From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 19:13:52 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 34ABC1065676; Tue, 24 Apr 2012 19:13:52 +0000 (UTC) (envelope-from slw@zxy.spb.ru) Received: from zxy.spb.ru (zxy.spb.ru [195.70.199.98]) by mx1.freebsd.org (Postfix) with ESMTP id E190F8FC0A; Tue, 24 Apr 2012 19:13:51 +0000 (UTC) Received: from slw by zxy.spb.ru with local (Exim 4.69 (FreeBSD)) (envelope-from ) id 1SMlBn-0008db-UK; Tue, 24 Apr 2012 23:14:15 +0400 Date: Tue, 24 Apr 2012 23:14:15 +0400 From: Slawa Olhovchenkov To: freebsd-current@freebsd.org, freebsd-performance@freebsd.org Message-ID: <20120424191415.GE76983@zxy.spb.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.21 (2010-09-15) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: slw@zxy.spb.ru X-SA-Exim-Scanned: No (on zxy.spb.ru); SAEximRunCond expanded to false Cc: Subject: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 19:13:52 -0000 I treid make -j 30 build{world,kernel} (latest -CURRENT) on 24-core machine and see poor scalability of pmap/mtx -- more then 50% cpu spend on system time. pmcstat: @ CPU_CLK_UNHALTED_CORE [194841 samples] 42.65% [83102] _mtx_lock_sleep @ /boot/kernel/kernel 40.97% [34051] pmap_enter 100.0% [34051] vm_fault_hold 100.0% [34051] trap_pfault 30.40% [25262] vm_page_activate 100.0% [25262] vm_fault_hold 100.0% [25262] trap_pfault 18.41% [15300] vm_pageq_remove 73.63% [11266] vm_page_free_toq 70.69% [7964] vm_object_terminate 29.31% [3302] vm_object_page_remove 26.37% [4034] vm_fault_hold 100.0% [4034] trap_pfault make -j 8: 15.44% [10740] _mtx_lock_sleep @ /boot/kernel/kernel 38.77% [4164] pmap_enter 99.93% [4161] vm_fault_hold 100.0% [4161] trap_pfault 00.07% [3] kmem_back 100.0% [3] kmem_malloc 27.98% [3005] vm_page_activate 100.0% [3005] vm_fault_hold 100.0% [3005] trap_pfault 20.64% [2217] vm_pageq_remove 64.73% [1435] vm_page_free_toq 63.41% [910] vm_object_terminate make -j 4 06.86% [4222] pagezero @ /boot/kernel/kernel 98.39% [4154] trap_pfault 100.0% [4154] trap 01.11% [47] vm_fault_hold From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 19:27:31 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D59401065677; Tue, 24 Apr 2012 19:27:31 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-yw0-f54.google.com (mail-yw0-f54.google.com [209.85.213.54]) by mx1.freebsd.org (Postfix) with ESMTP id 790A08FC18; Tue, 24 Apr 2012 19:27:31 +0000 (UTC) Received: by yhgm50 with SMTP id m50so837833yhg.13 for ; Tue, 24 Apr 2012 12:27:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=j7pYn4TZNu8sAus7s0FzDna2/UGLIbYsiYyPeuYQkDY=; b=nB+qET8SyJ7aZfD3qWF8JdMPTaSBWx7Z04MWqaJk2JJCdY34tX5Z9H7eWOvSz0Blxj HCjCTIOXFi/qV+Leu+24aYZF6XN9nlB7Ry7U+acdmYxKsad0HobiUuh5g5YZPca7TXcY u00g47EQ0sv5PIDRmH3FY0cIzGp8ywTi2Bn81jxdAW4toP0lwW0aB2b8cSxJnYZ9pWLz HLJ0sSx5bYF8LE8eOVoDP+Om8PUab8FPDer3YYaUAMP32rQBwDjsCUlOZ3mg/2Wm3hmY 50PLhAVAYgkA01zYnQA7lolUAkJOfNtfzSOrTKtWEr6SemiM/+rRzrUbp8brYz5dXubK 8iIQ== MIME-Version: 1.0 Received: by 10.50.168.67 with SMTP id zu3mr2989983igb.28.1335295650508; Tue, 24 Apr 2012 12:27:30 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.50.129.39 with HTTP; Tue, 24 Apr 2012 12:27:30 -0700 (PDT) In-Reply-To: <20120424191415.GE76983@zxy.spb.ru> References: <20120424191415.GE76983@zxy.spb.ru> Date: Tue, 24 Apr 2012 21:27:30 +0200 X-Google-Sender-Auth: Mvt-9psx88jaB_iz56_7J8splg0 Message-ID: From: "K. Macy" To: Slawa Olhovchenkov Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org Subject: Re: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 19:27:31 -0000 Known problem. There is an open disagreement about how to improve the granularity of locking in pmap. -Kip On Tue, Apr 24, 2012 at 9:14 PM, Slawa Olhovchenkov wrote: > I treid make -j 30 build{world,kernel} (latest -CURRENT) on 24-core machi= ne and see poor > scalability of pmap/mtx -- more then 50% cpu spend on system time. > > pmcstat: > > @ CPU_CLK_UNHALTED_CORE [194841 samples] > > 42.65% =A0[83102] =A0 =A0_mtx_lock_sleep @ /boot/kernel/kernel > =A040.97% =A0[34051] =A0 =A0 pmap_enter > =A0100.0% =A0[34051] =A0 =A0 =A0vm_fault_hold > =A0 100.0% =A0[34051] =A0 =A0 =A0 trap_pfault > =A030.40% =A0[25262] =A0 =A0 vm_page_activate > =A0100.0% =A0[25262] =A0 =A0 =A0vm_fault_hold > =A0 100.0% =A0[25262] =A0 =A0 =A0 trap_pfault > =A018.41% =A0[15300] =A0 =A0 vm_pageq_remove > =A073.63% =A0[11266] =A0 =A0 =A0vm_page_free_toq > =A0 70.69% =A0[7964] =A0 =A0 =A0 =A0vm_object_terminate > =A0 29.31% =A0[3302] =A0 =A0 =A0 =A0vm_object_page_remove > =A026.37% =A0[4034] =A0 =A0 =A0 vm_fault_hold > =A0 100.0% =A0[4034] =A0 =A0 =A0 =A0trap_pfault > > make -j 8: > > 15.44% =A0[10740] =A0 =A0_mtx_lock_sleep @ /boot/kernel/kernel > =A038.77% =A0[4164] =A0 =A0 =A0pmap_enter > =A099.93% =A0[4161] =A0 =A0 =A0 vm_fault_hold > =A0 100.0% =A0[4161] =A0 =A0 =A0 =A0trap_pfault > =A000.07% =A0[3] =A0 =A0 =A0 =A0 =A0kmem_back > =A0 100.0% =A0[3] =A0 =A0 =A0 =A0 =A0 kmem_malloc > =A027.98% =A0[3005] =A0 =A0 =A0vm_page_activate > =A0100.0% =A0[3005] =A0 =A0 =A0 vm_fault_hold > =A0 100.0% =A0[3005] =A0 =A0 =A0 =A0trap_pfault > =A020.64% =A0[2217] =A0 =A0 =A0vm_pageq_remove > =A064.73% =A0[1435] =A0 =A0 =A0 vm_page_free_toq > =A0 63.41% =A0[910] =A0 =A0 =A0 =A0 vm_object_terminate > > make -j 4 > > 06.86% =A0[4222] =A0 =A0 pagezero @ /boot/kernel/kernel > =A098.39% =A0[4154] =A0 =A0 =A0trap_pfault > =A0100.0% =A0[4154] =A0 =A0 =A0 trap > =A001.11% =A0[47] =A0 =A0 =A0 =A0vm_fault_hold > > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd= .org" --=20 =A0 =A0=93The real damage is done by those millions who want to 'get by.' The ordinary men who just want to be left in peace. Those who don=92t want their little lives disturbed by anything bigger than themselves. Those with no sides and no causes. Those who won=92t take measure of their own strength, for fear of antagonizing their own weakness. Those who don=92t like to make waves=97or enemies. =A0 =A0Those for whom freedom, honour, truth, and principles are only literature. Those who live small, love small, die small. It=92s the reductionist approach to life: if you keep it small, you=92ll keep it under control. If you don=92t make any noise, the bogeyman won=92t find you. =A0 =A0But it=92s all an illusion, because they die too, those people who roll up their spirits into tiny little balls so as to be safe. Safe?! >From what? Life is always on the edge of death; narrow streets lead to the same place as wide avenues, and a little candle burns itself out just like a flaming torch does. =A0 =A0I choose my own way to burn.=94 =A0 =A0Sophie Scholl From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 20:36:34 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DA5E5106564A; Tue, 24 Apr 2012 20:36:34 +0000 (UTC) (envelope-from slw@zxy.spb.ru) Received: from zxy.spb.ru (zxy.spb.ru [195.70.199.98]) by mx1.freebsd.org (Postfix) with ESMTP id 8D0218FC08; Tue, 24 Apr 2012 20:36:34 +0000 (UTC) Received: from slw by zxy.spb.ru with local (Exim 4.69 (FreeBSD)) (envelope-from ) id 1SMmTq-0009Yt-N7; Wed, 25 Apr 2012 00:36:58 +0400 Date: Wed, 25 Apr 2012 00:36:58 +0400 From: Slawa Olhovchenkov To: "K. Macy" Message-ID: <20120424203658.GR32749@zxy.spb.ru> References: <20120424191415.GE76983@zxy.spb.ru> 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) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: slw@zxy.spb.ru X-SA-Exim-Scanned: No (on zxy.spb.ru); SAEximRunCond expanded to false Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org Subject: Re: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 20:36:34 -0000 On Tue, Apr 24, 2012 at 09:27:30PM +0200, K. Macy wrote: > Known problem. There is an open disagreement about how to improve the > granularity of locking in pmap. split locking to process-specific information and global information? use lock-free lists (i see TAILQ_INSERT_TAIL in pmap_enter)? sorry for stupidity, if any. From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 20:43:09 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 936D51065672; Tue, 24 Apr 2012 20:43:09 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-iy0-f182.google.com (mail-iy0-f182.google.com [209.85.210.182]) by mx1.freebsd.org (Postfix) with ESMTP id 49B5D8FC12; Tue, 24 Apr 2012 20:43:09 +0000 (UTC) Received: by iahk25 with SMTP id k25so1931506iah.13 for ; Tue, 24 Apr 2012 13:43:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=ohb6GHr2lLDYcJnPMMPkvWkN0ku6ICOfdlUtx4Plnx8=; b=OyBlTObxKz3vUz3w4HUJ9puwG16qT87OuLwtMsP2njSc+mRXbotxQw0dQ2dJRyfKVN TP+FDX/CXLa8UBQlIymH5BaJPhkC2N7QMNMsz++YwpK/LzzrbmIau6OlaAt/GYycbEqG 23vZkg93DaX7uHbL+C354GGBHpray6dMYtm/Zowgg8/0aAFOE1dDzUUQaBUxDeeJHJyT RxVC3UUJ5/9hdEuuExrp2Fdzu0d8T+kOYnLoB13X+J0gctOzNaerLVCJBrsfEkl9+BJX GGBTbc6u8y2QbuxVO2Sk3Uk+J+oxARNbsJ2y118Wvvgy69i2djoctoib/q4x7Ma332hQ XfNg== MIME-Version: 1.0 Received: by 10.42.215.68 with SMTP id hd4mr2690083icb.30.1335300188762; Tue, 24 Apr 2012 13:43:08 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.50.129.39 with HTTP; Tue, 24 Apr 2012 13:43:08 -0700 (PDT) In-Reply-To: <20120424203658.GR32749@zxy.spb.ru> References: <20120424191415.GE76983@zxy.spb.ru> <20120424203658.GR32749@zxy.spb.ru> Date: Tue, 24 Apr 2012 22:43:08 +0200 X-Google-Sender-Auth: 5_KnCTHigoY3kIAkUj0i3t1n-rs Message-ID: From: "K. Macy" To: Slawa Olhovchenkov Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org Subject: Re: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 20:43:09 -0000 No. I developed a patch from Jeffr that pushed the vm_page_lock array down in to the machine dependent code, replacing most of the uses of the single vm_page_queue_lock. However, alc doesn't like the design and has not proposed an alternative. -Kip On Tue, Apr 24, 2012 at 10:36 PM, Slawa Olhovchenkov wrote= : > On Tue, Apr 24, 2012 at 09:27:30PM +0200, K. Macy wrote: > >> Known problem. There is an open disagreement about how to improve the >> granularity of locking in pmap. > > split locking to process-specific information and global information? > use lock-free lists (i see TAILQ_INSERT_TAIL in pmap_enter)? > > sorry for stupidity, if any. --=20 =A0 =A0=93The real damage is done by those millions who want to 'get by.' The ordinary men who just want to be left in peace. Those who don=92t want their little lives disturbed by anything bigger than themselves. Those with no sides and no causes. Those who won=92t take measure of their own strength, for fear of antagonizing their own weakness. Those who don=92t like to make waves=97or enemies. =A0 =A0Those for whom freedom, honour, truth, and principles are only literature. Those who live small, love small, die small. It=92s the reductionist approach to life: if you keep it small, you=92ll keep it under control. If you don=92t make any noise, the bogeyman won=92t find you. =A0 =A0But it=92s all an illusion, because they die too, those people who roll up their spirits into tiny little balls so as to be safe. Safe?! >From what? Life is always on the edge of death; narrow streets lead to the same place as wide avenues, and a little candle burns itself out just like a flaming torch does. =A0 =A0I choose my own way to burn.=94 =A0 =A0Sophie Scholl From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 20:45:08 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C9E4A1065674; Tue, 24 Apr 2012 20:45:08 +0000 (UTC) (envelope-from slw@zxy.spb.ru) Received: from zxy.spb.ru (zxy.spb.ru [195.70.199.98]) by mx1.freebsd.org (Postfix) with ESMTP id 7C8058FC20; Tue, 24 Apr 2012 20:45:08 +0000 (UTC) Received: from slw by zxy.spb.ru with local (Exim 4.69 (FreeBSD)) (envelope-from ) id 1SMmc9-0009dG-5L; Wed, 25 Apr 2012 00:45:33 +0400 Date: Wed, 25 Apr 2012 00:45:33 +0400 From: Slawa Olhovchenkov To: "K. Macy" Message-ID: <20120424204533.GS32749@zxy.spb.ru> References: <20120424191415.GE76983@zxy.spb.ru> <20120424203658.GR32749@zxy.spb.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: slw@zxy.spb.ru X-SA-Exim-Scanned: No (on zxy.spb.ru); SAEximRunCond expanded to false Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org Subject: Re: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 20:45:08 -0000 On Tue, Apr 24, 2012 at 10:43:08PM +0200, K. Macy wrote: > No. I developed a patch from Jeffr that pushed the vm_page_lock array > down in to the machine dependent code, replacing most of the uses of > the single vm_page_queue_lock. However, alc doesn't like the design > and has not proposed an alternative. can i test this? > -Kip > > On Tue, Apr 24, 2012 at 10:36 PM, Slawa Olhovchenkov wrote: > > On Tue, Apr 24, 2012 at 09:27:30PM +0200, K. Macy wrote: > > > >> Known problem. There is an open disagreement about how to improve the > >> granularity of locking in pmap. > > > > split locking to process-specific information and global information? > > use lock-free lists (i see TAILQ_INSERT_TAIL in pmap_enter)? > > > > sorry for stupidity, if any. > > > > -- > š š?The real damage is done by those millions who want to 'get by.' > The ordinary men who just want to be left in peace. Those who don?t > want their little lives disturbed by anything bigger than themselves. > Those with no sides and no causes. Those who won?t take measure of > their own strength, for fear of antagonizing their own weakness. Those > who don?t like to make waves?or enemies. > > š šThose for whom freedom, honour, truth, and principles are only > literature. Those who live small, love small, die small. It?s the > reductionist approach to life: if you keep it small, you?ll keep it > under control. If you don?t make any noise, the bogeyman won?t find > you. > > š šBut it?s all an illusion, because they die too, those people who > roll up their spirits into tiny little balls so as to be safe. Safe?! > >From what? Life is always on the edge of death; narrow streets lead to > the same place as wide avenues, and a little candle burns itself out > just like a flaming torch does. > > š šI choose my own way to burn.? > > š šSophie Scholl From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 20:51:33 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D25F0106566C; Tue, 24 Apr 2012 20:51:33 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-gy0-f182.google.com (mail-gy0-f182.google.com [209.85.160.182]) by mx1.freebsd.org (Postfix) with ESMTP id 758CE8FC0A; Tue, 24 Apr 2012 20:51:33 +0000 (UTC) Received: by ghrr20 with SMTP id r20so929139ghr.13 for ; Tue, 24 Apr 2012 13:51:32 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=ULlfCLcWnoPGOp3nJ6HmubRexj8G1TEk8DiCxV9nw/o=; b=bdWExRXHMDIVLEzPwSaTYiC1/apajFLGmvud8vziV84agP+WRsGMDVTKajeLDqBPQv 8NoL1pCjGnk3xPRkQwvYCn2+Y+li9UUVtZQWw7LqPmcB2ZUjdhGSOqI/C1IzWJjCvCsM 04X7DzsS+oLmrXd2azP1ygokyJdeYH7JHKwKQNdDhne4FGGPWTLw+8qss1t3st0NO7PQ TbMuJN9kQu8YFNgyceQEGKfuz45kyE1whk4gIOgMNv9KKKutLgwmCW99ERopbf45dO7w shv1Tn9QJc5pPhwIIWxEnekjV//4xG0n60ljy/vSxBUU2Gbp03kYkYMV4H6wdDYEbT24 pjww== MIME-Version: 1.0 Received: by 10.50.51.197 with SMTP id m5mr11852119igo.38.1335300692474; Tue, 24 Apr 2012 13:51:32 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.50.129.39 with HTTP; Tue, 24 Apr 2012 13:51:32 -0700 (PDT) In-Reply-To: <20120424204533.GS32749@zxy.spb.ru> References: <20120424191415.GE76983@zxy.spb.ru> <20120424203658.GR32749@zxy.spb.ru> <20120424204533.GS32749@zxy.spb.ru> Date: Tue, 24 Apr 2012 22:51:32 +0200 X-Google-Sender-Auth: j6iZpRkhRYRZA-T_CBspOW-I1xI Message-ID: From: "K. Macy" To: Slawa Olhovchenkov Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org Subject: Re: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 20:51:34 -0000 It's a bit dated at this point. Nonetheless, when gitorious is able to give something other than 503 to my search queries I'll post it. On Tue, Apr 24, 2012 at 10:45 PM, Slawa Olhovchenkov wrote= : > On Tue, Apr 24, 2012 at 10:43:08PM +0200, K. Macy wrote: > >> No. I developed a patch from Jeffr that pushed the vm_page_lock array >> down in to the machine dependent code, replacing most of the uses of >> the single vm_page_queue_lock. However, alc doesn't like the design >> and has not proposed an alternative. > > can i test this? > >> -Kip >> >> On Tue, Apr 24, 2012 at 10:36 PM, Slawa Olhovchenkov wr= ote: >> > On Tue, Apr 24, 2012 at 09:27:30PM +0200, K. Macy wrote: >> > >> >> Known problem. There is an open disagreement about how to improve the >> >> granularity of locking in pmap. >> > >> > split locking to process-specific information and global information? >> > use lock-free lists (i see TAILQ_INSERT_TAIL in pmap_enter)? >> > >> > sorry for stupidity, if any. >> >> >> >> -- >> =A0 =A0?The real damage is done by those millions who want to 'get by.' >> The ordinary men who just want to be left in peace. Those who don?t >> want their little lives disturbed by anything bigger than themselves. >> Those with no sides and no causes. Those who won?t take measure of >> their own strength, for fear of antagonizing their own weakness. Those >> who don?t like to make waves?or enemies. >> >> =A0 =A0Those for whom freedom, honour, truth, and principles are only >> literature. Those who live small, love small, die small. It?s the >> reductionist approach to life: if you keep it small, you?ll keep it >> under control. If you don?t make any noise, the bogeyman won?t find >> you. >> >> =A0 =A0But it?s all an illusion, because they die too, those people who >> roll up their spirits into tiny little balls so as to be safe. Safe?! >> >From what? Life is always on the edge of death; narrow streets lead to >> the same place as wide avenues, and a little candle burns itself out >> just like a flaming torch does. >> >> =A0 =A0I choose my own way to burn.? >> >> =A0 =A0Sophie Scholl --=20 =A0 =A0=93The real damage is done by those millions who want to 'get by.' The ordinary men who just want to be left in peace. Those who don=92t want their little lives disturbed by anything bigger than themselves. Those with no sides and no causes. Those who won=92t take measure of their own strength, for fear of antagonizing their own weakness. Those who don=92t like to make waves=97or enemies. =A0 =A0Those for whom freedom, honour, truth, and principles are only literature. Those who live small, love small, die small. It=92s the reductionist approach to life: if you keep it small, you=92ll keep it under control. If you don=92t make any noise, the bogeyman won=92t find you. =A0 =A0But it=92s all an illusion, because they die too, those people who roll up their spirits into tiny little balls so as to be safe. Safe?! >From what? Life is always on the edge of death; narrow streets lead to the same place as wide avenues, and a little candle burns itself out just like a flaming torch does. =A0 =A0I choose my own way to burn.=94 =A0 =A0Sophie Scholl From owner-freebsd-performance@FreeBSD.ORG Tue Apr 24 21:22:04 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id ADE6E1065674; Tue, 24 Apr 2012 21:22:04 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-yx0-f182.google.com (mail-yx0-f182.google.com [209.85.213.182]) by mx1.freebsd.org (Postfix) with ESMTP id 4E8018FC16; Tue, 24 Apr 2012 21:22:04 +0000 (UTC) Received: by yenl9 with SMTP id l9so959924yen.13 for ; Tue, 24 Apr 2012 14:22:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=xh0JnGtjP9zvGEjHTr+fnSjTEwr3Mi3MoM3Od6rENWQ=; b=n+99r9zX6W5BXfAYc4RnRMYWw5FYozKUJPn44OD2oI7gI6kM9sINTzuDultmMFDA4o iMAUleBAvqkAIX/+KkUbRA/eSf6edmeRwuZR+3gB+wVntbPzOyAzNy3hne7XukDakTHE r0o8Y2Nn3sb1bvFqgV38jaX6Bv/Ppmm+XuEbr27GV+7wxscXyTrgw2oZIpHwQsPpjZXd F4MG7Wgwlq8nWI71df1L8iyzL+Sc9nlQkJePTB9ubgjkPwlZ+MND6uFC+VhwYeGW/kjR d2a9l2pavzrQKtR1t2PhYql7FBzYPhLHq4C5WwKnxJThIVgmL5sDjLFQzSOHf0GxsJSh Pubw== MIME-Version: 1.0 Received: by 10.50.194.232 with SMTP id hz8mr47028igc.38.1335302523296; Tue, 24 Apr 2012 14:22:03 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.50.129.39 with HTTP; Tue, 24 Apr 2012 14:22:03 -0700 (PDT) In-Reply-To: References: <20120424191415.GE76983@zxy.spb.ru> <20120424203658.GR32749@zxy.spb.ru> <20120424204533.GS32749@zxy.spb.ru> Date: Tue, 24 Apr 2012 23:22:03 +0200 X-Google-Sender-Auth: 2wZTquXOFFKxG1_wdQDhVt1Xoj8 Message-ID: From: "K. Macy" To: Slawa Olhovchenkov Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org Subject: Re: pmap and mtx scalability problem X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2012 21:22:04 -0000 You can try these. Your mileage *will* vary. https://gitorious.org/~kmm/freebsd/kmm-sandbox/commits/work/svn_release_8_1= _0_page_lock https://gitorious.org/~kmm/freebsd/kmm-sandbox/commits/work/svn_trunk_page_= lock On Tue, Apr 24, 2012 at 10:51 PM, K. Macy wrote: > It's a bit dated at this point. Nonetheless, when gitorious is able to > give something other than 503 to my search queries I'll post it. > > On Tue, Apr 24, 2012 at 10:45 PM, Slawa Olhovchenkov wro= te: >> On Tue, Apr 24, 2012 at 10:43:08PM +0200, K. Macy wrote: >> >>> No. I developed a patch from Jeffr that pushed the vm_page_lock array >>> down in to the machine dependent code, replacing most of the uses of >>> the single vm_page_queue_lock. However, alc doesn't like the design >>> and has not proposed an alternative. >> >> can i test this? >> >>> -Kip >>> >>> On Tue, Apr 24, 2012 at 10:36 PM, Slawa Olhovchenkov w= rote: >>> > On Tue, Apr 24, 2012 at 09:27:30PM +0200, K. Macy wrote: >>> > >>> >> Known problem. There is an open disagreement about how to improve th= e >>> >> granularity of locking in pmap. >>> > >>> > split locking to process-specific information and global information? >>> > use lock-free lists (i see TAILQ_INSERT_TAIL in pmap_enter)? >>> > >>> > sorry for stupidity, if any. >>> >>> >>> >>> -- >>> =A0 =A0?The real damage is done by those millions who want to 'get by.' >>> The ordinary men who just want to be left in peace. Those who don?t >>> want their little lives disturbed by anything bigger than themselves. >>> Those with no sides and no causes. Those who won?t take measure of >>> their own strength, for fear of antagonizing their own weakness. Those >>> who don?t like to make waves?or enemies. >>> >>> =A0 =A0Those for whom freedom, honour, truth, and principles are only >>> literature. Those who live small, love small, die small. It?s the >>> reductionist approach to life: if you keep it small, you?ll keep it >>> under control. If you don?t make any noise, the bogeyman won?t find >>> you. >>> >>> =A0 =A0But it?s all an illusion, because they die too, those people who >>> roll up their spirits into tiny little balls so as to be safe. Safe?! >>> >From what? Life is always on the edge of death; narrow streets lead to >>> the same place as wide avenues, and a little candle burns itself out >>> just like a flaming torch does. >>> >>> =A0 =A0I choose my own way to burn.? >>> >>> =A0 =A0Sophie Scholl > > > > -- > =A0 =A0=93The real damage is done by those millions who want to 'get by.' > The ordinary men who just want to be left in peace. Those who don=92t > want their little lives disturbed by anything bigger than themselves. > Those with no sides and no causes. Those who won=92t take measure of > their own strength, for fear of antagonizing their own weakness. Those > who don=92t like to make waves=97or enemies. > > =A0 =A0Those for whom freedom, honour, truth, and principles are only > literature. Those who live small, love small, die small. It=92s the > reductionist approach to life: if you keep it small, you=92ll keep it > under control. If you don=92t make any noise, the bogeyman won=92t find > you. > > =A0 =A0But it=92s all an illusion, because they die too, those people who > roll up their spirits into tiny little balls so as to be safe. Safe?! > From what? Life is always on the edge of death; narrow streets lead to > the same place as wide avenues, and a little candle burns itself out > just like a flaming torch does. > > =A0 =A0I choose my own way to burn.=94 > > =A0 =A0Sophie Scholl --=20 =A0 =A0=93The real damage is done by those millions who want to 'get by.' The ordinary men who just want to be left in peace. Those who don=92t want their little lives disturbed by anything bigger than themselves. Those with no sides and no causes. Those who won=92t take measure of their own strength, for fear of antagonizing their own weakness. Those who don=92t like to make waves=97or enemies. =A0 =A0Those for whom freedom, honour, truth, and principles are only literature. Those who live small, love small, die small. It=92s the reductionist approach to life: if you keep it small, you=92ll keep it under control. If you don=92t make any noise, the bogeyman won=92t find you. =A0 =A0But it=92s all an illusion, because they die too, those people who roll up their spirits into tiny little balls so as to be safe. Safe?! >From what? Life is always on the edge of death; narrow streets lead to the same place as wide avenues, and a little candle burns itself out just like a flaming torch does. =A0 =A0I choose my own way to burn.=94 =A0 =A0Sophie Scholl