Date: Mon, 22 Jun 2009 13:12:08 +0200 (CEST) From: Wojciech Puchar <wojtek@wojtek.tensor.gdynia.pl> To: Pyun YongHyeon <pyunyh@gmail.com> Cc: freebsd-hackers@freebsd.org Subject: Re: is RTL8139 THAT bad? Message-ID: <alpine.BSF.2.00.0906221311210.28638@wojtek.tensor.gdynia.pl> In-Reply-To: <20090622001705.GA10712@michelle.cdnetworks.co.kr> References: <alpine.BSF.2.00.0906211709420.1184@wojtek.tensor.gdynia.pl> <20090622001705.GA10712@michelle.cdnetworks.co.kr>
next in thread | previous in thread | raw e-mail | index | archive | help
>> >> Why it's THAT bad? >> > > Because CPU always have to copy frames to/from the controller. comment says card do DMA. just then it has to copy but within main memory not PCI. > These CPU cycles could have been used in other task to give more > performance such as SSH encryption/decryption, checksum computation > etc. > >> 3.5MB/s is less that 2500 packets/second. 50% at 200Mhz means 100000000 >> cycles spend on interrupt service, which is 40000 CPU cycles per packet. >> > > That depends on your application. It would be ok for normal desktop > PCs with fast CPU but it wouldn't be acceptable on servers that > have to do lots of other processing. If you have fxp(4) or txp(4) i know all this, but i'm asking why processing single interrupt takes 40000 CPU cycles.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.BSF.2.00.0906221311210.28638>