From owner-freebsd-stable@FreeBSD.ORG Wed Aug 20 16:22:37 2014 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id DAFF2322 for ; Wed, 20 Aug 2014 16:22:36 +0000 (UTC) Received: from mail.intermedix.com (mail.epbs.com [66.210.191.9]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "Barracuda/emailAddress=sales@barracuda.com", Issuer "Barracuda/emailAddress=sales@barracuda.com" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 988213452 for ; Wed, 20 Aug 2014 16:22:36 +0000 (UTC) X-ASG-Debug-ID: 1408551755-049956325c1f9970001-BIHDGU Received: from mailgate00.corp.okcyok1.priv.intermedix.com (mailgate00.epbs.com [10.130.4.34]) by mail.intermedix.com with ESMTP id q8AHdssRKgO96lgi; Wed, 20 Aug 2014 11:22:35 -0500 (CDT) X-Barracuda-Envelope-From: Steve.Polyack@intermedix.com X-ASG-Whitelist: Client X-WSS-ID: 0NAM5HK-01-VKD-02 X-M-MSG: Received: from exchange01.epbs.com (exchange01.okcyok0.priv.intermedix.com [192.168.25.157]) (using TLSv1 with cipher RC4-MD5 (128/128 bits)) (No client certificate requested) by mailgate00.corp.okcyok1.priv.intermedix.com (Postfix) with ESMTPS id 2027258008; Wed, 20 Aug 2014 11:22:32 -0500 (CDT) Received: from EXCHANGE03.epbs.com ([0000:0000:0000:0000:0000:0000:0.0.0.1]) by exchange01.epbs.com ([192.168.25.157]) with mapi; Wed, 20 Aug 2014 11:22:35 -0500 From: "Polyack, Steve" To: Alan Cox , "freebsd-stable@freebsd.org" Date: Wed, 20 Aug 2014 11:22:33 -0500 Subject: RE: vmdaemon CPU usage and poor performance in 10.0-RELEASE Thread-Topic: vmdaemon CPU usage and poor performance in 10.0-RELEASE X-ASG-Orig-Subj: RE: vmdaemon CPU usage and poor performance in 10.0-RELEASE Thread-Index: Ac+8kR5OBWGqmcS0TImy3357pYMOBgAAbPNg Message-ID: <4D557EC7CC2A544AA7C1A3B9CBA2B3672609CF33F6@exchange03.epbs.com> References: <4D557EC7CC2A544AA7C1A3B9CBA2B36726098846B4@exchange03.epbs.com> <20140813152522.GI9400@home.opsec.eu> <4D557EC7CC2A544AA7C1A3B9CBA2B36726098847AF@exchange03.epbs.com> <4D557EC7CC2A544AA7C1A3B9CBA2B3672609BBA3C4@exchange03.epbs.com> <53F24E5B.1010809@rice.edu> <4D557EC7CC2A544AA7C1A3B9CBA2B3672609BBA64F@exchange03.epbs.com> <53F2790C.20703@rice.edu> <4D557EC7CC2A544AA7C1A3B9CBA2B3672609CF28E5@exchange03.epbs.com> <4D557EC7CC2A544AA7C1A3B9CBA2B3672609CF2F8F@exchange03.epbs.com> <4D557EC7CC2A544AA7C1A3B9CBA2B3672609CF31F0@exchange03.epbs.com> <53F4C4C2.1030109@rice.edu> <4D557EC7CC2A544AA7C1A3B9CBA2B3672609CF335D@exchange03.epbs.com> <53F4C82E.5000900@rice.edu> In-Reply-To: <53F4C82E.5000900@rice.edu> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: en-US Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-Barracuda-Connect: mailgate00.epbs.com[10.130.4.34] X-Barracuda-Start-Time: 1408551755 X-Barracuda-URL: http://192.168.25.21:8000/cgi-mod/mark.cgi X-Virus-Scanned: by bsmtpd at intermedix.com X-Barracuda-BRTS-Status: 1 X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 20 Aug 2014 16:22:37 -0000 > -----Original Message----- > From: Alan Cox [mailto:alc@rice.edu] > Sent: Wednesday, August 20, 2014 12:09 PM > To: Polyack, Steve; freebsd-stable@freebsd.org > Subject: Re: vmdaemon CPU usage and poor performance in 10.0-RELEASE >=20 > On 08/20/2014 10:56, Polyack, Steve wrote: > >> -----Original Message----- > >> From: Alan Cox [mailto:alc@rice.edu] > >> Sent: Wednesday, August 20, 2014 11:55 AM > >> To: Polyack, Steve; freebsd-stable@freebsd.org > >> Subject: Re: vmdaemon CPU usage and poor performance in 10.0-RELEASE > >> > >> On 08/20/2014 09:55, Polyack, Steve wrote: > >>>> -----Original Message----- > >>>> From: Polyack, Steve > >>>> Sent: Wednesday, August 20, 2014 9:14 AM > >>>> To: Polyack, Steve; Alan Cox; freebsd-stable@freebsd.org > >>>> Subject: RE: vmdaemon CPU usage and poor performance in 10.0- > RELEASE > >>>> > >>>> > >>>>> -----Original Message----- > >>>>> From: owner-freebsd-stable@freebsd.org [mailto:owner-freebsd- > >>>>> stable@freebsd.org] On Behalf Of Polyack, Steve > >>>>> Sent: Tuesday, August 19, 2014 12:37 PM > >>>>> To: Alan Cox; freebsd-stable@freebsd.org > >>>>> Subject: RE: vmdaemon CPU usage and poor performance in 10.0- > >> RELEASE > >>>>>> -----Original Message----- > >>>>>> From: owner-freebsd-stable@freebsd.org [mailto:owner-freebsd- > >>>>>> stable@freebsd.org] On Behalf Of Alan Cox > >>>>>> Sent: Monday, August 18, 2014 6:07 PM > >>>>>> To: freebsd-stable@freebsd.org > >>>>>> Subject: Re: vmdaemon CPU usage and poor performance in 10.0- > >>>> RELEASE > >>>>>> On 08/18/2014 16:29, Polyack, Steve wrote: > >>>>>>>> -----Original Message----- > >>>>>>>> From: owner-freebsd-stable@freebsd.org [mailto:owner-freebsd- > >>>>>>>> stable@freebsd.org] On Behalf Of Alan Cox > >>>>>>>> Sent: Monday, August 18, 2014 3:05 PM > >>>>>>>> To: freebsd-stable@freebsd.org > >>>>>>>> Subject: Re: vmdaemon CPU usage and poor performance in 10.0- > >>>>> RELEASE > >>>>>>>> On 08/18/2014 13:42, Polyack, Steve wrote: > >>>>>>>>> Excuse my poorly formatted reply at the moment, but this seems > to > >>>>>> have > >>>>>>>> fixed our problems. I'm going to update the bug report with a > note. > >>>>>>>>> Thanks Alan! > >>>>>>>> You're welcome. And, thanks for letting me know of the outcome. > >>>>>>>> > >>>>>>> Actually, I may have spoken too soon, as it looks like we're seei= ng > >>>>>> vmdaemon tying up the system again: > >>>>>>> root 6 100.0 0.0 0 16 - DL Wed0= 4PM 4:37.95 > >>>>> [vmdaemon] > >>>>>>> Is there anything I can check to help narrow down what may be the > >>>>>> problem? KTrace/truss on the "process" doesn't give any > information, I > >>>>>> suppose because it's actually a kernel thread. > >>>>>> > >>>>>> Can you provide the full output of top? Is there anything unusual > >> about > >>>>>> the hardware or software configuration? > >>>>> This may have just been a fluke (maybe NFS caching the old > >> vm_pageout.c > >>>>> during the first source build). We've rebuilt and are monitoring i= t > now. > >>>>> > >>>>> The hardware consists of a few Dell PowerEdge R720xd servers with > >> 256GB > >>>>> of RAM and array of SSDs (no ZFS). 64GB is dedicated to postgres > >>>>> shared_buffers right now. FreeBSD 10, PostgreSQL 9.3, Slony-I v2.2.= 2, > >> and > >>>>> redis-2.8.11 are all in use here. I can't say that anything is unu= sual > about > >>>> the > >>>>> configuration. > >>>>> > >>>> We are still seeing the issue. It seems to manifest once the "Free" > >> memory > >>>> gets under 10GB (of 256GB on the system), even though ~200GB of this > is > >>>> classified as Inactive. For us, this was about 7 hours of database > activity > >>>> (initial replication w/ slony). Right now vmdaemon is consuming 100= % > >> CPU > >>>> and shows 671:34 CPU time when it showed 0:00 up until the problem > >>>> manifested. The full top output (that fits on my screen) is below: > >>>> > >>>> last pid: 62309; load averages: 4.05, 4.24, 4.10 > >>>> up 0+22:34:31 09:08:43 > >>>> 159 processes: 8 running, 145 sleeping, 1 waiting, 5 lock > >>>> CPU: 14.5% user, 0.0% nice, 4.9% system, 0.0% interrupt, 80.5% id= le > >>>> Mem: 26G Active, 216G Inact, 4122M Wired, 1178M Cache, 1632M Buf, > >> 2136M > >>>> Free > >>>> Swap: 32G Total, 32G Free > >>>> > >>>> PID USERNAME THR PRI NICE SIZE RES STATE C TIME = WCPU > >>>> COMMAND > >>>> 11 root 32 155 ki31 0K 512K CPU31 31 669.6H 293= 4.23% idle > >>>> 6 root 1 -16 - 0K 16K CPU19 19 678:57 100= .00% vmdaemon > >>>> 1963 pgsql 1 45 0 67538M 208M CPU0 0 121:46 17= .38% > postgres > >>>> 2037 pgsql 1 77 0 67536M 2200K *vm ob 14 6:24 15= .97% > postgres > >>>> 1864 pgsql 1 31 0 67536M 1290M semwai 4 174:41 15= .19% > >> postgres > >>>> 1996 pgsql 1 38 0 67538M 202M semwai 16 120:27 15= .09% > >> postgres > >>>> 1959 pgsql 1 39 0 67538M 204M CPU27 27 117:30 15= .09% > postgres > >>>> 1849 pgsql 1 32 0 67536M 1272M semwai 23 126:22 13= .96% > >> postgres > >>>> 1997 pgsql 1 31 0 67538M 206M CPU30 30 122:26 11= .77% > postgres > >>>> 2002 pgsql 1 34 0 67538M 182M sbwait 11 55:20 11= .28% > postgres > >>>> 1961 pgsql 1 32 0 67538M 206M CPU12 12 121:47 10= .99% > postgres > >>>> 1964 pgsql 1 30 0 67538M 206M semwai 28 122:08 9= .86% > postgres > >>>> 1962 pgsql 1 29 0 67538M 1286M sbwait 2 45:49 7= .18% > postgres > >>>> 1752 root 1 22 0 78356K 8688K CPU2 2 175:46 6= .88% snmpd > >>>> 1965 pgsql 1 25 0 67538M 207M semwai 9 120:55 6= .59% > postgres > >>>> 1960 pgsql 1 23 0 67538M 177M semwai 6 52:42 4= .88% > postgres > >>>> 1863 pgsql 1 25 0 67542M 388M semwai 25 9:12 2= .20% > postgres > >>>> 1859 pgsql 1 22 0 67538M 1453M *vm ob 20 6:13 2= .10% > postgres > >>>> 1860 pgsql 1 22 0 67538M 1454M sbwait 8 6:08 1= .95% postgres > >>>> 1848 pgsql 1 21 0 67586M 66676M *vm ob 30 517:07 1= .66% > >> postgres > >>>> 1856 pgsql 1 22 0 67538M 290M *vm ob 15 5:39 1= .66% > postgres > >>>> 1846 pgsql 1 21 0 67538M 163M sbwait 15 5:46 1= .46% postgres > >>>> 1853 pgsql 1 21 0 67538M 110M sbwait 30 8:54 1= .17% postgres > >>>> 1989 pgsql 1 23 0 67536M 5180K sbwait 18 1:41 0= .98% postgres > >>>> 5 root 1 -16 - 0K 16K psleep 6 9:33 0= .78% pagedaemon > >>>> 1854 pgsql 1 20 0 67538M 338M sbwait 22 5:38 0= .78% postgres > >>>> 1861 pgsql 1 20 0 67538M 286M sbwait 15 6:13 0= .68% postgres > >>>> 1857 pgsql 1 20 0 67538M 1454M semwai 10 6:19 0= .49% > postgres > >>>> 1999 pgsql 1 36 0 67538M 156M *vm ob 28 120:56 0= .39% > postgres > >>>> 1851 pgsql 1 20 0 67538M 136M sbwait 22 5:48 0= .39% postgres > >>>> 1975 pgsql 1 20 0 67536M 5688K sbwait 25 1:40 0= .29% postgres > >>>> 1858 pgsql 1 20 0 67538M 417M sbwait 3 5:55 0= .20% postgres > >>>> 2031 pgsql 1 20 0 67536M 5664K sbwait 5 3:26 0= .10% postgres > >>>> 1834 root 12 20 0 71892K 12848K select 20 34:05 0= .00% slon > >>>> 12 root 78 -76 - 0K 1248K WAIT 0 25:47 0= .00% intr > >>>> 2041 pgsql 1 20 0 67536M 5932K sbwait 14 12:50 0= .00% > postgres > >>>> 2039 pgsql 1 20 0 67536M 5960K sbwait 17 9:59 0= .00% postgres > >>>> 2038 pgsql 1 20 0 67536M 5956K sbwait 6 8:21 0= .00% postgres > >>>> 2040 pgsql 1 20 0 67536M 5996K sbwait 7 8:20 0= .00% postgres > >>>> 2032 pgsql 1 20 0 67536M 5800K sbwait 22 7:03 0= .00% postgres > >>>> 2036 pgsql 1 20 0 67536M 5748K sbwait 23 6:38 0= .00% postgres > >>>> 1812 pgsql 1 20 0 67538M 59185M select 1 5:46 0= .00% postgres > >>>> 2005 pgsql 1 20 0 67536M 5788K sbwait 23 5:14 0= .00% postgres > >>>> 2035 pgsql 1 20 0 67536M 4892K sbwait 18 4:52 0= .00% > > >>>> 1852 pgsql 1 21 0 67536M 1230M semwai 7 4:47 0= .00% > postgres > >>>> 13 root 3 -8 - 0K 48K - 28 4:46 0= .00% geom > >>>> > >>>> > >>> Another thing I've noticed is that this sysctl vm.stats counter is > increasing > >> fairly rapidly: > >>> # sysctl vm.stats.vm.v_pdpages && sleep 1 && sysctl > >> vm.stats.vm.v_pdpages > >>> vm.stats.vm.v_pdpages: 3455264541 > >>> vm.stats.vm.v_pdpages: 3662158383 > >> I'm not sure what that tells us, because both the page daemon and the > vm > >> ("swap") daemon increment this counter. > >> > >>> Also, to demonstrate what kind of problems this seems to cause: > >>> # time sleep 1 > >>> > >>> real 0m18.288s > >>> user 0m0.001s > >>> sys 0m0.004s > >> If you change the sysctl vm.swap_enabled to 0, how does your system > >> behave? > >> > > Setting vm.swap_enabled to 0 made the problem clear up almost > instantly. vmdaemon is back to 0.00% CPU usage and the system is > responsive once again. > > > > >=20 > I doubt that you need whole process swapping. The page daemon is > probably sufficient. See how things go for a few days and let me know. >=20 > There is still a bug here that needs diagnosing and fixing. So, I will > likely send you a debugging patch in the near future, and ask you to > reenable swapping under that patch. >=20 If it helps at all - setting vm.swap_enabled=3D0 seems to fix the problem e= ven without the aforementioned patch to vm_pageout.c. Thanks again, Steve