Date: Sun, 29 Apr 2012 16:09:34 +1000 (EST) From: Ian Smith <smithi@nimnet.asn.au> To: Alexander Motin <mav@freebsd.org> Cc: Albert Shih <Albert.Shih@obspm.fr>, freebsd-stable@freebsd.org, Luigi Rizzo <rizzo@iet.unipi.it>, Oliver Pinter <oliver.pntr@gmail.com> Subject: Re: High load event idl. Message-ID: <20120429155512.M91148@sola.nimnet.asn.au> In-Reply-To: <4F9CCEF2.6050609@FreeBSD.org> References: <20120427203013.GB60961@pcjas.obspm.fr> <CAPjTQNFsHZQLp8oMwhjkAWLnYZ5mPv9kr9=X5GhqHqExoHM0yw@mail.gmail.com> <20120427213459.GA61125@pcjas.obspm.fr> <4F9B946D.3030607@FreeBSD.org> <CAPjTQNGts290DyjORNfir8_rZ5S_vdog%2BJMEBA9mc2vJhUa=jg@mail.gmail.com> <4F9CCEF2.6050609@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. --0-553176730-1335678991=:91148 Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1 Content-Transfer-Encoding: 8BIT Content-ID: <20120429155718.B91148@sola.nimnet.asn.au> On Sun, 29 Apr 2012 08:17:38 +0300, Alexander Motin wrote: > On 04/29/12 01:53, Oliver Pinter wrote: > > Attached the ktr file. This is on core2duo P9400 cpu ( > > smbios.system.product="HP ProBook 5310m (WD792EA#ABU)" ). The workload > > is only a single user boost: sh + top running, but the load average is > > near 0.5. > > ktr shows no real load there. But it shows that you are using dummynet, that > schedules its runs on every hardclock tick. I believe that load you see is > the result or synchronization between dummynet calls and loadvg sampling, > both of which called from hardclock. I think removing dummynet from equation, > should hide this problem and also reduce you laptops power consumption. > > What's about fixing this, it is loadavg sampling algorithm that should be > changed. Fixing dummynet to not run on every hardclock tick would also be > great. Wading in out of my depth, and copying Luigi in case he misses it .. but even back in the olden days when HZ defaulted to 100, one was advised to use HZ >= 1000 for smooth dummynet traffic shaping dispatch scheduling. I wonder, with the newer clocks and timers, whether there is another clock that could be used for dummynet scheduling, that would not have this effect (even if largely cosmetic?) on load average calculation? cheers, Ian > > On 4/28/12, Alexander Motin<mav@freebsd.org> wrote: > > > On 04/28/12 00:34, Albert Shih wrote: > > > > Le 27/04/2012 ? 22:45:40+0200, Oliver Pinter a écrit > > > > > > I'm running 9-stable on all my computer. (csup yesterday). > > > > > > > > > > > > On my desktop everything is fine. But I've two laptop, (both are > > > > > > Dell). > > > > > > On > > > > > > both latptop I've problem about the load, event when I do nothing I > > > > > > got > > > > > > a > > > > > > load between 0.5-1. > > > > > > > > > > > > Here the result of a «top» on the laptop : > > > > > > > > > > > > last pid: 2434; load averages: 0.63, 0.67, 0.59 up 0+00:23:59 > > > > > > 22:25:29 > > > > > > 57 processes: 3 running, 54 sleeping > > > > > > CPU: 2.7% user, 0.0% nice, 3.7% system, 1.4% interrupt, 92.2% > > > > > > idle > > > > > > Mem: 89M Active, 92M Inact, 198M Wired, 13M Cache, 100M Buf, 3529M > > > > > > Free > > > > > > Swap: 4096M Total, 4096M Free > > > > > > > > > > > > Here on the desktop : > > > > > > > > > > > > last pid: 61010; load averages: 0.00, 0.00, 0.00 up 2+11:02:42 > > > > > > 22:29:08 > > > > > > 126 processes: 1 running, 125 sleeping > > > > > > CPU: % user, % nice, % system, % interrupt, % > > > > > > idle > > > > > > Mem: 803M Active, 2874M Inact, 1901M Wired, 112M Cache, 620M Buf, > > > > > > 202M > > > > > > Free > > > > > > Swap: 6144M Total, 36M Used, 6107M Free > > > > > > > > > > > > > > > > http://lists.freebsd.org/pipermail/freebsd-bugs/2012-April/048213.html > > > > > > > > What I understand of your message (I'm definitvly not a dev) is that's > > > > only > > > > a little problem of accounting. > > > > > > > > I'm not absolute sure of that because my laptop fan never stop... > > > > > > > > If you want any more information... > > > > > > Definitely, because here I don't see much. > > > > > > Generally, all CPU loads and load averages now calculated via sampling, > > > so theoretically with spiky load numbers may vary for many reasons. I > > > would start from collecting information about running processes. To find > > > fast switching processes that could hide from accounting try `top -SH -m > > > io -o vcsw`. To get more information about scheduler work, use > > > /usr/src/tools/sched/schedgraph.py (instruction inside it). > > > > > > -- > > > Alexander Motin --0-553176730-1335678991=:91148--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20120429155512.M91148>