From owner-freebsd-hackers Mon Nov 13 08:20:46 1995 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.6.12/8.6.6) id IAA07519 for hackers-outgoing; Mon, 13 Nov 1995 08:20:46 -0800 Received: from ulantris.infinop.com (root@[205.230.144.80]) by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id IAA07477 for ; Mon, 13 Nov 1995 08:20:35 -0800 Received: (from john@localhost) by ulantris.infinop.com (8.6.11/8.6.9) id KAA04083 for hackers@freebsd.org; Mon, 13 Nov 1995 10:33:01 -0600 From: "John A. Booth" Message-Id: <199511131633.KAA04083@ulantris.infinop.com> Subject: Re: Disk I/O that binds To: hackers@freebsd.org Date: Mon, 13 Nov 1995 10:33:01 -0600 (CST) In-Reply-To: from "Frank Durda IV" at Nov 12, 95 01:13:00 pm X-Mailer: ELM [version 2.4 PL24] Content-Type: text Content-Length: 694 Sender: owner-hackers@freebsd.org Precedence: bulk > > My system where I have seen something that somewhat resembles his > description is a mixed IDE SCSI system, and when things bog, the hog > process and the binding process are both trying to get to the same > SCSI drive. The IDE is for swap and root and is idle during these events. I've got an all IDE system, this seems to occur on my system when I have a large process core (I've got a few muds running and they're updated quite frequently, so we get a few bugs). The whole system is basically frozen while it's coring we usualy get between 3 meg and 7 meg core files. This is a noname 486/66 24M ram, main drive is a 1 gig IBM (they're recent 'fast' one), generic IDE controller.