From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp108.mail.mud.yahoo.com (smtp108.mail.mud.yahoo.com [209.191.85.218]) by ozlabs.org (Postfix) with SMTP id 758EE67A76 for ; Mon, 17 Apr 2006 01:20:15 +1000 (EST) Message-ID: <4441ECE6.5010709@yahoo.com.au> Date: Sun, 16 Apr 2006 17:06:14 +1000 From: Nick Piggin MIME-Version: 1.0 To: Steven Rostedt Subject: Re: [PATCH 00/05] robust per_cpu allocation for modules References: <1145049535.1336.128.camel@localhost.localdomain> <4440855A.7040203@yahoo.com.au> <4441B02D.4000405@yahoo.com.au> In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Cc: Andrew Morton , linux-mips@linux-mips.org, David Mosberger-Tang , linux-ia64@vger.kernel.org, Martin Mares , spyro@f2s.com, Joe Taylor , Andi Kleen , linuxppc-dev@ozlabs.org, paulus@samba.org, benedict.gaster@superh.com, bjornw@axis.com, Ingo Molnar , grundler@parisc-linux.org, starvik@axis.com, Linus Torvalds , Thomas Gleixner , rth@twiddle.net, Chris Zankel , tony.luck@intel.com, LKML , ralf@linux-mips.org, Marc Gauthier , lethal@linux-sh.org, schwidefsky@de.ibm.com, linux390@de.ibm.com, davem@davemloft.net, parisc-linux@parisc-linux.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Steven Rostedt wrote: > On Sun, 16 Apr 2006, Nick Piggin wrote: >>Why is your module using so much per-cpu memory, anyway? > > > Wasn't my module anyway. The problem appeared in the -rt patch set, when > tracing was turned on. Some module was affected, and grew it's per_cpu > size by quite a bit. In fact we had to increase PERCPU_ENOUGH_ROOM by up > to something like 300K. Well that's easy then, just configure PERCPU_ENOUGH_ROOM to be larger when tracing is on in the -rt patchset? Or use alloc_percpu for the tracing data? >>I don't think it would have been hard for the original author to make >>it robust... just not both fast and robust. PERCPU_ENOUGH_ROOM seems >>like an ugly hack at first glance, but I'm fairly sure it was a result >>of design choices. > > Yeah, and I discovered the reasons for those choices as I worked on this. > I've put a little more thought into this and still think there's a > solution to not slow things down. > > Since the per_cpu_offset section is still smaller than the > PERCPU_ENOUGH_ROOM and robust, I could still copy it into a per cpu memory > field, and even add the __per_cpu_offset to it. This would still save > quite a bit of space. Well I don't think making it per-cpu would help much (presumably it is not going to be written to very frequently) -- I guess it would be a small advantage on NUMA. The main problem is the extra load in the fastpath. You can't start the next load until the results of the first come back. > So now I'm asking for advice on some ideas that can be a work around to > keep the robustness and speed. > > Is there a way (for archs that support it) to allocate memory in a per cpu > manner. So each CPU would have its own variable table in the memory that > is best of it. Then have a field (like the pda in x86_64) to point to > this section, and use the linker offsets to index and find the per_cpu > variables. > > So this solution still has one more redirection than the current solution > (per_cpu_offset__##var -> __per_cpu_offset -> actual_var where as the > current solution is __per_cpu_offset -> actual_var), but all the loads > would be done from memory that would only be specified for a particular > CPU. > > The generic case would still be the same as the patches I already sent, > but the archs that can support it, can have something like the above. > > Would something like that be acceptible? I still don't understand what the justification is for slowing down this critical bit of infrastructure for something that is only a problem in the -rt patchset, and even then only a problem when tracing is enabled. -- SUSE Labs, Novell Inc. Send instant messages to your online friends http://au.messenger.yahoo.com