From: Nick Piggin Subject: Re: GFP_ATOMIC page allocation failures. Date: Thu, 3 Apr 2008 16:57:43 +1100 Message-ID: <200804031657.43895.nickpiggin@yahoo.com.au> References: <20080401235609.GA6947@codemonkey.org.uk> <20080402103355.77ef22ff.akpm@linux-foundation.org> <47F3CE10.1060903@garzik.org> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: Andrew Morton , Chris Snook , Dave Jones , Linux Kernel , NetDev , David Miller , Linus Torvalds To: Jeff Garzik Return-path: Received: from smtp113.mail.mud.yahoo.com ([209.191.84.66]:27893 "HELO smtp113.mail.mud.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1757366AbYDCF5u (ORCPT ); Thu, 3 Apr 2008 01:57:50 -0400 In-Reply-To: <47F3CE10.1060903@garzik.org> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: On Thursday 03 April 2008 05:18, Jeff Garzik wrote: > Turning to Nick's comment, > > > It's still actually nice to know how often it is happening even for > > these known good sites because too much can indicate a problem and > > that you could actually bring performance up by tuning some things. > > then create a counter or acculuation buffer somewhere. > > We don't need spew every time there is memory pressure of this magnitude. Not a complete solution. Counter would be nice, but you need backtraces and want a way to more proactively warn the user/tester/developer. I agree that I don't exactly like adding nowarns around, and I don't think places like driver writers should have to know about this stuff. > IMO there are much better ways than printk(), to inform tasks, and > humans, of allocation failures. I think with a tweaked warning message, a ratelimited printk is OK.