Date: Sun, 9 Dec 2001 23:02:13 -0500 From: Jim Durham <durham@w2xo.pgh.pa.us> To: Matthew Dillon <dillon@apollo.backplane.com>, D J Hawkey Jr <hawkeyd@visi.com> Cc: hackers@FreeBSD.ORG Subject: Re: FreeBSD performs worse that Linux - Patches #2 & #3 Message-ID: <200112100402.fBA42Ge21093@w2xo.pgh.pa.us> In-Reply-To: <200112090811.fB98BYD35974@apollo.backplane.com> References: <20011206114725.A836@sheol.localdomain> <200112090811.fB98BYD35974@apollo.backplane.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sunday 09 December 2001 03:11 am, Matthew Dillon wrote: > :Hello all. > : > :I read with interest (and fair ignorance ;-) ) the thread about delayed > :ACKs in the TCP/IP stack. > :... > :If Matt or any other qualified hackers can make the time to double-check > :my patches, I'd appreciate it. Matt's first patch didn't apply (no NewReno > :in 4.2REL), and the third patch (to tcp_input.c) required a little more > : work (I changed tests for 'tcp_delack_enabled' to 'DELAY_ACK()'). I'd > : just like some assurance I got it right. > : > :All in all, kudos to Matt for this. In day-to-day use, I can "feel" the > :improvementi, and everything seems as solid as ever! > : > :Dave > > Ach. If you want my specific attention (or any FreeBSD developer's > specific attention) you should always Cc: the person specifically. > Otherwise my mail filter won't put it in my personal mail box :-) > > In anycase, your patches look fine. In fact, you not only applied > my fixes you also applied a fix in the delayed-ack check that was > made (by someone else) some time after 4.2Rel -- the callout_pending() > check in DELAY_ACK() fixed a serious bug in prior releases all by > itself. Kudos! > > I'm glad people have been testing this and getting such good results. > I MFC'd it fairly quickly into stable (because TCP was seriously messed > up) and its nice to get feedback that justifies the decision. > > -Matt > Matthew Dillon > <dillon@backplane.com> > Matt, could you clarify. Is the patch that Dave applied to 4.2 applicable to 4.4-RELEASE? It sounded like not. I applied the tcp_output.c and uipc_socket.c patch to my 4.4-RELEASE servers and it made a whole lot of difference, like 500KB/sto 954KB/s from my old P200 server to my laptop. Thanks. -- Jim Durham To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200112100402.fBA42Ge21093>