the stress test was (simulatenously) :
dd if=/dev/hda5 of=/dev/null (5gb)
ping -f -s 1024 foo (from a other host on base-2 LAN)
make clean && make dep && make -j zImage && make modules (2.0.31)
plus your path you send me and
serial console path
make clean && make (ssh-1.2.20)
netscape communicator 4.03 pro (remote display)
w/out compling ssh everything was quite peacefull.. swap ussage low ..
load did not execd 20.. i think around 15 or so .. and it would not
increase...
staring compling ssh at the same time..
load increases ... goes up to 70.0 or so, and then it beings drecrease..
constantly .. even though really nothing changed and any of proceses
did not finish
the thing is that zombies being to appear .. but the odd thing is that
they also disappear as well (hmm wasn't that zombie can't 'quit' until its
parents quit?) .. but make does not complain about any errors (should it?)
but it was not given for me to finish the test .. the load went down up to
15.0 or so... but it was interrupted by
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
eth1: Tx request while isr active.
net dead.. the interrupts were probably overused by this mesg since the
serial console was kinda dead as well .. (but it did keep displaying it on
sceen) ... i was unable to sync so nothing got saved in syslog except what
was in scroll buffer of xterm)
the worst thing is that i'm not sure if I this is hardware or software
problem
anyways a dmesg output follows..
Console: 16 point font, 400 scans
Console: colour VGA+ 80x25, 1 virtual console (max 63)
pcibios_init : BIOS32 Service Directory structure at 0x000faf70
pcibios_init : BIOS32 Service Directory entry at 0xfb370
pcibios_init : PCI BIOS revision 2.10 entry at 0xfb3a0
Probing PCI hardware.
Calibrating delay loop.. ok - 149.50 BogoMIPS
Memory: 63296k/65536k available (620k kernel code, 384k reserved, 1236k
data)
This processor honours the WP bit even when in supervisor mode. Good.
Swansea University Computer Society NET3.035 for Linux 2.0
NET3: Unix domain sockets 0.13 for Linux NET3.035.
Swansea University Computer Society TCP/IP for NET3.034
IP Protocols: IGMP, ICMP, UDP, TCP
VFS: Diskquotas version dquot_5.6.0 initialized
Checking 386/387 coupling... Ok, fpu using exception 16 error reporting.
Checking 'hlt' instruction... Ok.
Linux version 2.0.31 (root@eax.student.umd.edu) (gcc version 2.7.2.1) #1 Sat Sep
6 22:22:23 EDT 1997
Starting kswapd v 1.4.2.2
Serial driver version 4.13 with no serial options enabled
tty00 at 0x03f8 (irq = 4) is a 16550A
tty01 at 0x02f8 (irq = 3) is a 16550A
Software Watchdog Timer: 0.04, timer margin: 60 sec
APM BIOS version 1.2 Flags 0x07 (Driver version 1.2)
Entry f000:804e cseg16 f000 dseg fdfc cseg len ef7f, dseg len 0
Connection version 1.1
AC on line, battery status unknown, battery life unknown
battery flag 0x80, battery life unknown
apm_bios: enable power management: Power management disabled
Real Time Clock Driver v1.07
Ramdisk driver initialized : 16 ramdisks of 4096K size
ide: i82371 PIIX (Triton) on PCI bus 0 function 57
ide0: BM-DMA at 0xf000-0xf007
ide1: BM-DMA at 0xf008-0xf00f
hda: Maxtor 87000D8, 6679MB w/256kB Cache, CHS=851/255/63, DMA
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Ethernet Bridge 002 for NET3.035 (Linux 2.0)
Partition check:
hda: hda1 hda2 hda3 hda4 < hda5 hda6 hda7 >
VFS: Mounted root (ext2 filesystem) readonly.
Adding Swap: 130748k swap-space (priority -1)
Swansea University Computer Society IPX 0.34 for NET3.035
IPX Portions Copyright (c) 1995 Caldera, Inc.
Appletalk 0.17 for Linux NET3.035
3c59x.c:v0.43 9/2/97 Donald Becker
http://cesdis.gsfc.nasa.gov/linux/drivers/vortex.html
loading device 'eth0'...
eth0: 3Com 3c590 Vortex 10Mbps at 0x6100, 00:a0:24:6b:3b:d3, IRQ 11
32K byte-wide RAM 1:1 Rx:Tx split, autoselect/10baseT interface.
eth0: Overriding PCI latency timer (CFLT) setting of 32, new value is 248.
3c503.c: Presently autoprobing (not recommended) for a single card.
loading device 'eth1'...
3c503.c:v1.10 9/23/93 Donald Becker (becker@cesdis.gsfc.nasa.gov)
eth1: 3c503 at i/o base 0x300, node 02 60 8c 4c f9 bd, using internal xcvr.
eth1: 3c503 - 8kB RAM, 8kB shared mem window at 0xdc000-0xddfff.
-Adam