1 |
Hi, Kyle. |
2 |
|
3 |
I have the same f***ing problem with 2.6.29 on Dual Pentium 3 Server |
4 |
with Intel Pro 100 driver unlikely tg3 driver (64bit PCI-X) |
5 |
I've waste 2 hours of my working time while diagnosing this problem. |
6 |
My solution is a rollback to the last 2.6.28 kernel too. |
7 |
|
8 |
KL> IRQ processing smells like the problem - trouble pops up with |
9 |
KL> NFS/ftp/ping/whatever, but only when I saturate the link. Back to |
10 |
KL> .28 until that "minor" bug is fixed. |
11 |
|
12 |
KL> Thanks. |
13 |
|
14 |
KL> On Wed, Apr 01, 2009 at 12:15:43PM +0000, Duncan wrote: |
15 |
>> Kyle Liddell <kyle@××××××××××××××××.net> posted |
16 |
>> 20090401060645.GA4182@athlon, excerpted below, on Wed, 01 Apr 2009 |
17 |
>> 02:06:45 -0400: |
18 |
>> |
19 |
>> > After upgrading the kernel from 2.6.28-gentoo-r3 to 2.6.29, I'm having a |
20 |
>> > weird problem: If I make "light" use of the network (ssh, email, http, |
21 |
>> > etc), no trouble. But, if I make "heavy" use of the network (say, |
22 |
>> > copying a few GB from a local NFS server to /dev/null), the network |
23 |
>> > interface stops working almost immediately. ifconfig, mii-tool, the |
24 |
>> > NIC's led, and the switch's LED all say that the link is still up. But, |
25 |
>> > all my connections time out, ping gets no replies, etc. (I'm using the |
26 |
>> > via-velocity driver for my motherboard's built-in 1GB NIC.) |
27 |
>> |
28 |
>> I'm unsure if your hardware is affected, but there's a known NAPI and |
29 |
>> interrupt related regression in 2.6.29. It was due to a commit trying to |
30 |
>> fix another bug just a few hours before release, and the discovery and |
31 |
>> subsequent bug trace was one of two subthreads quickly attached to Linus' |
32 |
>> 2.6.29 official announcement. (FWIW, the other subthread was even more |
33 |
>> fallout from the earlier ext4 data loss over improper shutdown, where |
34 |
>> ext3 was fine. That has and continues to generate HUGE subthreads all |
35 |
>> over the place, from the Ubuntu bug filing that was one of the first |
36 |
>> reports of it to LKML to /. to LWN. ext4 may have had the dev- removed |
37 |
>> from the name, but it's not exactly stable as this demonstrates, and |
38 |
>> what's worse, many people including Ted Tso seem to think the problem |
39 |
>> really is NOTABUG.) |
40 |
>> |
41 |
|
42 |
|
43 |
KL> __________ Информация от ESET Smart Security, версия базы данных |
44 |
KL> сигнатур вирусов 3984 (20090402) __________ |
45 |
|
46 |
KL> Сообщение проверено программой ESET Smart Security. |
47 |
|
48 |
KL> http://www.esetnod32.ru |
49 |
|
50 |
|
51 |
|
52 |
|
53 |
|
54 |
|
55 |
-- |
56 |
С уважением, |
57 |
Осипов mailto:demofly@××××.ru |