Date: Wed, 28 Sep 2005 20:06:30 +0530 From: Joseph Koshy <joseph.koshy@gmail.com> To: Niklas Sorensson <nik@cs.chalmers.se> Cc: freebsd-current@freebsd.org Subject: Re: hwpmc & sampling Message-ID: <84dead72050928073643bf3f8f@mail.gmail.com> In-Reply-To: <61020.83.226.117.75.1127916689.squirrel@webmail.chalmers.se> References: <52420.83.226.117.75.1127863485.squirrel@webmail.chalmers.se> <84dead72050928025251c032f7@mail.gmail.com> <61020.83.226.117.75.1127916689.squirrel@webmail.chalmers.se>
next in thread | previous in thread | raw e-mail | index | archive | help
ns> Seems wierd huh? I'd love to get this to work and would'nt ns> mind investigating the issue if you point me in the right ns> direction. Wierd. The output of 'time' that you posted showed low usr+sys numbers, but a large elapsed time. This would happen if the process is sleeping waiting for data or an external event. ns> real 0m24.728s ns> user 0m0.001s ns> sys 0m0.004s If this was a typo and the process was actually using the CPU for all 24.7 seconds, could you compare the gprof profiles you get from a pmcstat -S and a pmcstat -P run? -- FreeBSD Volunteer, http://people.freebsd.org/~jkoshy
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?84dead72050928073643bf3f8f>