On 11/3/05, Mike Gerdts <[EMAIL PROTECTED]> wrote: > The ugly part was getting time stamps for when the sample was taken > into the logs. It wasn't really that bad, just annoying that I > discovered it after collecting many days of logs. Now I timestamp > intervals into the log using the perl equivalent of "newtask -p > timestampproject /bin/true". > > In any case, Adrian's advice suggested that the exacct way may not be > such a bad way to go long term.
Just as a follow-up.... Since we talked about the timestamp problem on my blog about a year ago, it was fixed in Nevada, but has not yet been backported to S10 or S9. The engineer who worked on that bug left Sun, so exacct didn't get much attention since then. I'll get it fixed for you in S10U2 timeframe. The other problem (reporting RSS statistics) was fixed in time for S10 FCS. You can check out the history of exacct.c here: http://cvs.opensolaris.org/source/history/on/usr/src/uts/common/os/exacct.c - Andrei _______________________________________________ perf-discuss mailing list perf-discuss@opensolaris.org
