From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756450Ab2BDAYm (ORCPT ); Fri, 3 Feb 2012 19:24:42 -0500 Received: from mail-bk0-f46.google.com ([209.85.214.46]:56920 "EHLO mail-bk0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756277Ab2BDAYl (ORCPT ); Fri, 3 Feb 2012 19:24:41 -0500 Date: Sat, 4 Feb 2012 03:24:35 +0300 From: Alexey Dobriyan To: Andy Lutomirski Cc: linux-kernel@vger.kernel.org Subject: Re: 3.0 does not survive make -j [sic] on a kernel tree Message-ID: <20120204002435.GA3054@p183.telecom.by> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Feb 03, 2012 at 04:18:28PM -0800, Andy Lutomirski wrote: > make clean ; make -j hangs quickly, 100% reproducibly. The system > answers pings but is otherwise completely unresponsive. The > softlockup detector output and eventual oom is below. The system does > not appear to recover. > > The correct answer is "don't do that". But this seems like poor behavior. "make -j" is like fork bomb. But if you turn on heavy debugging options, system might actually survive to the completion.