From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yury Norov Date: Sun, 28 Nov 2021 23:36:27 +0000 Subject: Re: [PATCH 0/9] lib/bitmap: optimize bitmap_weight() usage Message-Id: <20211128233627.GA323159@lapt> List-Id: References: <20211128035704.270739-1-yury.norov@gmail.com> <1638096766.3elxdzb8ly.astroid@bobo.none> In-Reply-To: <1638096766.3elxdzb8ly.astroid@bobo.none> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Nicholas Piggin Cc: Arnaldo Carvalho de Melo , Andy Gross , David Airlie , Alexey Klimov , Andi Kleen , Andrew Morton , Alexander Shishkin , Amitkumar Karwar , Andrew Lunn , Andy Shevchenko , Anup Patel , Ard Biesheuvel , Arnd Bergmann , Jens Axboe , bcm-kernel-feedback-list@broadcom.com, Borislav Petkov , Catalin Marinas , Christoph Lameter , Daniel Vetter , Dave Hansen , David Laight , Dennis Zhou , Dinh Nguyen , Geetha sowjanya , Geert Uytterhoeven , Greg Kroah-Hartman , Guo Ren , Heiko Carstens , Christoph Hellwig , Hans de Goede , Ian Rogers , Jason Wessel , "James E.J. Bottomley" , Jonathan Cameron , Jiri Olsa , Juri Lelli , Kees Cook , Krzysztof Kozlowski , Jakub Kicinski , Kalle Valo , kvm@vger.kernel.org, Lee Jones , linux-alpha@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Russell King , linux-crypto@vger.kernel.org, linux-csky@vger.kernel.org, linux-ia64@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mips@vger.kernel.org, linux-mm@kvack.org, linux-perf-users@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, Rasmus Villemoes , linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org, linux-snps-arc@lists.infradead.org, Andy Lutomirski , Mark Gross , Mark Rutland , "Martin K. Petersen" , Marc Zyngier , Matti Vaittinen , Mauro Carvalho Chehab , Mel Gorman , Mike Marciniszyn , Ingo Molnar , Michael Ellerman , Marcin Wojtas , Palmer Dabbelt , "Paul E. McKenney" , Peter Zijlstra , Solomon Peachy , Petr Mladek , "Rafael J. Wysocki" , Randy Dunlap , Steven Rostedt , Roy Pledge , Saeed Mahameed , Sagi Grimberg , Subbaraya Sundeep , Stephen Boyd , Sergey Senozhatsky , Stephen Rothwell , Sunil Goutham , Sudeep Holla , Tariq Toukan , Thomas Gleixner , Tejun Heo , Thomas Bogendoerfer , Ulf Hansson , Vlastimil Babka , Vineet Gupta , Vincent Guittot , Viresh Kumar , Vivien Didelot , Will Deacon On Sun, Nov 28, 2021 at 09:08:41PM +1000, Nicholas Piggin wrote: > Excerpts from Yury Norov's message of November 28, 2021 1:56 pm: > > In many cases people use bitmap_weight()-based functions like this: > > > > if (num_present_cpus() > 1) > > do_something(); > > > > This may take considerable amount of time on many-cpus machines because > > num_present_cpus() will traverse every word of underlying cpumask > > unconditionally. > > > > We can significantly improve on it for many real cases if stop traversing > > the mask as soon as we count present cpus to any number greater than 1: > > > > if (num_present_cpus_gt(1)) > > do_something(); > > > > To implement this idea, the series adds bitmap_weight_{eq,gt,le} > > functions together with corresponding wrappers in cpumask and nodemask. > > There would be no change to callers if you maintain counters like what > is done for num_online_cpus() today. Maybe some fixes to arch code that > does not use set_cpu_possible() etc APIs required, but AFAIKS it would > be better to fix such cases anyway. Thanks, Nick. I'll try to do this.