Messages in this thread | | | Date | Sat, 7 Mar 1998 22:35:10 -0800 | From | Bill Broadhurst <> | Subject | Process die under moderate load. v2.1.8x |
| |
For sometime now I've been seeing processes die when the machine is under a moderate load. 2.1.89 has lasted longer than the earlier kernels but it still won't get through a compile of perl 5.0 without having some of the processes (ld, nmake, various others) die. When one dies, it's only a matter of time until others follow. Most notably update. of course, when this happens the only thing to do is reboot.
The machine: Tysn Tomcat IV w/ dual P200's. Kernel 2.1.89 SMP with no other patches. SCSI subsystem: Buslogic 935 and 4 ultra drives, tape, and CDROM. 128M Dram + 239M swap.
One thing to note is that when a process dies, it has a disk busy and any other process that tries to access that disk for any reason also dies.
Never any log messages, never anything to point the finger at any sub-system.
Also, it may be noted that this happens with three machines. At first I thought it was only one machine but today I tried another machine for the long perl 5 compile and it died too. As did a third. All three have different m/b's, but all have 128MB of DRAM except one which has 64M. All are SMP kernels v2.1.89. All are SCSI subsystems (but one is an adaptec controller) with multiple disks.
Any thoughts as to where I go from here? Or what I have to do to fix this? If anything?
-bb
-- ---------------------------------------------------------------------- Dr. Bill Broadhurst | Independent contract Engineer. (619)296-3710 | BIOS, Firmware, & Diagnostics. bbroad@CX492564-a.dt1.sdca.home.com | Finger for PGP 5.0 public key. ----------------------------------------------------------------------
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |