lkml.org 
[lkml]   [2002]   [Aug]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Re: big IRQ latencies, was: <no subject>
Matti Aarnio <matti.aarnio@zmailer.org> schrieb am 25.08.02 15:18:07:
> On Sun, Aug 25, 2002 at 02:38:59PM +0200, joerg.beyer@email.de wrote:
> > Zwane Mwaikambo <zwane@linuxpower.ca> schrieb am 25.08.02 14:10:12:
> > > On Sun, 25 Aug 2002 joerg.beyer@email.de wrote:
> > ...
> > > That should fix your slowdown during untarring/disk access, as for your
> > > NIC problem looks like you might be having a receive FIFO overflow, so
> > > perhaps the card stops processing incoming packets? I have no clue,
> >
> > maybe this helps: outgoing transfer (from the laptop to some
> > other machine) is reasonable fast: I could copy gig's of data
> > away, but not to the machine. I asume sending away makes not
> > so heavy use of IRQ's, right?
>
> A laptop, you say ? And network reception is jamming while

yes a laptop.

> there is high disk-write activity ?

nope - no other disk activity except the scp I used to
copy a file over the net.

> /sbin/hdparam -v /dev/hda
>
> /dev/hda:
> multcount = 16 (on)
> I/O support = 1 (32-bit) <----- ??
> unmaskirq = 1 (on) <----- ??
> using_dma = 1 (on) <----- ??
> keepsettings = 1 (on) <----- ??
> nowerr = 0 (off)
> readonly = 0 (off)
> readahead = 8 (on)
>

I set the values as you suggested, but it made no difference:

joerg@laptop> scp othermachione:1gig_file /tmp

it take ~ 1/2 minute for 1 gig and gives a lot of errors
on the nic:

eth0 Protokoll:Ethernet Hardware Adresse 00:07:CA:00:AC:A3
inet Adresse:10.0.0.30 Bcast:10.255.255.255 Maske:255.0.0.0
UP BROADCAST NOTRAILERS RUNNING MULTICAST MTU:1500 Metric:1
RX packets:875 errors:6440 dropped:263 overruns:6440 frame:0
TX packets:897 errors:0 dropped:0 overruns:0 carrier:0
Kollisionen:0 Sendewarteschlangenlänge:100
RX bytes:1234333 (1.1 Mb) TX bytes:79498 (77.6 Kb)
Interrupt:10 Basisadresse:0xf000

along with > 300 entries in /var/log/messages like this:

kernel: eth0: Too much work at interrupt, IntrStatus=0x0040

could anybody explain to me, why there is "Too much work at interrupt"?
and what I could do about it?

Joerg

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:28    [W:0.027 / U:1.460 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site