Date: Sun, 24 Feb 2002 19:57:36 +0000 From: Andrew Mobbs <andrewm@chiark.greenend.org.uk> To: hackers@FreeBSD.org Subject: Re: Test patch for msync/object-flushing performance (for stable) Message-ID: <E16f4m8-0001YT-00@chiark.greenend.org.uk> In-Reply-To: <20020224114508.P15264-100000@patrocles.silby.com> References: <15481.61.57511.222531@chiark.greenend.org.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
In article <20020224114508.P15264-100000@patrocles.silby.com> you write: > >On Sun, 24 Feb 2002, Andrew Mobbs wrote: > >> vm.msync_flush_flags >> | 0 | 1 | 2 | 3 | >> -------+-------+-------+-------+-------| >> write | 519 | 517 | 1632 | 519 | >> sync | 2227 | 176 | 848 | 177 | > ^^^ >I don't get that one; any idea why bit 1 on for the first test performs so >differently from the other tests? Were these tests all run sequentially? >Maybe memory is becoming more fragmented as time goes on, causing that >optimization to not be able to work properly. I put that one down to other activity on the system, given the four other repeats with bit 1 set didn't show that. I tried to leave it as quiet as possible, but didn't bother disabling any cron jobs. Which is why I repeated each test 5 times. The test order was 0,1,2,3,0,1,2,3 &c. run sequentially. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E16f4m8-0001YT-00>