Date: Fri, 28 Sep 2012 15:46:54 +0400 From: Andrey Zonov <zont@FreeBSD.org> To: Andre Oppermann <oppermann@networx.ch> Cc: "freebsd-net@freebsd.org" <freebsd-net@freebsd.org>, "Eggert, Lars" <lars@netapp.com> Subject: Re: [patch] sysctls for TCP timers Message-ID: <50658E2E.5010602@FreeBSD.org> In-Reply-To: <50634F85.50901@networx.ch> References: <505AC500.6060903@FreeBSD.org> <D4D47BCFFE5A004F95D707546AC0D7E906888619@SACEXCMBX01-PRD.hq.netapp.com> <505F2C2D.5050904@FreeBSD.org> <50634F85.50901@networx.ch>
next in thread | previous in thread | raw e-mail | index | archive | help
This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig3043F80B35A7FB0F99E87D09 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 9/26/12 10:55 PM, Andre Oppermann wrote: > On 23.09.2012 17:35, Andrey Zonov wrote: >> On 9/20/12 11:35 AM, Eggert, Lars wrote: >>> Hi, >>> >>> On Sep 20, 2012, at 9:25, Andrey Zonov <zont@freebsd.org> wrote: >>>> Some of them may be read google's article about tuning TCP parameter= s >>>> [1]. I convert most of TCP timers to sysctls [2] and we are using t= his >>>> patch for few months. We tuned net.inet.tcp.rtobase and >>>> net.inet.tcp.syncache.rexmttime and it gives good results >>>> (especially in >>>> conjunction with cc_htcp(4)). >>> >>> can you share some measurements that quantify the results? >>> >> >> When we set net.inet.tcp.syncache.rexmttime=3D200 and >> net.inet.tcp.syncache.rexmtlimit=3D7 for our external web service, the= >> number of duplicated SYN was reduced in four times. >=20 > This isn't surprising. You're simply trading retransmits by the client= > with retransmits by the server. Whether this is within the overall pac= ket > conservation principle is not clear. On the timeline it may be an > advantage. >=20 This is great improvement for us. 2% of our users don't wait for 3 seconds any more. > I'm not comfortable with the rather low retransmit time you've chosen > here. Considering higher RTT's (e.g. Hawaii or JP/CN) and the bufferbl= oat > problem this may be too low. When it is to be tuned, then something in= the > range of 500-1000ms may be more realistic to avoid spurious retransmits= =2E >=20 For example Linux some time ago set RTO to 1 sec. OSX for a long time has RTO 1 sec. > When a SYN or SYN/ACK retransmit happens, the initial CWND should be > reduced > per the applicable RFC's as this indicates packet loss on the downstrea= m. >=20 --=20 Andrey Zonov --------------enig3043F80B35A7FB0F99E87D09 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG/MacGPG2 v2.0.18 (Darwin) Comment: GPGTools - http://gpgtools.org iQEcBAEBAgAGBQJQZY4wAAoJEBWLemxX/CvTaIsIAIGxsw4aWCYF+1CuLXkNrIgP K5KPjeIKSo7Um+jJNUAz8hFxepbEf3Y4AFGY2Y98NQHCJKxHi+bUmNZrC3Svs6CV 1MdUEeDGjSp9k9Ef5zrZaWzKhmzQPlxZ+DtamksMOzM03OWD0cIqixP/2UNr2/C/ 9JlcEOJpER2AlRxyJ+8+6bWJH33RDBF7C4vZcCDSfxjsvBhwWOGScMhuqh69Xmef /ixU8uYRGOWZaw3T1tv6oItChBOaSjF+Wv8VBpkt82uFswccHLfRmvAor7Lu/IoZ ASg5/1l1TLAbttRw9zMiAQHWyPQtVbjI3xqwilK6QMvzTESoBtX35sO1PXe5tKo= =MT2u -----END PGP SIGNATURE----- --------------enig3043F80B35A7FB0F99E87D09--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?50658E2E.5010602>