| Title: | + OpenVMS Clusters - The best clusters in the world! + |
| Notice: | This conference is COMPANY CONFIDENTIAL. See #1.3 |
| Moderator: | PROXY::MOORE |
| Created: | Fri Aug 26 1988 |
| Last Modified: | Fri Jun 06 1997 |
| Last Successful Update: | Fri Jun 06 1997 |
| Number of topics: | 5320 |
| Total number of notes: | 23384 |
| T.R | Title | User | Personal Name | Date | Lines |
|---|---|---|---|---|---|
| 5216.1 | UTRTSC::jvdbu.uto.dec.com::JurVanDerBurg | Change mode to Panic! | Fri Jan 24 1997 01:05 | 7 | |
> >Unavail station buffs 82 Excessive collisions 0 Does this machine run Pathworks? It looks like it just spent too much time at a high ipl, which may be caused by many things. Jur. | |||||
| 5216.2 | How to check what is in high IPL? | VAXRIO::MAURO | Fri Jan 24 1997 06:32 | 12 | |
Dear Jur,
the system hasn't Pathworks. This cluster basicly runs a process
control application (real-time) written in C. It also has installed
UCX, DECnet IV, Bookbrowser, Volshadow and Fortran.
I have two crash dumps, one with the system hung (.0) e other with the
application hung. Could you give or tell where to get tips in how to
check who is executing in high IPL, analyzing the crash? It's a ASRV
1000 system.
Thanks, Mauro.
| |||||
| 5216.3 | UTRTSC::jvdbu.uto.dec.com::JurVanDerBurg | Change mode to Panic! | Fri Jan 24 1997 07:40 | 9 | |
Most of the times when something has hung for a long time at high ipl you won't find a trace in the dump. At the moment the hang is over the system comes back to life, sess it's othwer cluster members again and will be forced out of the cluster because it's been away too long. Sometimes you can find some evidence in nonpaged pool. Jur. | |||||