Panics on busy server running CURRENT

Hi all,

On a IBM 345 dual xeon, I've got massive problems with stability.

Sometimes the box locks up on background fsck after a crash,
sometimes it panics with a page fault.

Does anybody of you has similar problems with CURRENT and
SMP on busy machines ?

This is still with HTT, SMP enabled and SCHED4BSD.
In the meanwhile I turned of HTT because someone told me on IRC
that my chipset w/HTT enabled does behave unstable:

> <ket_> mbr - i've had a LOT of people tell me the GC-HE w/HTT causes unknown
>  lockups, unreproducible errors, memory errors, and strange bus errors. on
>  multiple operating systems.

> <ket_> GC-HE itself is acknowledged to be a buggy chipset, they're up to
  something like rev8 on the silicon.

db>          where^M
Debugger(c0654981) at Debugger+0x46^M
__panic(c06543cd,252,c06543b5,c065438c,c06543f2) at __panic+0x13d^M
_mtx_lock_spin(c06a6cc0,0,0,0) at _mtx_lock_spin+0x8a^M
turnstile_claim(c76c52c0) at turnstile_claim+0x11c^M
_mtx_lock_sleep(c06a6d00,0,0,0) at _mtx_lock_sleep+0x44^M
vm_fault(c774584c,86c3000,1,0,c7773bd0) at vm_fault+0x182^M
trap_pfault(e92e5d48,1,86c300b,86c300b,0) at trap_pfault+0xfa^M
trap(2f,2f,2f,36b8,86c3000) at trap+0x1e2^M
calltrap() at calltrap+0x5^M
--- trap 0xc, eip = 0x284c6a20, esp = 0xbfbe5b00, ebp = 0xbfbe5b18 ---

Some of the processes might be interesting ...

 1722 c7bda370 e9457000 65534   707   707 0000100 [LOCK  Giant c76c52c0] perl
 1716 c746cdc0 e9138000 65534   707   707 0000100 [LOCK  Giant c76c52c0] perl
 1703 c7865000 e93bd000    0   724   724 0000100 [LOCK  Giant c76c52c0] sendmail
 1539 c798d898 e943d000    0   639   639 0000100 [LOCK  Giant c76c52c0] sendmail
  712 c78661b8 e93c7000    0     1    94 0000002 [LOCK  Giant c76c52c0] spamass-milter
   10 c3066000 e1308000    0     0     0 0000204 [SLPQ ktrace 0xc06a67d8][SLP] ktrace

Martin