Zwane Mwaikambo <[email protected]> schrieb am 25.08.02 14:10:12:
> On Sun, 25 Aug 2002 [email protected] 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?
does this help?
Joerg
ps: sorry for the missing subjectline
On Sun, Aug 25, 2002 at 02:38:59PM +0200, [email protected] wrote:
> Zwane Mwaikambo <[email protected]> schrieb am 25.08.02 14:10:12:
> > On Sun, 25 Aug 2002 [email protected] 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
there is high disk-write activity ?
/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)
> does this help?
> Joerg
>
> ps: sorry for the missing subjectline
/Matti Aarnio
Matti Aarnio <[email protected]> schrieb am 25.08.02 15:18:07:
> On Sun, Aug 25, 2002 at 02:38:59PM +0200, [email protected] wrote:
> > Zwane Mwaikambo <[email protected]> schrieb am 25.08.02 14:10:12:
> > > On Sun, 25 Aug 2002 [email protected] 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 Sendewarteschlangenl?nge: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