From owner-freebsd-performance@FreeBSD.ORG Wed Jun 1 11:22:38 2011 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 87485106566B for ; Wed, 1 Jun 2011 11:22:38 +0000 (UTC) (envelope-from avg@FreeBSD.org) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id C24608FC13 for ; Wed, 1 Jun 2011 11:22:37 +0000 (UTC) Received: from odyssey.starpoint.kiev.ua (alpha-e.starpoint.kiev.ua [212.40.38.101]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id OAA02829 for ; Wed, 01 Jun 2011 14:11:43 +0300 (EEST) (envelope-from avg@FreeBSD.org) Message-ID: <4DE61E6F.1010209@FreeBSD.org> Date: Wed, 01 Jun 2011 14:11:43 +0300 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.17) Gecko/20110504 Lightning/1.0b2 Thunderbird/3.1.10 MIME-Version: 1.0 To: freebsd-performance@FreeBSD.org X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Wed, 01 Jun 2011 11:30:36 +0000 Cc: Subject: tlb shootdown 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: Wed, 01 Jun 2011 11:22:38 -0000 Anyone knows of a benchmark/test that can measure/demonstrate difference in tlb shootdown performance (or its lack)? -- Andriy Gapon From owner-freebsd-performance@FreeBSD.ORG Thu Jun 2 12:17:20 2011 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 461B41065676 for ; Thu, 2 Jun 2011 12:17:20 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from lo.gmane.org (lo.gmane.org [80.91.229.12]) by mx1.freebsd.org (Postfix) with ESMTP id 049C78FC18 for ; Thu, 2 Jun 2011 12:17:19 +0000 (UTC) Received: from list by lo.gmane.org with local (Exim 4.69) (envelope-from ) id 1QS6bR-00077v-PV for freebsd-performance@freebsd.org; Thu, 02 Jun 2011 14:02:17 +0200 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Thu, 02 Jun 2011 14:02:17 +0200 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Thu, 02 Jun 2011 14:02:17 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-performance@freebsd.org From: Ivan Voras Date: Thu, 02 Jun 2011 14:02:06 +0200 Lines: 7 Message-ID: References: <4DE61E6F.1010209@FreeBSD.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@dough.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101102 Thunderbird/3.1.6 In-Reply-To: <4DE61E6F.1010209@FreeBSD.org> X-Enigmail-Version: 1.1.2 Subject: Re: tlb shootdown 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: Thu, 02 Jun 2011 12:17:20 -0000 On 01/06/2011 13:11, Andriy Gapon wrote: > > Anyone knows of a benchmark/test that can measure/demonstrate difference in tlb > shootdown performance (or its lack)? The "tlb" utility from lmbench may help you. From owner-freebsd-performance@FreeBSD.ORG Thu Jun 2 14:24:50 2011 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 4B3CE106566B for ; Thu, 2 Jun 2011 14:24:50 +0000 (UTC) (envelope-from avg@FreeBSD.org) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 6B68F8FC0A for ; Thu, 2 Jun 2011 14:24:49 +0000 (UTC) Received: from odyssey.starpoint.kiev.ua (alpha-e.starpoint.kiev.ua [212.40.38.101]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id RAA26623; Thu, 02 Jun 2011 17:24:47 +0300 (EEST) (envelope-from avg@FreeBSD.org) Message-ID: <4DE79D2F.8050907@FreeBSD.org> Date: Thu, 02 Jun 2011 17:24:47 +0300 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.17) Gecko/20110504 Lightning/1.0b2 Thunderbird/3.1.10 MIME-Version: 1.0 To: Ivan Voras References: <4DE61E6F.1010209@FreeBSD.org> In-Reply-To: X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Thu, 02 Jun 2011 15:23:22 +0000 Cc: freebsd-performance@FreeBSD.org Subject: Re: tlb shootdown 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: Thu, 02 Jun 2011 14:24:50 -0000 on 02/06/2011 15:02 Ivan Voras said the following: > On 01/06/2011 13:11, Andriy Gapon wrote: >> >> Anyone knows of a benchmark/test that can measure/demonstrate difference in tlb >> shootdown performance (or its lack)? > > The "tlb" utility from lmbench may help you. Just because it's named tlb and I asked for tlb something? :) tlb - TLB size and latency benchmark ... tlb tries to determine the size, in pages, of the TLB. The largest amount of memory it will examine is len bytes. ... Once the TLB boundary is located tlb reports the TLB miss latency as the TLB latency for twice as many pages as the TLB can hold. I am not this will tell anything about TLB _shootdown_ performance of SMP systems. Perhaps I wasn't specific enough in my original question. -- Andriy Gapon From owner-freebsd-performance@FreeBSD.ORG Thu Jun 2 15:28:13 2011 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 4686F106564A; Thu, 2 Jun 2011 15:28:13 +0000 (UTC) (envelope-from ivoras@gmail.com) Received: from mail-wy0-f182.google.com (mail-wy0-f182.google.com [74.125.82.182]) by mx1.freebsd.org (Postfix) with ESMTP id A523D8FC1A; Thu, 2 Jun 2011 15:28:12 +0000 (UTC) Received: by wyf23 with SMTP id 23so958360wyf.13 for ; Thu, 02 Jun 2011 08:28:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:references:user-agent:in-reply-to:mime-version :content-type:subject:from:date:to:cc:message-id; bh=Dx2TkV7hLK9i0pEUcOifdZ8zBZYQ3JTI3F2GsQsOWSc=; b=J5609mqMWx9b/hN/tHgxW+qqdr4NFw+0+3bKHCBxq/J7+W9JxmFv5xgqp8fZJSVket ouIcdaWyVDqfAeEy8cQFA5GXuLLZhcOzIvt+2aUZCOwakx2kP4Uujaz435Gj83kzpdo/ xuz2KwuEr4B2goF0c5Ogr5rD3lEY5QYYKUg/8= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=references:user-agent:in-reply-to:mime-version:content-type:subject :from:date:to:cc:message-id; b=Wnc4nTuzG5hUaXYWtbaj7c0hBQW4t6TqtJiVK84064jgEmDlT+h3QqL0OSQahMF42t z6PUy9K1nhfJKT6uOSt0yu656r8ZZe41dJD3WI88+/4zsUqDLXZVmQ6B3bH9JiV/KL8k 5rDtwH8przgRCtK2MJoHI6Puz4x08UhprUy+g= Received: by 10.227.178.203 with SMTP id bn11mr879332wbb.51.1307028491579; Thu, 02 Jun 2011 08:28:11 -0700 (PDT) Received: from [212.15.173.107] ([212.15.173.107]) by mx.google.com with ESMTPS id ej7sm461706wbb.36.2011.06.02.08.28.08 (version=SSLv3 cipher=OTHER); Thu, 02 Jun 2011 08:28:10 -0700 (PDT) References: <4DE61E6F.1010209@FreeBSD.org> <4DE79D2F.8050907@FreeBSD.org> User-Agent: K-9 Mail for Android In-Reply-To: <4DE79D2F.8050907@FreeBSD.org> MIME-Version: 1.0 From: Ivan Voras Date: Thu, 02 Jun 2011 17:28:04 +0200 To: Andriy Gapon Message-ID: <72d97a0b-5ad9-4405-9b0a-832ba5a872ee@email.android.com> X-Mailman-Approved-At: Thu, 02 Jun 2011 15:36:39 +0000 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: freebsd-performance@FreeBSD.org Subject: Re: tlb shootdown 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: Thu, 02 Jun 2011 15:28:13 -0000 On the second reading, if you are asking how fast a shootdown operation itself is, then yes, it will probably not help you :) -- Sent from my Android phone, please excuse my brevity. Andriy Gapon wrote: on 02/06/2011 15:02 Ivan Voras said the following: > On 01/06/2011 13:11, Andriy Gapon wrote: >> >> Anyone knows of a benchmark/test that can measure/demonstrate difference in tlb >> shootdown performance (or its lack)? > > The "tlb" utility from lmbench may help you. Just because it's named tlb and I asked for tlb something? :) tlb - TLB size and latency benchmark ... tlb tries to determine the size, in pages, of the TLB. The largest amount of memory it will examine is len bytes. ... Once the TLB boundary is located tlb reports the TLB miss latency as the TLB latency for twice as many pages as the TLB can hold. I am not this will tell anything about TLB _shootdown_ performance of SMP systems. Perhaps I wasn't specific enough in my original question. -- Andriy Gapon From owner-freebsd-performance@FreeBSD.ORG Thu Jun 2 15:40:01 2011 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 8F9A21065670; Thu, 2 Jun 2011 15:40:01 +0000 (UTC) (envelope-from ivoras@gmail.com) Received: from mail-yi0-f54.google.com (mail-yi0-f54.google.com [209.85.218.54]) by mx1.freebsd.org (Postfix) with ESMTP id 32BFC8FC15; Thu, 2 Jun 2011 15:40:01 +0000 (UTC) Received: by yie12 with SMTP id 12so610909yie.13 for ; Thu, 02 Jun 2011 08:40:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:sender:in-reply-to:references:from :date:x-google-sender-auth:message-id:subject:to:cc:content-type; bh=gZ9YV/NMgeOG7ai+jhDsHgW3W0NNQX7ebUNmshtMQcs=; b=G+xyWI8IpU6HI7zbiOLQBBepAVjCjsSMwM6ij1DnDLpB33aaZO66oBZa+ZoKqQ7UNA GjXjLNKeqq+2WVhSkRkPpbh7y/XSi4J8rmhNsxb6mTaKEKwf/QQvq2d+GreFyEnMgZmM 9GUNp1kiSfh4ywRHdo3H+KxpVvntrLZp7IZok= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:from:date :x-google-sender-auth:message-id:subject:to:cc:content-type; b=ChIB/sXXz7vxfJ4MnVgSohrkoru/RCHLleGJYnqYjG39oJTdhWqfQk8N4V8Qrshw3s Xq7qM8Lv1gMKyfTh+j20jesJeB6glENBpnb06V6UgjSGraORkWUPvFZeT1iJwi7tXnv+ InpwAgqJqMKhjxj3bcnIIUNWBqm9iX13mi0Ws= Received: by 10.91.182.3 with SMTP id j3mr783802agp.66.1307027671258; Thu, 02 Jun 2011 08:14:31 -0700 (PDT) MIME-Version: 1.0 Sender: ivoras@gmail.com Received: by 10.100.3.15 with HTTP; Thu, 2 Jun 2011 08:13:51 -0700 (PDT) In-Reply-To: <4DE79D2F.8050907@FreeBSD.org> References: <4DE61E6F.1010209@FreeBSD.org> <4DE79D2F.8050907@FreeBSD.org> From: Ivan Voras Date: Thu, 2 Jun 2011 17:13:51 +0200 X-Google-Sender-Auth: I1ZgZ0ODQ7ZCU7Pw1GazxsPNTPM Message-ID: To: Andriy Gapon Content-Type: text/plain; charset=UTF-8 Cc: freebsd-performance@freebsd.org Subject: Re: tlb shootdown 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: Thu, 02 Jun 2011 15:40:01 -0000 On 2 June 2011 16:24, Andriy Gapon wrote: > on 02/06/2011 15:02 Ivan Voras said the following: >> On 01/06/2011 13:11, Andriy Gapon wrote: >>> >>> Anyone knows of a benchmark/test that can measure/demonstrate difference in tlb >>> shootdown performance (or its lack)? >> >> The "tlb" utility from lmbench may help you. > > Just because it's named tlb and I asked for tlb something? :) No, because it satisfies one thing you asked for: measuring tlb shootdown performance: ./tlb -c tlb: 16 pages 0.75218 nanoseconds If you look at the code, this is probably exactly what you need: the difference between the case with tlb misses and without. From owner-freebsd-performance@FreeBSD.ORG Thu Jun 2 20:02:31 2011 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 7E4E21065670 for ; Thu, 2 Jun 2011 20:02:31 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from mail.zoral.com.ua (mx0.zoral.com.ua [91.193.166.200]) by mx1.freebsd.org (Postfix) with ESMTP id EFF3F8FC0C for ; Thu, 2 Jun 2011 20:02:30 +0000 (UTC) Received: from deviant.kiev.zoral.com.ua (root@deviant.kiev.zoral.com.ua [10.1.1.148]) by mail.zoral.com.ua (8.14.2/8.14.2) with ESMTP id p52JUL5f014045 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Thu, 2 Jun 2011 22:30:21 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: from deviant.kiev.zoral.com.ua (kostik@localhost [127.0.0.1]) by deviant.kiev.zoral.com.ua (8.14.4/8.14.4) with ESMTP id p52JUL6B008035; Thu, 2 Jun 2011 22:30:21 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by deviant.kiev.zoral.com.ua (8.14.4/8.14.4/Submit) id p52JUJic008034; Thu, 2 Jun 2011 22:30:19 +0300 (EEST) (envelope-from kostikbel@gmail.com) X-Authentication-Warning: deviant.kiev.zoral.com.ua: kostik set sender to kostikbel@gmail.com using -f Date: Thu, 2 Jun 2011 22:30:19 +0300 From: Kostik Belousov To: Andriy Gapon Message-ID: <20110602193019.GI48734@deviant.kiev.zoral.com.ua> References: <4DE61E6F.1010209@FreeBSD.org> <4DE79D2F.8050907@FreeBSD.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="5OeNRVRLQ41UuqCe" Content-Disposition: inline In-Reply-To: <4DE79D2F.8050907@FreeBSD.org> User-Agent: Mutt/1.4.2.3i X-Virus-Scanned: clamav-milter 0.95.2 at skuns.kiev.zoral.com.ua X-Virus-Status: Clean X-Spam-Status: No, score=-3.3 required=5.0 tests=ALL_TRUSTED,AWL,BAYES_00, DNS_FROM_OPENWHOIS autolearn=no version=3.2.5 X-Spam-Checker-Version: SpamAssassin 3.2.5 (2008-06-10) on skuns.kiev.zoral.com.ua Cc: freebsd-performance@freebsd.org, Ivan Voras Subject: Re: tlb shootdown 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: Thu, 02 Jun 2011 20:02:31 -0000 --5OeNRVRLQ41UuqCe Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Jun 02, 2011 at 05:24:47PM +0300, Andriy Gapon wrote: > on 02/06/2011 15:02 Ivan Voras said the following: > > On 01/06/2011 13:11, Andriy Gapon wrote: > >> > >> Anyone knows of a benchmark/test that can measure/demonstrate differen= ce in tlb > >> shootdown performance (or its lack)? > >=20 > > The "tlb" utility from lmbench may help you. >=20 > Just because it's named tlb and I asked for tlb something? :) >=20 > tlb - TLB size and latency benchmark > ... > tlb tries to determine the size, in pages, of the TLB. The largest > amount of memory it will examine is len bytes. > ... > Once the TLB boundary is located tlb reports the TLB miss latency as > the TLB latency for twice as many pages as the TLB can hold. >=20 > I am not this will tell anything about TLB _shootdown_ performance of SMP= systems. > Perhaps I wasn't specific enough in my original question. Apparently, lmbench does not install a single multithreaded binary. So, despite my expectation, it is not useful for what you have asked. I think, the working scenario would be to have multithreaded process, each thread of which does mmap, then accesses the mmaped pages, then unmaps the region. You would count the number of accesses per time unit, the more the better. --5OeNRVRLQ41UuqCe Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iEYEARECAAYFAk3n5MoACgkQC3+MBN1Mb4iEqQCgjApNgtBmqYWGFblGTZ2KmpuC dpwAn2oWNA6WchRwnpC/8Di99NfOZTK+ =8vTi -----END PGP SIGNATURE----- --5OeNRVRLQ41UuqCe--