Date: Sat, 6 Oct 2007 23:01:03 -0500 From: "Christian S.J. Peron" <csjp@FreeBSD.org> To: Katsuji Ishikawa <k.ishish@gmail.com> Cc: freebsd-current@freebsd.org Subject: Re: heavy network load Message-ID: <20071007040103.GA58108@sub.vaned.net> In-Reply-To: <caa84c540710052249y402c7196x1adfb777ecaf97a@mail.gmail.com> References: <caa84c540710052249y402c7196x1adfb777ecaf97a@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--T4sUOijqQbZv57TR Content-Type: text/plain; charset=us-ascii Content-Disposition: inline The original author of the scheduler has come up with this patch which should fix the issue. Please test the attached patch. On Sat, Oct 06, 2007 at 02:49:01PM +0900, Katsuji Ishikawa wrote: > Hi . > I use -CURRENT on Parallels Desktop(Mac OS X). It works very fine. > But today I csup'ed and installed these. After that, I encountered > network problem.. > > > Details: > > Host: Parallels Desktop (Mac OS X) , 192.168.0.3 > Guest: FreeBSD-CURRENT , 192.168.0.6 > > before (Old current) > katsuji@hexley% ping 192.168.0.6 > PING 192.168.0.6 (192.168.0.6): 56 data bytes > 64 bytes from 192.168.0.6: icmp_seq=0 ttl=64 time=0.462 ms > 64 bytes from 192.168.0.6: icmp_seq=1 ttl=64 time=0.623 ms > 64 bytes from 192.168.0.6: icmp_seq=2 ttl=64 time=0.497 ms > 64 bytes from 192.168.0.6: icmp_seq=3 ttl=64 time=0.571 ms > 64 bytes from 192.168.0.6: icmp_seq=4 ttl=64 time=0.610 ms > 64 bytes from 192.168.0.6: icmp_seq=5 ttl=64 time=0.510 ms > ^C > --- 192.168.0.6 ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max/stddev = 0.462/0.545/0.623/0.060 ms > > > after (csuped today, occured packet loss...) > katsuji@hexley% ping 192.168.0.6 > PING 192.168.0.6 (192.168.0.6): 56 data bytes > 64 bytes from 192.168.0.6: icmp_seq=0 ttl=64 time=4397.146 ms > 64 bytes from 192.168.0.6: icmp_seq=1 ttl=64 time=3397.082 ms > 64 bytes from 192.168.0.6: icmp_seq=2 ttl=64 time=2397.021 ms > 64 bytes from 192.168.0.6: icmp_seq=3 ttl=64 time=1395.493 ms > 64 bytes from 192.168.0.6: icmp_seq=4 ttl=64 time=393.692 ms > ^C > --- 192.168.0.6 ping statistics --- > 11 packets transmitted, 5 packets received, 54% packet loss > round-trip min/avg/max/stddev = 393.692/2396.087/4397.146/1415.415 ms > > > kernel configuration: > > katsuji@seven% cat ULE3 [/sys/i386/conf] > include GENERIC > ident ULE3 > > nooptions SCHED_4BSD > options SCHED_ULE > > > Have you any good ideas? > > Regards, > > -- > Katsuji ISHIKAWA <k.ishish@gmail.com> > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" -- Christian S.J. Peron csjp@FreeBSD.ORG FreeBSD Committer --T4sUOijqQbZv57TR Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="sched_ule.c.diff" ? change.diff ? d ? kern_lockf.1182548846.diff ? lockf.diff ? lockf_restrict.1183833125.diff ? sched_smp.c ? sched_ule.c.diff Index: sched_ule.c =================================================================== RCS file: /home/ncvs/src/sys/kern/sched_ule.c,v retrieving revision 1.212 diff -u -r1.212 sched_ule.c --- sched_ule.c 2 Oct 2007 01:30:18 -0000 1.212 +++ sched_ule.c 7 Oct 2007 04:01:20 -0000 @@ -743,6 +743,9 @@ int load; int cpu; + if (!smp_started) + return (1); + KASSERT(steal_thresh != 0, ("steal_thresh == 0")); /* We don't want to be preempted while we're iterating over tdqs */ spinlock_enter(); tdg = tdq->tdq_group; --T4sUOijqQbZv57TR--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20071007040103.GA58108>