Date: Wed, 28 Jan 2004 13:46:02 -0500 From: Don Bowman <don@sandvine.com> To: 'Robert Watson' <rwatson@freebsd.org>, Don Bowman <don@sandvine.com> Cc: "'freebsd-current@freebsd.org'" <freebsd-current@freebsd.org> Subject: RE: system call performance 4.x vs 5.x [and UP vs MP] Message-ID: <FE045D4D9F7AED4CBFF1B3B813C85337035E4704@mail.sandvine.com>
next in thread | raw e-mail | index | archive | help
> From: Robert Watson [mailto:rwatson@freebsd.org] > On Wed, 28 Jan 2004, Don Bowman wrote: > ... > > BTW, is your table below "4.7 UP vs 5.x MP"? I was left > unclear from the > title. Generally, the results I see suggest 5.x UP is > currently slower > than 4.x UP (something we should make back up over the next > three or four > months), but that 5.x MP is quite a bit faster than 4.x MP in many > interesting cases (i.e., network throughput, builds, etc). Especially > with the recent IPI changes and scheduling changes, I see > substantially > lower latency in scheduling various kernel threads on 5.x-MP > compared to > 4.x-MP, which means a lot more work gets done. Sorry, its MP versus MP, both on the same box. [i shouldn't have included the UP vs MP in the title, it confuses things, it was just an observation on 4.7 in isolation]. Thank you for the excellent answer. I will try the pipe() suggestion, and the netperf_socket branch. We are definitely seeing that e.g. bridging performance on 5.2 (MP) is very much worse than on 4.7 (MP). --don
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?FE045D4D9F7AED4CBFF1B3B813C85337035E4704>