1) buggy kernel (it happens).  upgrade to something newer and see if the
problem goes away.

2) heat.  scsi drives get hot.  i've seen this before when my machine
wasn't adequately cooled.  processors get hot.  Does this only happen if
it's been running for a while?

3) faulty hardware, usually memory (though could be a scsi controller or
a harddrive).  memtest86 usually will catch most memory errors and ram
is pretty cheap to replace these days.

<p>1 and 2 should be fairly easy to fix.  3 involves lots of diagnosis.

jack.

--- >8 ----
List archives:  http://www.xiph.org/archives/
icecast project homepage: http://www.icecast.org/
To unsubscribe from this list, send a message to
'icecast-request@xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is
needed.
Unsubscribe messages sent to the list will be ignored/filtered.