* Simon Riggs: >> I think the best option is setitimer(), but it's not POSIX so >> platform support is going to be patchy. > > Don't understand that. I thought that was to do with alarms and > signals.
You could use it for sampling. Every few milliseconds, you record which code is executing (possibly using a global variable which is set and reset accordingly). But this might lead to tons of interrupted system calls, and not all systems mask them, so this might not be an option for the PostgreSQL code base. On the other hand, if performance in more recent Linux releases (from kernel.org) are acceptable, you should assume that the problem will eventually fix itself. FWIW, I see the 9x overhead on something that is close to 2.6.17 (on AMD64/Opteron), so this could be wishful thinking. 8-( -- Florian Weimer <[EMAIL PROTECTED]> BFK edv-consulting GmbH http://www.bfk.de/ Kriegsstraße 100 tel: +49-721-96201-1 D-76133 Karlsruhe fax: +49-721-96201-99 ---------------------------(end of broadcast)--------------------------- TIP 1: if posting/reading through Usenet, please send an appropriate subscribe-nomail command to [EMAIL PROTECTED] so that your message can get through to the mailing list cleanly
