Hi hackers,

I have two SPARCstations; SS5 and SS10. Both are running NetBSD 3 with
jdc@'s raidframe patches(1*). The SS5 is UP, and stable. The SS10
however, is very unstable under high load, subject to hang and/or panic
without warning. Here's a backtrace(2*) of a panic I witnessed
yesterday (I've compiled in DDB):

---clip---
db{0}> bt
cpu_Debugger(0xf031bbc8, 0xf031d3d8, 0x1, 0x1244c34c, 0x100, 0xf0356800) at netbsd:pool_get+0x190
pool_get(0xf0391428, 0x0, 0x1000000, 0x20402a08, 0xefffc9b4, 0x0) at netbsd:pool_cache_get_paddr+0x138
pool_cache_get_paddr(0xf03910bc, 0x0, 0xf0d6e454, 0x20402a08, 0xefffca24, 0xefffca20) at netbsd:lance_get+0x148
lance_get(0xf0391000, 0x2470, 0x5b6, 0x8, 0x0, 0xc) at netbsd:lance_read+0x34
lance_read(0xf08eac00, 0x2470, 0xf08eac38, 0x8, 0xf3de6824, 0xf0bedaf0) at netbsd:am7990_rint+0x11c
am7990_rint(fuck these memory addresses) et netbsd:am7990_intr
am7990_intr() at netbsd:lsi64854_enet_intr
lsi6845_enet_intr() at netbsd:sparc_interrupt44c
---clap---

Above copied off VT220 screen manually so nevermind the typos and other 
bollocks. 

Also, trying to force a crashdump on the box does not work. Observe the
screenshots(3*). 

However, after compiling a UP kernel things seem to work just fine. I'm
typing this on the problematic box with UP kernel, network constantly
blowing ~220kB/sec down and CPU constantly between 60 and 100 percentage
use. Apart from a little sluggishness involvend with using mutt and vim
with syntax highlighting, the box seems to work fine. 

Here's also the dmesg(4*) from the box. It includes both dmesgs; with
SMP support in, and without. All help is appreciated. 

(1*) http://nlt.hole.fi/atte/sparc-raidroot/
(2*) http://nlt.hole.fi/atte/nbsd_31_sparc_ss10_bt.txt
(3*) http://nlt.hole.fi/atte/sparc-crashdump-fail/
(4*) http://nlt.hole.fi/atte/nbsd_31_sparc_ss10_dmesg.txt

-- 
Atte Peltomäki
http://kameli.org