I run a highly frequented web server (>10 hits/second) and got big troubles with
a kernel oops which appeared in 2.0.33 and .34. The oops seems only to be
triggered under high load. When the httpd is idle no oops happen.
"dmesg" gives me this (if the machine does not crash):
------------------------------
general protection: 0000
CPU: 0
EIP: 0010:[<00147534>]
EFLAGS: 00010213
eax: dcf91923 ebx: 00000000 ecx: 03c26c30 edx: f000f84d
esi: 03c26ccc edi: 000001a7 ebp: 03c26c0c esp: 03592ee8
ds: 0018 es: 0018 fs: 002b gs: 002b ss: 0018
Process httpd.fnet (pid: 2672, process nr: 52, stackpage=03592000)
Stack: 03c26c0c 03592f7c 00000000 00000000 101dd9d6 03c26c30 00000000 000001a7
02f3a414 00f03148 001ed07c 00151d9e 03c26c0c 03592f78 00000e59 00000000
00000000 03592f7c 00001000 00f03100 080f1a04 00f03190 00137eaf 00f03190
Call Trace: [<00151d9e>] [<00137eaf>] [<00123038>] [<0010a5d2>]
Code: 8a 40 0d a8 02 74 04 ff 4c 24 10 8b 7c 24 10 39 7b 30 0f 87
------------------------------
"ksymoops /System.map < oops.dmesg" gives me this answer:
------------------------------
Using `/System.map' to map addresses to symbols.
>>EIP: 147534 <tcp_recvmsg+170/40c>
Trace: 151d9e <inet_recvmsg+72/88>
Trace: 137eaf <sock_read+ab/c0>
Trace: 123038 <sys_read+c0/e8>
Trace: 10a5d2 <system_call+52/80>
Code: 147534 <tcp_recvmsg+170/40c>
------------------------------
If you need any more information I'd gladly answer any question. :-)
Any help is greatly appreciated.
Harry
-------------------------------------------------------------------
PGP fingerprint: B9 EE 83 0C 1F 48 54 50 9F A7 7A 00 6C 94 36 02
PGP public key available by fingering harry@nero.respublica.de
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html