[OpenVMS Alpha V7.3-2] System freezed

From: Peter 'EPLAN' LANGSTOEGER (peter_at_langstoeger.at)
Date: 08/31/04 

Date: Tue, 31 Aug 2004 14:25:28 +0000 (UTC)

Yesterday I had a nice suprise finding my PWS workstation frozen after
the weekend. AMDS (which I fortunately configured long ago) showed nothing
on limit (97% CPU, 82% Mem, 124 BIO/s which is quite usual) but DTSESSION
was MWAIT (RWMBX) and I wasn't able to login.

So I tried logging via SSH and later via LAT but these processes got
stuck too (COMO but with Prio 15/4 !).

I decided to free up some memory by killing some processes (APACHE, WBEM, ...)
via AMDS but it didn't help. Memory usage came down to 68% but the frozen
processes stayed COMO and even some of the killed processes went into COMO
or MWAIT instead of vanishing. Finally I 'fixed' (crashed) the node.

Anyone seen such a behaviour before ? Could a recent ECO have introduced it ?

For me it sounds like the SWAPPER bugfix description of VMS732_SYS-V0400
which is also mentioned in the VMS732_SYS-V0500. I haven't installed V5
yet but I have V4 of VMS732_SYS in. OTOH I haven't had my process count
or memory usage differently now, so why is the problem new for me. Which
ECO introduced it ?

TIA 

-- 
Peter "EPLAN" LANGSTOEGER
Network and OpenVMS system specialist
E-mail  peter@langstoeger.at
A-1030 VIENNA  AUSTRIA              I'm not a pessimist, I'm a realist