From owner-freebsd-current Sun Jul 2 23:53:21 1995 Return-Path: current-owner Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id XAA21941 for current-outgoing; Sun, 2 Jul 1995 23:53:21 -0700 Received: from clinet.fi (root@clinet.fi [193.64.6.1]) by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id XAA21933 for ; Sun, 2 Jul 1995 23:53:11 -0700 Received: from katiska.clinet.fi (root@katiska.clinet.fi [193.64.6.3]) by clinet.fi (8.6.10/8.6.4) with ESMTP id JAA09078 for ; Mon, 3 Jul 1995 09:52:46 +0300 From: Heikki Suonsivu Received: (hsu@localhost) by katiska.clinet.fi (8.6.11/8.6.4) id JAA00240; Mon, 3 Jul 1995 09:52:46 +0300 Date: Mon, 3 Jul 1995 09:52:46 +0300 Message-Id: <199507030652.JAA00240@katiska.clinet.fi> To: freebsd-current@freefall.cdrom.com Subject: Re: kern/579: sio: RS_IBUFSIZE 256 too small Organization: Clinet Ltd, Espoo, Finland Sender: current-owner@FreeBSD.org Precedence: bulk In article <199507021921.TAA26200@puffin.pelican.com> Pete Carah writes: >> Both these machines report "interrupt-level buffer overflow":s >> very frequently on a leased line running at 38400, badly dropping ... >This is because you don't use crtscts and something or other delays On many async leased lines there is no hardware flow control, all you get through is two data wires. Even if there was, if you stop receiving because internal rs buffer overflows, you are idling the fixed-speed link, thus it should only done if the machine really can't cope with all the data (but it certainly does cope in this case). After pushing the input buffer to 4k I got a significant performance improvement and no more loss of data. My workaround is apparently wrong, it works as I don't need and don't have rts/cts flow control, but clearly something needs to be done to sio in this respect. 256 bytes seems overly tight to me, moving data in pieces this small is waste of cpu. Does it need to do a context switch or interrupt for each time it loads the 256 byte buffer to a tty buffer? >> On 386-16 I also saw several spontaneous reboots when loading the >> PPP link. Is this the old route delete bug? Must be independent of ttyhog and such. I have seen a few bpf commits recently to deal with tcpdump on down interfaces. Don't know if they fix anything since I don't use bpf particularly. I have bpf enabled in kernel but I haven't used tcpdump on the interface (at the time it reboots). The kernels are recent (2.0.5R and up). -- Heikki Suonsivu, T{ysikuu 10 C 83/02210 Espoo/FINLAND, hsu@cs.hut.fi home +358-0-8031121 work -4513377 fax -4555276 riippu SN