From owner-freebsd-current Thu Jul 1 23:34:31 1999 Delivered-To: freebsd-current@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [209.157.86.2]) by hub.freebsd.org (Postfix) with ESMTP id D9FED14DCC for ; Thu, 1 Jul 1999 23:34:29 -0700 (PDT) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id XAA52990; Thu, 1 Jul 1999 23:34:29 -0700 (PDT) (envelope-from dillon) Date: Thu, 1 Jul 1999 23:34:29 -0700 (PDT) From: Matthew Dillon Message-Id: <199907020634.XAA52990@apollo.backplane.com> To: current@FreeBSD.ORG Subject: Something weird happening w/ SMP -current Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG I'm getting some really odd stuff with recent -current's configured for SMP. Processes are getting stuck in getblk() and other I/O waits. It does not appear to occur with UP configuration, only SMP. I seem to be able to repeat the problem by dd'ing a raw partition from a SCSI{ disk to /dev/null: dd if=/dev/rda1d bs=32k of=/dev/null If I run a 'systat -vm 1' in another window what I see are a bunch of ahc2 interrupts, around 500-1000 per second, and then it just stops. Then a few seconds later it starts up again. Then it just stops. Then a few seconds later it starts up again. It is as thought interrupts are being disabled for long periods of time but the weird thing is that other interrupts such as clk and rtc continue to work just fine. When the interrupts stop, dd is stuck in a disk-wait state. I'm sure it isn't the SCSI bus: I've got three SCSI busses and it occurs on all three. Plus it does not occur on a UP kernel, only an SMP kernel. If I run an endless loop in another window (e.g. systat shows 50% idle on the 2x SMP box), the interrupts appear to work for longer periods of time before crapping out. It is very weird. I have no idea what is going on. -Matt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message