If the system becomes uncontrollable, the last resort is to push the TOC button or run the TC command from the GSP. This will cause the system to generate a crash dump under /var/adm/crash. By analyzing this dump one can find out the cause of the system hang. You can get a basic crash dump analysis with the crashinfo tool, which is supplied by HP for a customer request. Now I will show you how to use this tool. Remember that with crashinfo you’ll only get a basic analysis, and by sending the crash dump to HP support they may get a much more advanced analysis.
“There are 2 versions of crashinfo – crashinfo-a-2.exe (64-bit PA2.0) and crashinfo-a-i.exe (IA64). The 64-bit PA2.0 version can be run on both PA and IA64 systems, and analyze both PA2.0 and IA64 crashdumps. The IA64 version will only run on IA64 systems, but can analyze crashdumps from both IA64 and PA2.0 systems. For performance reasons you may wish to use the IA64 version when running on IA64 systems.”
The easiest way to use this tool is to set your working directory to the latest crash dump dir and run it like this:
# cd /var/adm/crash/crash.0 # /tmp/crashinfo > crashinfo_analysis
You can also specify the dump directory from the command line:
# /tmp/crashinfo /var/adm/crash/crash.1
If crashinfo doesn’t find any dump data in your current directory and you didn’t supply any dump dir at the command line, crashinfo will fall back to the live vmunix kernel and its memory.
Source: HP crashinfo readme document
UPDATE: As of HP-UX 11iv3 the crashinfo is part of the SFM (System Fault Management) bundle, so you should find it here:
# ll /opt/sfm/tools/ total 4304 -r-xr-xr-x 1 root root 2192148 Dec 1 2006 crashinfo-a-i.exe -r--r--r-- 1 bin bin 1741 Dec 1 2006 crashinfo.README