-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1
Hi,
This is on a new HP Proliant DL 320 box, on which I've installed Red Hat 9 plus the latest updates. gcc -v shows:
gcc version 3.2.2 20030222 (Red Hat Linux 3.2.2-5)
(Single) CPU is a hyperthreading-disabled Pentium 4, 2.66GHz. Output of lspci is below. There's only a single non-raided IDE hard drive in the box. Kernel is configured for 4GB memory (there'e 1152MB in the box)
00:00.0 Host bridge: ServerWorks GCNB-LE Host Bridge (rev 32)
00:00.1 Host bridge: ServerWorks GCNB-LE Host Bridge
00:02.0 RAID bus controller: CMD Technology Inc PCI0649 (rev 02)
00:03.0 VGA compatible controller: ATI Technologies Inc Rage XL (rev 27)
00:04.0 System peripheral: Compaq Computer Corporation Advanced System Management Controller
00:05.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5702 Gigabit Ethernet (rev 02)
00:06.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5702 Gigabit Ethernet (rev 02)
00:0f.0 ISA bridge: ServerWorks CSB6 South Bridge (rev a0)
00:0f.1 IDE interface: ServerWorks CSB6 RAID/IDE Controller (rev a0)
00:0f.2 USB Controller: ServerWorks CSB6 OHCI USB Controller (rev 05)
00:0f.3 Host bridge: ServerWorks GCLE-2 Host Bridge
ethtool run on eth0 (the only active interface) shows:
Settings for eth0: Supported ports: [ MII ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Half 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Half 1000baseT/Full Advertised auto-negotiation: Yes Speed: 100Mb/s Duplex: Half Port: Twisted Pair PHYAD: 1 Transceiver: internal Auto-negotiation: on Supports Wake-on: g Wake-on: d Current message level: 0x000000ff (255) Link detected: yes
The machine locks up hard when doing a large (> few hundred MB) rsync copy from another machine. Most occasions, no oops is displayed/logged, but after a few goes. I managed trigger one which is ksymoops-ed below. Note this was copied by hand.
I've tried with and without apic with no joy. memtest runs show zero errors. The latest Red Hat kernels lock up in the same way, but have another bug (in RH bugzilla) which prevent use here.
Strangely, an indentical machine, configured the same way, has not yet displayed this problem.
Cheers,
Chris.
skput:over c01a41e0:29186 put 29186 dev:eth0kernel BUG at skbuff.c:92! Invalid Operand: 0000 CPU: 0 EIP: 0010:[<c01c8e9b>] Not tainted Using defaults from ksymoops -t elf32-i386 -a i386 EFLAGS: 00010282 eax: 0000002d ebx: 00007202 ecx: c0256000 edx: f7467f7c esi: f74dc080 edi: 00000000 ebp: f74ef660 esp: c0257ed4 Stack: c0232220 c01a41e0 00007202 00007202 c1de5400 c01a41ec f74dc080 00007202 c01a41e0 002ab478 00007206 c1de5594 00007202 00000000 000003b5 002ab3b3 00010000 00000040 c1de5560 00000292 c1de5400 c01a435b c1de5560 00000040 Call Trace: [<c01a41e0>] [<c01a41ec>] [<c01a41e0>] [<c01a435b>] [<c01cd87a>] [<c011d225>] [<c0108bce>] [<c0105360>] [<c010b238>] [<c0105360>] [<c0105383>] [<c0105412>] [<c0105000>] Code: 0f 0b 5c 00 df 14 23 c0 83 c4 14 c3 89 f6 8d bc 27 00 00 00
>>EIP; c01c8e9b <skb_over_panic+3b/50> <=====
>>ecx; c0256000 <init_task_union+0/2000> >>edx; f7467f7c <_end+371993a4/38553488> >>esi; f74dc080 <_end+3720d4a8/38553488> >>ebp; f74ef660 <_end+37220a88/38553488> >>esp; c0257ed4 <init_task_union+1ed4/2000>
Trace; c01a41e0 <tg3_rx+2c0/3d0> Trace; c01a41ec <tg3_rx+2cc/3d0> Trace; c01a41e0 <tg3_rx+2c0/3d0> Trace; c01a435b <tg3_poll+6b/100> Trace; c01cd87a <net_rx_action+6a/100> Trace; c011d225 <do_softirq+95/a0> Trace; c0108bce <do_IRQ+9e/a0> Trace; c0105360 <default_idle+0/40> Trace; c010b238 <call_do_IRQ+5/d> Trace; c0105360 <default_idle+0/40> Trace; c0105383 <default_idle+23/40> Trace; c0105412 <cpu_idle+52/70> Trace; c0105000 <_stext+0/0>
Code; c01c8e9b <skb_over_panic+3b/50> 00000000 <_EIP>: Code; c01c8e9b <skb_over_panic+3b/50> <===== 0: 0f 0b ud2a <===== Code; c01c8e9d <skb_over_panic+3d/50> 2: 5c pop %esp Code; c01c8e9e <skb_over_panic+3e/50> 3: 00 df add %bl,%bh Code; c01c8ea0 <skb_over_panic+40/50> 5: 14 23 adc $0x23,%al Code; c01c8ea2 <skb_over_panic+42/50> 7: c0 83 c4 14 c3 89 f6 rolb $0xf6,0x89c314c4(%ebx) Code; c01c8ea9 <skb_over_panic+49/50> e: 8d bc 27 00 00 00 00 lea 0x0(%edi,1),%edi
<0>Kernel panic: Aiee, killing interrupt handler!
-----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
iD8DBQE/k78y6jnoXJ/rdIERAnLIAKCy4Aopmjng/l8KapQlAoPhOAjftwCguJ0G vfP4PJW2PMzDZ2srjjrmBmY= =XpJk -----END PGP SIGNATURE-----
- : send the line "unsubscribe linux-net" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
