Return to BSD News archive
Xref: sserve comp.os.linux.development:18758 comp.os.linux.misc:28922 comp.os.386bsd.questions:14268 comp.os.386bsd.misc:3991 sci.electronics:83402 Path: sserve!newshost.anu.edu.au!harbinger.cc.monash.edu.au!yarrina.connect.com.au!warrane.connect.com.au!godzilla.zeta.org.au!not-for-mail From: bde@zeta.org.au (Bruce Evans) Newsgroups: comp.os.linux.development,comp.os.linux.misc,comp.os.386bsd.questions,comp.os.386bsd.misc,sci.electronics Subject: Re: 16550 detection Date: 6 Nov 1994 13:23:00 +1100 Organization: Kralizec Dialup Unix Sydney - +61-2-837-1183, v.32bis v.42bis Lines: 18 Message-ID: <39hem4$uct@godzilla.zeta.org.au> References: <CMETZ.94Oct30051603@itchy.inner.net> <MICHAELV.94Oct31211019@MindBender.HeadCandy.com> <TYTSO.94Nov1182557@dcl.mit.edu> <199411032154.NAA12270@exit.com> NNTP-Posting-Host: localhost.zeta.org.au In article <199411032154.NAA12270@exit.com>, Frank Mayhar <fmayhar@netcom.com> wrote: >you'll be running at up to 128kbps uncompressed. Without that 1024-byte >FIFO, the host would quickly become swamped with interrupts. At 115,200, >that's 720 interrupts per second with a 16-byte FIFO, and at 900kbps, >that's over 5600 per second. That 1024-byte FIFO reduces this to 12 >and 87, respectively, around an order of magnitude fewer. (The ESP >supports DMA, as well, which further reduces the load on the host.) I've been testing swamping with interrupts under FreeBSD-2.0 on a 486DX/33 recently. It takes about 50000 interrupts per second to swamp it (16000 clock and a potential 46080 serial are reduced to about 50000 total). A 16-byte FIFO reduces the pure interrupt overhead to about half the i/o overhead, so a larger FIFO wouldn't help much without better i/o. -- Bruce Evans bde@zeta.org.au