Re: [PERFORM] Tanking a server with shared memory

2004-09-05 Thread Tom Lane
Martin Foster <[EMAIL PROTECTED]> writes: > While I know this is a Perl issue, but figured I might be able to gain > some insight on how a server could drop without at least generating a > panic. Any ideas? The standard spelling for this is "kernel bug". Send a reproducible example to the Open

[PERFORM] Tanking a server with shared memory

2004-09-05 Thread Martin Foster
I have been experimenting with the 'IPC::Shareable' module under the native implementation of Perl 5 for OpenBSD 3.5. While it is not loaded by default it is a pure pure implementation. I have tested this module under two machines, one which used to run PostgreSQL and has a higher then normal