Date: Sun, 28 Nov 2004 09:40:30 +0900 From: Rob <spamrefuse@yahoo.com> To: freebsd-stable@freebsd.org Subject: Re: make -j$n buildworld : use of -j investigated Message-ID: <41A91E7E.8050409@yahoo.com> In-Reply-To: <200411270903.iAR93Aao024219@moon.behrens> References: <200411270903.iAR93Aao024219@moon.behrens>
next in thread | previous in thread | raw e-mail | index | archive | help
Frank Behrens wrote: > I read this thread with interest and saw the question, how the system > wil behave with hyperthreading. Should I not benchmark my system? > here you have the results. The interpretation is left to the experts. > > IMHO HT is not as useless as expected. :-) > > I did not switch off SMP with sysctl, but used an extra UP Kernel to > allow some optimizations during compile. But I don't know if there > are any.. > > Hardware is > CPU: Intel(R) Pentium(R) 4 CPU 2.80GHz (2798.66-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0xf33 Stepping = 3 > Hyperthreading: 2 logical CPUs > real memory = 1072889856 (1023 MB) > avail memory = 1040453632 (992 MB) According to my formula: time(minutes) = 1e5 / ( speed(MHz) * nproc ) and taking nproc = 1, this results in time = 1e5 / 2798.66 = 36 minutes Quite accurate for your system as well. At least this formula gives a resonable estimate about the compile time. Apparently HT does not help much, since with SMP kernel, times do not get any close to 36/2 = 18 minutes. However, there is a slight improvement from -j1 to -j2 with SMP. I myself have not yet tested HT systems. Rob.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?41A91E7E.8050409>