From mboxrd@z Thu Jan 1 00:00:00 1970 References: <7f11f16bfdb01c0041b0397a1cea04c5@proxima.alt.za> <7dc7cfb35a012dedc41828d03d5cdff3@lilly.quanstro.net> <4CB999B4-E9C6-4A74-B849-4003DD3D23D1@9srv.net> <22d498b89c3b4d2e50c1c5cc0e9d72c0@lilly.quanstro.net> <536D0D14-3391-426A-930F-2B92FFD734DB@9srv.net> <418789bb5bc4501ab70366014c15b965@lilly.quanstro.net> From: Bakul Shah Content-Type: text/plain; charset=us-ascii In-Reply-To: <418789bb5bc4501ab70366014c15b965@lilly.quanstro.net> Message-Id: <0841E3F3-400C-4E19-811F-37B0595006BD@bitblocks.com> Date: Fri, 21 Nov 2014 09:31:19 -0800 To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net> Content-Transfer-Encoding: quoted-printable Mime-Version: 1.0 (1.0) Subject: Re: [9fans] running plan9 : an ideal setup? Topicbox-Message-UUID: 2dc5cf60-ead9-11e9-9d60-3106f5b1d025 This paper is well worth reading: http://groups.csail.mit.edu/ana/Publications/PubPDFs/1988Analysis%20TCP%20Pr= ocessing%20Overhead.pdf While the traditional BSD implementation uses mbufs that complicate things, a= ctual tcp processing can be done quite cheaply. > On Nov 21, 2014, at 6:34 AM, erik quanstrom wrote:= >=20 >> On Thu Nov 20 13:44:04 EST 2014, a@9srv.net wrote: >> Both. I agree with what you're saying about the computers, but I was thin= king of the fact that the wire speed is fast enough in most cases that the t= cp/ip overhead doesn't impact things noticeably for most uses. There are out= liers in both cases, of course. >=20 > this is not correct. tcp doesn't help at all when the wire is fast (short= , fat). it's the classic tradeoff of cpu > for (networking) performance. the wire being fast enough is an argument a= gainst using tcp, > not for it. >=20 > so really, it's the gobs of cpu we currently have that make tcp not an iss= ue, not the gobs of bandwidth. >=20 > - erik >=20