Date: Wed, 24 Nov 2010 02:18:57 -0800 From: "Li, Qing" <qing.li@bluecoat.com> To: "Andrey Groshev" <greenx@yartv.ru> Cc: freebsd-stable@freebsd.org Subject: Re: upd: 7.2->8.1 & many networks trouble & flowtable Message-ID: <A9DF1923-565F-4B43-8429-51C9D27FCC87@bluecoat.com> In-Reply-To: <4CECDC89.7070706@yartv.ru> References: <m2zku7cqt5.wl%randy@psg.com> <m2y69rcqjc.wl%randy@psg.com> <201010221416.o9MEGSa0094817@lava.sentex.ca> <m2tykeb9ac.wl%randy@psg.com> <201010221425.o9MEPcWC094867@lava.sentex.ca> <m2k4lab6nh.wl%randy@psg.com> <201010221848.o9MIm7WF096197@lava.sentex.ca> <m2y69q9e38.wl%randy@psg.com> <4CC1F3B8.3010302@bogus.com> <4CC225D3.1030502@ops-netman.net> <7.1.0.9.0.20101022210145.06fe25e8@sentex.net> <201010230159.o9N1xGGF098363@lava.sentex.ca> <AANLkTimWTTHWC04my3CSoNGYsLarS9F10eoO=8Fz37cF@mail.gmail.com> <201010230821.o9N8LVuR001382@lava.sentex.ca> <20101023091555.W66242@maildrop.int.zabbadoz.net> <20101123175100.V24596@maildrop.int.zabbadoz.net> <AANLkTi=E89jJH68Ng1R06tKQi%2BxpaYORpktrZk5cvjVh@mail.gmail.com> <4CECDC89.7070706@yartv.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
I am the main author of this paper you referenced in your email. The main discussion and focus of my paper was on the design and work done to= separate L2 and L3 for both IPv4 and IPv6 to facilitate the elimination of G= IANT lock in the networking subsystem, thus achieving high parallelism.=20 This redesign of separately managing L2 ARP/ND6 and L3 routing tables alread= y show performance gain on multicore systems. The flow-table enhancement is just one other component, described towards th= e end of the paper. Yes, It is experimental and was discussed as such in the= paper as well as on the mailing list.=20 I did not know flow-table feature was enabled by default. I wouldn't have do= ne so myself. So help me understand you better: are you complaining about the general L2/L= 3 separation work, or you are angry about the flow-table enhancement in part= icular? cheers, -- Qing On Nov 24, 2010, at 1:54 AM, "Andrey Groshev" <greenx@yartv.ru> wrote: > Hi, PPL! >=20 > A couple of days ago decided to upgrade from 7.2-STABLE to 8.1-STABLE (amd= 64). > By tradition, waited some pitfalls. > But damn, not to the same degree! >=20 > The hardware on the server: > Motherboard: Intel SE7520JR23S > CPU's: 2 x Xeon 3Ghz > Ram: 4Gb >=20 > Software used: openospfd, openbgpd, bind, and so on. > In general, used as a boundary Router. >=20 > Update ... and began: > 1. The server died a few minutes after launch, not even reacting to the ke= yboard. By issuing a warning about "em0 watchdog .....". I thought to myself= - broke the driver, connect the other network card. Server even stopped han= ging. > 2. Nearest switch does not like OSPF from the server and it shuts down a p= ort or vlan. > 3. openbgpd loads CPU nearly 100%. > 4. bind does not respond, despite the fact that properly loads the CPU. >=20 > In the end, I turned off everything that does not work as is necessary, > Only remaining process FLOWCLEANER which can be CPU at 100%. >=20 >=20 > Google started about this flowcleaner. > And what happened? I found a report entitled "Optimizing the BSD Routing S= ystem for Parallel Processing"(1). Roughly speaking, flowtable - a new appro= ach to routing. Dividing the levels 2 and 3 can achieve more parallelism. Bu= t in the end, due to this - to increase network performance. Ok, everything l= ooks great! >=20 > And now I ask: for whom all this? IMHO for example, ISP. Or, as stated in t= he above-mentioned report: >=20 >> >> "The main goals for redesigning the kernel routing infrastructure=20 > was to reduce the scope of the customization necessary when deriving produ= cts from FreeBSD, and to offer a generic solution that could be an integral p= art of the kernel." <<< >=20 > What ultimately relevant only to the equipment is used at the ISP. > Since the average user with its tiny routing table - it is not necessary. > But beyond the problems begin. How long have you seen the ISP without "ful= lview bpg"? >=20 > But beyond the problems begin. > Almost everywhere where it is mentioned a problem with FLOWCLEANER recomme= nded for deletion from the kernel option FLOWTABLE. > And one of the co-authors wrote in his blog(2): >> >> "One oversight that come up shortly afterwards > is that it adversely impacts performance for systems > with many routing prefixes to a greater degree than I had expected." <<< >=20 > How long have you seen the ISP without "fullview bpg"? > It turns out that the technology is designed to increase network performan= ce that most network generally kills, which implies that it is not suitable f= or use. > And here it is not simply included in the source tree, and is enabled by d= efault in the GENERIC kernel! > And do not say that there was no PR - they are (3)! >=20 > ---- >=20 > Sorry so long sets out the main meaning of the message is this: > Why in the kernel introduced new features, if it is good only on paper? > May exclude this option from the GENERIC kernel? >=20 > ---- >=20 > Links: > 1. - http://conferences.sigcomm.org/sigcomm/2009/workshops/presto/papers/p= 37.pdf > 2. - http://daemonflux.blogspot.com/2010/01/updates.html > 3. - http://people.freebsd.org/~linimon/studies/prs/prs_for_tag_flowtable.= html >=20 > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org"
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?A9DF1923-565F-4B43-8429-51C9D27FCC87>