Date: Fri, 18 Oct 2002 23:58:03 +0300 From: "Petri Helenius" <pete@he.iki.fi> To: "Prafulla Deuskar" <pdeuskar@FreeBSD.ORG> Cc: "Luigi Rizzo" <rizzo@icir.org>, "Lars Eggert" <larse@ISI.EDU>, <freebsd-net@FreeBSD.ORG> Subject: Re: ENOBUFS Message-ID: <018001c276e9$0d6a4100$3500080a@PHE> References: <3DAC8FAD.30601@isi.edu> <068b01c2749f$32e7cf70$8c2a40c1@PHE> <20021015161055.A27443@carp.icir.org> <06c901c274d8$e5280b80$8c2a40c1@PHE> <3DAD01A7.3020807@isi.edu> <071501c274db$222c3ea0$8c2a40c1@PHE> <3DAD06AF.7060701@isi.edu> <0be401c2761f$855af670$8c2a40c1@PHE> <20021017201158.A75351@carp.icir.org> <0d0b01c27680$b553ba90$8c2a40c1@PHE> <20021018102203.A86452@hub.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
> Transmit/Receive Interrupt Delay values are in units of 1.024 microseconds. > The em driver currently uses these to enable interrupt coalescing on the cards. > Is this one and 24 one thousandth of microseconds or 1024 microseconds which equals to about one millisecond and sounds quite a lot? With former, em would "top out" at about 35000 interrupts a second. (times two for two interfaces) With 256 receive descriptors available this would translate to about 9Mpps :-) Pete To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?018001c276e9$0d6a4100$3500080a>