From owner-freebsd-performance@FreeBSD.ORG Fri Nov 2 19:00:48 2007 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 8C24216A47C for ; Fri, 2 Nov 2007 19:00:48 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from webaccess-cl.virtdom.com (webaccess-cl.virtdom.com [216.240.101.25]) by mx1.freebsd.org (Postfix) with ESMTP id 332E713C478 for ; Fri, 2 Nov 2007 19:00:48 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from [192.168.1.100] (cpe-24-94-75-93.hawaii.res.rr.com [24.94.75.93]) (authenticated bits=0) by webaccess-cl.virtdom.com (8.13.6/8.13.6) with ESMTP id lA2INmpq003885 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NO); Fri, 2 Nov 2007 14:23:50 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Fri, 2 Nov 2007 10:25:52 -0800 (PST) From: Jeff Roberson X-X-Sender: jroberson@10.0.0.1 To: Josh Carroll In-Reply-To: <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> Message-ID: <20071102102331.G544@10.0.0.1> References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 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: Fri, 02 Nov 2007 19:00:48 -0000 On Thu, 25 Oct 2007, Josh Carroll wrote: >> I'm confident that we can improve things. It will probably not make the >> cut for 7.0 since it will be too disruptive. I'm sure it can be >> backported before 7.1 when ULE is likely to become the default. > > That sounds great! I figured it was something that would have to wait > until 7.0 released. I completely understand that. > >> I hope that we can continue to work together to verify any fixes I may >> come up with. > > Absolutely! Just let me know how I can help. If you need a guinea > pig...er...tester :) I'll be glad to help! > Could you try spot checking a couple of tests with kern.sched.slice set to half its present value? 4BSD on average will use half the slice that ULE will by default. > Another thing I noticed between ULE and 4BSD is my core temperatures > seem erratic on ULE. I use RRDtool with the new coretemp(4) feature > and noticed the temperatures are spiking a lot with ULE, and generally > slightly higher than when running a 4BSD kernel. I don't know if > that's significant or not. Just something I noticed when I modified my > RRD scripts to use coretemp. > > For a side-by-side comparison, see this page: > > http://pflog.net/~floyd/fbsd_sched.html This is interesting. I have had a couple of laptop users report success in using lower power saving modes with ULE. Are these core temp observations repeatable? Thanks, Jeff > > Thanks again for all your help! Please let me know if/when I can do > anything else to help out. > > Regards, > Josh > _______________________________________________ > 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" > From owner-freebsd-performance@FreeBSD.ORG Fri Nov 2 19:49:41 2007 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 08B5816A41A for ; Fri, 2 Nov 2007 19:49:41 +0000 (UTC) (envelope-from nevans@talkpoint.com) Received: from mailbox.talkpoint.com (mailbox.talkpoint.com [204.141.15.162]) by mx1.freebsd.org (Postfix) with ESMTP id 9B11213C48D for ; Fri, 2 Nov 2007 19:49:40 +0000 (UTC) (envelope-from nevans@talkpoint.com) Received: from localhost (localhost [127.0.0.1]) by mailbox.talkpoint.com (Postfix) with ESMTP id 06D58458004; Fri, 2 Nov 2007 15:48:49 -0400 (EDT) X-Virus-Scanned: amavisd-new at X-Spam-Flag: NO X-Spam-Score: -2.466 X-Spam-Level: X-Spam-Status: No, score=-2.466 tagged_above=-10 required=5 tests=[AWL=0.133, BAYES_00=-2.599] Received: from mailbox.talkpoint.com ([127.0.0.1]) by localhost (mailbox.talkpoint.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id JG7Foq2pOuKH; Fri, 2 Nov 2007 15:48:47 -0400 (EDT) Received: from pleiades.nextvenue.com (pleiades.nextvenue.com [204.141.15.194]) by mailbox.talkpoint.com (Postfix) with ESMTP id 08EB9458002; Fri, 2 Nov 2007 15:48:47 -0400 (EDT) Date: Fri, 2 Nov 2007 15:48:00 -0400 From: Nick Evans To: Jeff Roberson Message-ID: <20071102154800.3ae9ac99@pleiades.nextvenue.com> In-Reply-To: <20071102102331.G544@10.0.0.1> References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> X-Mailer: Claws Mail 2.8.0 (GTK+ 2.10.9; i386-portbld-freebsd7.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Josh Carroll , freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 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: Fri, 02 Nov 2007 19:49:41 -0000 > This is interesting. I have had a couple of laptop users report success > in using lower power saving modes with ULE. Are these core temp > observations repeatable? > > Thanks, > Jeff > > > > > Thanks again for all your help! Please let me know if/when I can do > > anything else to help out. > > > > Regards, > > Josh > > _______________________________________________ > > 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" > > > _______________________________________________ > 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" After this was mentioned I tried coretemp on my 8-core system and am seeing the same behavior. Idle: dev.cpu.0.temperature: 48 dev.cpu.1.temperature: 45 dev.cpu.2.temperature: 41 dev.cpu.3.temperature: 41 dev.cpu.4.temperature: 44 dev.cpu.5.temperature: 44 dev.cpu.6.temperature: 41 dev.cpu.7.temperature: 42 After 10-15 minutes of 8 distributed.net crunchers running: dev.cpu.0.temperature: 63 dev.cpu.1.temperature: 59 dev.cpu.2.temperature: 55 dev.cpu.3.temperature: 54 dev.cpu.4.temperature: 58 dev.cpu.5.temperature: 59 dev.cpu.6.temperature: 56 dev.cpu.7.temperature: 56 Interesting distribution. Cores 2, 3, 6 and 7 consistently run cooler than 0, 1, 4 and 5. This behavior has been consistent since I started looking at it a few days ago. Is there anyway to tell which package a particular core is attached to or is it sequential 0-3 on package 1, 4-7 on package 2? Nick From owner-freebsd-performance@FreeBSD.ORG Fri Nov 2 20:13:19 2007 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 306C816A418 for ; Fri, 2 Nov 2007 20:13:19 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.181]) by mx1.freebsd.org (Postfix) with ESMTP id DD7DD13C4B5 for ; Fri, 2 Nov 2007 20:13:18 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: by py-out-1112.google.com with SMTP id u77so1796909pyb for ; Fri, 02 Nov 2007 13:12:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=8xeLoFzt8UJ5dZCqOvAZiKipzUTu0zXXV4nYwHYKolw=; b=Dx0hICtCsGLYu/yrzLFUrR2UkcGraT5wtC5Y+W/+idRK2Ke3uGG8DbmTk3Dyv+M+Wu0HoM0D9NNDTLiC+01TG5P6hdxQD5HzLFNtzuq+xQJeh12aXcSzFqwXsu6LLPOLA4UNZK9Sm1O0aeeV2V3CG78kqid7vjF9pn1Liwz8ROY= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=bN+iVdK4HtCObUBjQNIZixqm2eMf+R8We7is9jTONT6u7wNAQgprbeA/uozcDlsUWItfNWuv66YQ72rPVDl6JdedGQdMiQWmAsArpN4nH67PHWT6A/z6gcT9oIx+rw5zO40eYGdxaJDL/ykB9WSE2QNMOhmxIEefeMu9vbIz+kQ= Received: by 10.35.78.9 with SMTP id f9mr2449021pyl.1194033988925; Fri, 02 Nov 2007 13:06:28 -0700 (PDT) Received: by 10.35.110.17 with HTTP; Fri, 2 Nov 2007 13:06:28 -0700 (PDT) Message-ID: <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> Date: Fri, 2 Nov 2007 16:06:28 -0400 From: "Josh Carroll" To: "Jeff Roberson" In-Reply-To: <20071102102331.G544@10.0.0.1> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: josh.carroll@gmail.com List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 Nov 2007 20:13:19 -0000 > Could you try spot checking a couple of tests with kern.sched.slice set to > half its present value? 4BSD on average will use half the slice that ULE > will by default. The initial value was 13, and I changed it to 7. Here is the time result for the ffmpeg run: 13: 1:39.09 7: 1:37.01 I also ran it with 4BSD again, as I think I recompiled ffmpeg since my previous testing. It ran in: 1:35.29 So the difference in this workload is only 2.63% when I change the slice value to 7. I will re-run my super-smack testing as well and reply with the results. > This is interesting. I have had a couple of laptop users report success > in using lower power saving modes with ULE. Are these core temp > observations repeatable? Yes, seem to be. I notice the trend in the graphs whenever I'm booted into the ULE kernel for long enough to see a few hours' of data. Thanks, Josh From owner-freebsd-performance@FreeBSD.ORG Fri Nov 2 23:31:10 2007 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 4DB5F16A418 for ; Fri, 2 Nov 2007 23:31:10 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from webaccess-cl.virtdom.com (webaccess-cl.virtdom.com [216.240.101.25]) by mx1.freebsd.org (Postfix) with ESMTP id EDCD113C4AC for ; Fri, 2 Nov 2007 23:31:09 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from [192.168.1.100] (cpe-24-94-75-93.hawaii.res.rr.com [24.94.75.93]) (authenticated bits=0) by webaccess-cl.virtdom.com (8.13.6/8.13.6) with ESMTP id lA2N2l0Z072611 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NO); Fri, 2 Nov 2007 19:02:49 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Fri, 2 Nov 2007 15:04:50 -0800 (PST) From: Jeff Roberson X-X-Sender: jroberson@10.0.0.1 To: Josh Carroll In-Reply-To: <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> Message-ID: <20071102150028.R544@10.0.0.1> References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 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: Fri, 02 Nov 2007 23:31:10 -0000 On Fri, 2 Nov 2007, Josh Carroll wrote: >> Could you try spot checking a couple of tests with kern.sched.slice set to >> half its present value? 4BSD on average will use half the slice that ULE >> will by default. > > The initial value was 13, and I changed it to 7. Here is the time > result for the ffmpeg run: > > 13: 1:39.09 > 7: 1:37.01 > > I also ran it with 4BSD again, as I think I recompiled ffmpeg since my > previous testing. It ran in: > > 1:35.29 > > So the difference in this workload is only 2.63% when I change the > slice value to 7. I will re-run my super-smack testing as well and > reply with the results. Thank you, that was very useful. I may have something to test very soon. I have a patch that attempts to limit the maximum latency a timesharing thread will see based on the cpu load. It does this by scaling down the slice as the system becomes overloaded. How many ffmpeg instances per cpu core were you running? It's not clear to me why a shorter slice would help if it's 1cpu:1core unless ULE is somehow letting idle pagezero run away and do things when it shouldn't. > >> This is interesting. I have had a couple of laptop users report success >> in using lower power saving modes with ULE. Are these core temp >> observations repeatable? > > Yes, seem to be. I notice the trend in the graphs whenever I'm booted > into the ULE kernel for long enough to see a few hours' of data. What would be interesting to know is if the sum of the temperatures is any different. 4BSD gets a much more random distribution of load because a thread is run on whatever cpu context switches next. ULE will have specific load patterns since it scans lists of cpus in a fixed order to assign load. So that means it prefers to run on lower numbered cpus if they are idle. This should have a side effect of allowing unused cores to powerdown more frequently than with 4BSD although I have not verified this in practice. Jeff > > Thanks, > Josh > _______________________________________________ > 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" > From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 03:30:36 2007 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 A2C2316A421 for ; Sat, 3 Nov 2007 03:30:36 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.181]) by mx1.freebsd.org (Postfix) with ESMTP id 658C113C48E for ; Sat, 3 Nov 2007 03:30:35 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: by py-out-1112.google.com with SMTP id u77so1959153pyb for ; Fri, 02 Nov 2007 20:30:15 -0700 (PDT) Received: by 10.35.27.1 with SMTP id e1mr2790016pyj.1194053998073; Fri, 02 Nov 2007 18:39:58 -0700 (PDT) Received: by 10.35.110.17 with HTTP; Fri, 2 Nov 2007 18:39:58 -0700 (PDT) Message-ID: <8cb6106e0711021839i4714bdfbh74d412b3e14e808@mail.gmail.com> Date: Fri, 2 Nov 2007 21:39:58 -0400 From: "Josh Carroll" To: "Jeff Roberson" In-Reply-To: <20071102150028.R544@10.0.0.1> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: josh.carroll@gmail.com List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 03 Nov 2007 03:30:36 -0000 > Thank you, that was very useful. I may have something to test very soon. Sounds great Jeff, just say the word when you need someone to do the testing. I'll be glad to help! > What would be interesting to know is if the sum of the temperatures is any > different. 4BSD gets a much more random distribution of load because a > thread is run on whatever cpu context switches next. ULE will have > specific load patterns since it scans lists of cpus in a fixed order to > assign load. That seems to correlate with what I'm seeing, since the core that is "spiking" is cpu0. I will write a little perl script to calculate the sum periodically and record that. You're right, the one core may be increasing 1-2 C periodically, but the other cores may remain lower. I can definitely get you some numbers here. So I went ahead and ran sysbench to see if changing the kern.sched.slice value affected that (which I hear is a much more accurate benchmark of real world MySQL performance than, say, supersmack). There is a slight hit with the lower slice value, though it's minimal. Although with 4 threads, the lower slice value actually increases performance slightly. Here are the results (with 4BSD as a baseline): 4bsd ule.13 ule.7 2263.6 2250.36 2265.67 2181.18 2310.02 2300.25 2137.87 2304.04 2269.54 2100.41 2252.04 2249.26 buildworld isn't cooperating for me, but once I iron that out, I'll post some results there as well :) Thanks once again for all your efforts Jeff. I (and I'm sure others) really appreciate your work. Regards, Josh From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 20:18:17 2007 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 AA99116A419 for ; Sat, 3 Nov 2007 20:18:17 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from webaccess-cl.virtdom.com (webaccess-cl.virtdom.com [216.240.101.25]) by mx1.freebsd.org (Postfix) with ESMTP id 68AAA13C4A8 for ; Sat, 3 Nov 2007 20:18:17 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from [192.168.1.100] (cpe-24-94-75-93.hawaii.res.rr.com [24.94.75.93]) (authenticated bits=0) by webaccess-cl.virtdom.com (8.13.6/8.13.6) with ESMTP id lA3KHZel042666 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NO); Sat, 3 Nov 2007 16:17:37 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Sat, 3 Nov 2007 12:19:35 -0800 (PST) From: Jeff Roberson X-X-Sender: jroberson@10.0.0.1 To: Josh Carroll In-Reply-To: <8cb6106e0711031227t1e829969s2e6062e1db5167af@mail.gmail.com> Message-ID: <20071103121921.M544@10.0.0.1> References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> <8cb6106e0711021839i4714bdfbh74d412b3e14e808@mail.gmail.com> <8cb6106e0711031227t1e829969s2e6062e1db5167af@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 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: Sat, 03 Nov 2007 20:18:17 -0000 On Sat, 3 Nov 2007, Josh Carroll wrote: >> buildworld isn't cooperating for me, but once I iron that out, I'll >> post some results there as well :) > > I was able to get buildworld compiling ok and here are the results: > > 4BSD ULE.13 ULE.7 > 13:24.73 13:44.28 13:38.85 > > Only a 1.75% difference when the slice value is set to 7. > What was the -j value and number of processors? > If anyone has suggestions for other benchmarks to run for different > workloads to test, let me know and I'd be happy to run it for the > above 3 configurations. > > Josh > From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 20:31:22 2007 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 5BCDE16A420 for ; Sat, 3 Nov 2007 20:31:22 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.177]) by mx1.freebsd.org (Postfix) with ESMTP id 01E0E13C4A6 for ; Sat, 3 Nov 2007 20:31:21 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: by py-out-1112.google.com with SMTP id u77so2309003pyb for ; Sat, 03 Nov 2007 13:31:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=AmlvtV3/WqfJlN16/vK7WDE4Q9n0gcReMO7rLvcsJbo=; b=Zb0jTAYHLgZ4k1BqTmSh/mnBYDKmiChca9+QmsgD7dEMHU+p+Mu3yUJtgfFqbfPajSwwXu/tMV5CPKqmAudsWnOzcXLbeFu1S95FV1ZlM7x0vN89iekdH4tS3TsfhFAaqfnQqvY8nsmmvvDYj+b6fgyrLRfGjzoALU16TzkkmDc= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=a5UiXIQ6C5FQaAgE0bcTW9Tl6NlXby5WZN33PBqaQ5dTcF/nWicyU0jOZf/sVh3mmkBmX4Re1LmIfjvW2YWQTiwO8n8OTVrPY17RrDVj7pI9D6K81TnqHRfU8dZHAjb+rldExzH8gE3g9+H+rVnse4D7X23ok332IAP/NpnfcHs= Received: by 10.35.128.1 with SMTP id f1mr3738577pyn.1194118056022; Sat, 03 Nov 2007 12:27:36 -0700 (PDT) Received: by 10.35.110.17 with HTTP; Sat, 3 Nov 2007 12:27:35 -0700 (PDT) Message-ID: <8cb6106e0711031227t1e829969s2e6062e1db5167af@mail.gmail.com> Date: Sat, 3 Nov 2007 15:27:35 -0400 From: "Josh Carroll" To: "Jeff Roberson" In-Reply-To: <8cb6106e0711021839i4714bdfbh74d412b3e14e808@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> <8cb6106e0711021839i4714bdfbh74d412b3e14e808@mail.gmail.com> Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: josh.carroll@gmail.com List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 03 Nov 2007 20:31:22 -0000 > buildworld isn't cooperating for me, but once I iron that out, I'll > post some results there as well :) I was able to get buildworld compiling ok and here are the results: 4BSD ULE.13 ULE.7 13:24.73 13:44.28 13:38.85 Only a 1.75% difference when the slice value is set to 7. If anyone has suggestions for other benchmarks to run for different workloads to test, let me know and I'd be happy to run it for the above 3 configurations. Josh From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 22:00:32 2007 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 C087916A421 for ; Sat, 3 Nov 2007 22:00:32 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from webaccess-cl.virtdom.com (webaccess-cl.virtdom.com [216.240.101.25]) by mx1.freebsd.org (Postfix) with ESMTP id 27C1313C4A6 for ; Sat, 3 Nov 2007 22:00:32 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from [192.168.1.100] (cpe-24-94-75-93.hawaii.res.rr.com [24.94.75.93]) (authenticated bits=0) by webaccess-cl.virtdom.com (8.13.6/8.13.6) with ESMTP id lA3Lc5Mj054860 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NO); Sat, 3 Nov 2007 17:38:07 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Sat, 3 Nov 2007 13:40:05 -0800 (PST) From: Jeff Roberson X-X-Sender: jroberson@10.0.0.1 To: Josh Carroll In-Reply-To: <8cb6106e0711031416l4183e2beueb87fade0d56f504@mail.gmail.com> Message-ID: <20071103133711.Q544@10.0.0.1> References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> <8cb6106e0711021839i4714bdfbh74d412b3e14e808@mail.gmail.com> <8cb6106e0711031227t1e829969s2e6062e1db5167af@mail.gmail.com> <20071103121921.M544@10.0.0.1> <8cb6106e0711031416l4183e2beueb87fade0d56f504@mail.gmail.com> MIME-Version: 1.0 Content-Type: MULTIPART/MIXED; BOUNDARY="0-298094039-1194126005=:544" Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 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: Sat, 03 Nov 2007 22:00:32 -0000 This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. --0-298094039-1194126005=:544 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed On Sat, 3 Nov 2007, Josh Carroll wrote: >> What was the -j value and number of processors? > > -j 8. > > I did the following (one warm up, 3 times in a row after that, averaged): > > cd /usr/src > rm -rf /usr/obj/* > make clean > time make -j8 -DNOCLEAN buildworld > > The system is a Q6600, so 4 cores. Josh, thanks for your help so far. This has been very useful. I have attached a patch which does three basic things that might improve these benchmarks: 1) Improves context switch time by shuffling around some priority computation work to happen far less frequently. 2) Dynamically adjusts slice sizes to respond to load. With low load kern.sched.slice is used but this is scaled down to kern.sched.slice_min when there is too much work on the queue. This also changes the default slice size down to 8 stathz ticks. 3) Improves the load balancer to not just consider the number of runnable threads but how much work they each might do. Any testing you can run this through is appreciated. Anyone else lurking in this thread who would like to is also welcome to report back findings. Thanks, Jeff > > Thanks, > Josh > --0-298094039-1194126005=:544 Content-Type: TEXT/x-diff; charset=US-ASCII; name=uleslice.diff Content-Transfer-Encoding: BASE64 Content-ID: <20071103134005.R544@10.0.0.1> Content-Description: Content-Disposition: attachment; filename=uleslice.diff SW5kZXg6IHNjaGVkX3VsZS5jDQo9PT09PT09PT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09DQpS Q1MgZmlsZTogL2hvbWUvbmN2cy9zcmMvc3lzL2tlcm4vc2NoZWRfdWxlLmMs dg0KcmV0cmlldmluZyByZXZpc2lvbiAxLjIxNg0KZGlmZiAtdSAtcjEuMjE2 IHNjaGVkX3VsZS5jDQotLS0gc2NoZWRfdWxlLmMJMjMgT2N0IDIwMDcgMDA6 NTI6MjQgLTAwMDAJMS4yMTYNCisrKyBzY2hlZF91bGUuYwkzIE5vdiAyMDA3 IDIxOjM2OjI3IC0wMDAwDQpAQCAtODgsNyArODgsOCBAQA0KIAlzaG9ydAkJ dHNfZmxhZ3M7CS8qIFRTRl8qIGZsYWdzLiAqLw0KIAl1X2NoYXIJCXRzX3Jx aW5kZXg7CS8qIFJ1biBxdWV1ZSBpbmRleC4gKi8NCiAJdV9jaGFyCQl0c19j cHU7CQkvKiBDUFUgdGhhdCB3ZSBoYXZlIGFmZmluaXR5IGZvci4gKi8NCi0J aW50CQl0c19zbGljZTsJLyogVGlja3Mgb2Ygc2xpY2UgcmVtYWluaW5nLiAq Lw0KKwlpbnQJCXRzX3NsaWNlOwkvKiBUaWNrcyBvZiBzbGljZSB1c2VkLiAq Lw0KKwlpbnQJCXRzX3Njb3JlOwkvKiBJbnRlcmFjdGl2aXR5IHNjb3JlLiAq Lw0KIAl1X2ludAkJdHNfc2xwdGltZTsJLyogTnVtYmVyIG9mIHRpY2tzIHdl IHZvbC4gc2xlcHQgKi8NCiAJdV9pbnQJCXRzX3J1bnRpbWU7CS8qIE51bWJl ciBvZiB0aWNrcyB3ZSB3ZXJlIHJ1bm5pbmcgKi8NCiAJLyogVGhlIGZvbGxv d2luZyB2YXJpYWJsZXMgYXJlIG9ubHkgdXNlZCBmb3IgcGN0Y3B1IGNhbGN1 bGF0aW9uICovDQpAQCAtMTAyLDYgKzEwMyw3IEBADQogLyogZmxhZ3Mga2Vw dCBpbiB0c19mbGFncyAqLw0KICNkZWZpbmUJVFNGX0JPVU5ECTB4MDAwMQkJ LyogVGhyZWFkIGNhbiBub3QgbWlncmF0ZS4gKi8NCiAjZGVmaW5lCVRTRl9Y RkVSQUJMRQkweDAwMDIJCS8qIFRocmVhZCB3YXMgYWRkZWQgYXMgdHJhbnNm ZXJhYmxlLiAqLw0KKyNkZWZpbmUJVFNGX0lOVEVSTE9BRAkweDAwMDQJCS8q IEludGVyYWN0aXZlIGxvYWQgb24gcnVucS4gKi8NCiANCiBzdGF0aWMgc3Ry dWN0IHRkX3NjaGVkIHRkX3NjaGVkMDsNCiANCkBAIC0xNjcsMTMgKzE2OSwx NSBAQA0KICAqCQkJdGhlIHNoaWZ0IGZhY3Rvci4gIFdpdGhvdXQgdGhlIHNo aWZ0IHRoZSBlcnJvciByYXRlDQogICoJCQlkdWUgdG8gcm91bmRpbmcgd291 bGQgYmUgdW5hY2NlcHRhYmx5IGhpZ2guDQogICogcmVhbHN0YXRoejoJCXN0 YXRoeiBpcyBzb21ldGltZXMgMCBhbmQgcnVuIG9mZiBvZiBoei4NCi0gKiBz Y2hlZF9zbGljZToJCVJ1bnRpbWUgb2YgZWFjaCB0aHJlYWQgYmVmb3JlIHJl c2NoZWR1bGluZy4NCisgKiBzY2hlZF9zbGljZV9tYXg6CU1heGltdW0gcnVu dGltZSBvZiBlYWNoIHRocmVhZCBiZWZvcmUgcmVzY2hlZHVsaW5nLg0KKyAq IHNjaGVkX3NsaWNlX21pbjoJTWluaW11bSBydW50aW1lIG9mIGVhY2ggdGhy ZWFkIGJlZm9yZSByZXNjaGVkdWxpbmcuDQogICogcHJlZW1wdF90aHJlc2g6 CVByaW9yaXR5IHRocmVzaG9sZCBmb3IgcHJlZW1wdGlvbiBhbmQgcmVtb3Rl IElQSXMuDQogICovDQogc3RhdGljIGludCBzY2hlZF9pbnRlcmFjdCA9IFND SEVEX0lOVEVSQUNUX1RIUkVTSDsNCiBzdGF0aWMgaW50IHJlYWxzdGF0aHo7 DQogc3RhdGljIGludCB0aWNraW5jcjsNCi1zdGF0aWMgaW50IHNjaGVkX3Ns aWNlOw0KK3N0YXRpYyBpbnQgc2NoZWRfc2xpY2VfbWF4ID0gMTsNCitzdGF0 aWMgaW50IHNjaGVkX3NsaWNlX21pbiA9IDE7DQogI2lmZGVmIFBSRUVNUFRJ T04NCiAjaWZkZWYgRlVMTF9QUkVFTVBUSU9ODQogc3RhdGljIGludCBwcmVl bXB0X3RocmVzaCA9IFBSSV9NQVhfSURMRTsNCkBAIC0xOTQsNiArMTk4LDcg QEANCiAJc3RydWN0IHJ1bnEJdGRxX3JlYWx0aW1lOwkJLyogcmVhbC10aW1l IHJ1biBxdWV1ZS4gKi8NCiAJc3RydWN0IHJ1bnEJdGRxX3RpbWVzaGFyZTsJ CS8qIHRpbWVzaGFyZSBydW4gcXVldWUuICovDQogCXN0cnVjdCBydW5xCXRk cV9pZGxlOwkJLyogUXVldWUgb2YgSURMRSB0aHJlYWRzLiAqLw0KKwl1bnNp Z25lZCBpbnQJdGRxX2ludGVybG9hZDsJCS8qIEludGVyYWN0aXZlIGxvYWQu ICovDQogCWludAkJdGRxX2xvYWQ7CQkvKiBBZ2dyZWdhdGUgbG9hZC4gKi8N CiAJdV9jaGFyCQl0ZHFfaWR4OwkJLyogQ3VycmVudCBpbnNlcnQgaW5kZXgu ICovDQogCXVfY2hhcgkJdGRxX3JpZHg7CQkvKiBDdXJyZW50IHJlbW92YWwg aW5kZXguICovDQpAQCAtMjM5LDcgKzI0NCw2IEBADQogc3RhdGljIGludCBi YWxhbmNlX2ludGVydmFsID0gMTI4OwkvKiBEZWZhdWx0IHNldCBpbiBzY2hl ZF9pbml0dGlja3MoKS4gKi8NCiBzdGF0aWMgaW50IHBpY2tfcHJpID0gMTsN CiBzdGF0aWMgaW50IGFmZmluaXR5Ow0KLXN0YXRpYyBpbnQgdHJ5c2VsZiA9 IDE7DQogc3RhdGljIGludCBzdGVhbF9odHQgPSAxOw0KIHN0YXRpYyBpbnQg c3RlYWxfaWRsZSA9IDE7DQogc3RhdGljIGludCBzdGVhbF90aHJlc2ggPSAy Ow0KQEAgLTI4OCwxMCArMjkyLDEyIEBADQogc3RhdGljIHZvaWQgdGRxX3Nl dHVwKHN0cnVjdCB0ZHEgKik7DQogc3RhdGljIHZvaWQgdGRxX2xvYWRfYWRk KHN0cnVjdCB0ZHEgKiwgc3RydWN0IHRkX3NjaGVkICopOw0KIHN0YXRpYyB2 b2lkIHRkcV9sb2FkX3JlbShzdHJ1Y3QgdGRxICosIHN0cnVjdCB0ZF9zY2hl ZCAqKTsNCitzdGF0aWMgaW50IHRkcV9zbGljZShzdHJ1Y3QgdGRxICopOw0K IHN0YXRpYyBfX2lubGluZSB2b2lkIHRkcV9ydW5xX2FkZChzdHJ1Y3QgdGRx ICosIHN0cnVjdCB0ZF9zY2hlZCAqLCBpbnQpOw0KIHN0YXRpYyBfX2lubGlu ZSB2b2lkIHRkcV9ydW5xX3JlbShzdHJ1Y3QgdGRxICosIHN0cnVjdCB0ZF9z Y2hlZCAqKTsNCi12b2lkIHRkcV9wcmludChpbnQgY3B1KTsNCi1zdGF0aWMg dm9pZCBydW5xX3ByaW50KHN0cnVjdCBydW5xICpycSk7DQordm9pZCB0ZHFf cHJpbnQoaW50KTsNCit2b2lkIHNjaGVkX3ByaW50KHN0cnVjdCB0aHJlYWQg Kik7DQorc3RhdGljIHZvaWQgcnVucV9wcmludChzdHJ1Y3QgcnVucSAqKTsN CiBzdGF0aWMgdm9pZCB0ZHFfYWRkKHN0cnVjdCB0ZHEgKiwgc3RydWN0IHRo cmVhZCAqLCBpbnQpOw0KICNpZmRlZiBTTVANCiBzdGF0aWMgdm9pZCB0ZHFf bW92ZShzdHJ1Y3QgdGRxICosIHN0cnVjdCB0ZHEgKik7DQpAQCAtMzQ1LDYg KzM1MSwyNiBAQA0KIAl9DQogfQ0KIA0KK3ZvaWQNCitzY2hlZF9wcmludChz dHJ1Y3QgdGhyZWFkICp0ZCkNCit7DQorCXN0cnVjdCB0ZF9zY2hlZCAqdHM7 DQorDQorCWlmICh0ZCA9PSBOVUxMKQ0KKwkJdGQgPSBjdXJ0aHJlYWQ7DQor CXRzID0gdGQtPnRkX3NjaGVkOw0KKwlwcmludGYoImZsYWdzOiAgICAweCVY XG4iLCB0cy0+dHNfZmxhZ3MpOw0KKwlwcmludGYoInJxaW5kZXg6ICAlZFxu IiwgdHMtPnRzX3JxaW5kZXgpOw0KKwlwcmludGYoImNwdTogICAgICAlZFxu IiwgdHMtPnRzX2NwdSk7DQorCXByaW50Zigic2xpY2U6ICAgICVkXG4iLCB0 cy0+dHNfc2xpY2UpOw0KKwlwcmludGYoInNjb3JlOiAgICAlZFxuIiwgdHMt PnRzX3Njb3JlKTsNCisJcHJpbnRmKCJzbHB0aW1lOiAgJWRcbiIsIHRzLT50 c19zbHB0aW1lKTsNCisJcHJpbnRmKCJydW50aW1lOiAgJWRcbiIsIHRzLT50 c19ydW50aW1lKTsNCisJcHJpbnRmKCJsdGljazogICAgJWRcbiIsIHRzLT50 c19sdGljayk7DQorCXByaW50ZigiZnRpY2s6ICAgICVkXG4iLCB0cy0+dHNf ZnRpY2spOw0KKwlwcmludGYoInRpY2tzOiAgICAlZFxuIiwgdHMtPnRzX3Rp Y2tzKTsNCit9DQorDQogLyoNCiAgKiBQcmludCB0aGUgc3RhdHVzIG9mIGEg cGVyLWNwdSB0aHJlYWQgcXVldWUuICBTaG91bGQgYmUgYSBkZGIgc2hvdyBj bWQuDQogICovDQpAQCAtMzU3LDcgKzM4Myw5IEBADQogDQogCXByaW50Zigi dGRxICVkOlxuIiwgVERRX0lEKHRkcSkpOw0KIAlwcmludGYoIlx0bG9ja3B0 ciAgICAgICAgICVwXG4iLCBURFFfTE9DS1BUUih0ZHEpKTsNCisJcHJpbnRm KCJcdGludGVybG9hZDoJICAlZFxuIiwgdGRxLT50ZHFfaW50ZXJsb2FkKTsN CiAJcHJpbnRmKCJcdGxvYWQ6ICAgICAgICAgICAlZFxuIiwgdGRxLT50ZHFf bG9hZCk7DQorCXByaW50ZigiXHRzbGljZTogICAgICAgICAgJWRcbiIsIHRk cV9zbGljZSh0ZHEpKTsNCiAJcHJpbnRmKCJcdHRpbWVzaGFyZSBpZHg6ICAl ZFxuIiwgdGRxLT50ZHFfaWR4KTsNCiAJcHJpbnRmKCJcdHRpbWVzaGFyZSBy aWR4OiAlZFxuIiwgdGRxLT50ZHFfcmlkeCk7DQogCXByaW50ZigiXHRyZWFs dGltZSBydW5xOlxuIik7DQpAQCAtMzgzLDggKzQxMSwxMiBAQA0KIHN0YXRp YyBfX2lubGluZSB2b2lkDQogdGRxX3J1bnFfYWRkKHN0cnVjdCB0ZHEgKnRk cSwgc3RydWN0IHRkX3NjaGVkICp0cywgaW50IGZsYWdzKQ0KIHsNCisJdV9j aGFyIHByaTsNCisNCisJcHJpID0gdHMtPnRzX3RocmVhZC0+dGRfcHJpb3Jp dHk7DQogCVREUV9MT0NLX0FTU0VSVCh0ZHEsIE1BX09XTkVEKTsNCiAJVEhS RUFEX0xPQ0tfQVNTRVJUKHRzLT50c190aHJlYWQsIE1BX09XTkVEKTsNCisJ VERfU0VUX1JVTlEodHMtPnRzX3RocmVhZCk7DQogI2lmZGVmIFNNUA0KIAlp ZiAoVEhSRUFEX0NBTl9NSUdSQVRFKHRzLT50c190aHJlYWQpKSB7DQogCQl0 ZHEtPnRkcV90cmFuc2ZlcmFibGUrKzsNCkBAIC0zOTIsMTUgKzQyNCwxNSBA QA0KIAkJdHMtPnRzX2ZsYWdzIHw9IFRTRl9YRkVSQUJMRTsNCiAJfQ0KICNl bmRpZg0KLQlpZiAodHMtPnRzX3J1bnEgPT0gJnRkcS0+dGRxX3RpbWVzaGFy ZSkgew0KLQkJdV9jaGFyIHByaTsNCi0NCi0JCXByaSA9IHRzLT50c190aHJl YWQtPnRkX3ByaW9yaXR5Ow0KKwlpZiAocHJpIDw9IFBSSV9NQVhfUkVBTFRJ TUUpIHsNCisJCXRzLT50c19ydW5xID0gJnRkcS0+dGRxX3JlYWx0aW1lOw0K Kwl9IGVsc2UgaWYgKHByaSA8PSBQUklfTUFYX1RJTUVTSEFSRSkgew0KKwkJ dHMtPnRzX3J1bnEgPSAmdGRxLT50ZHFfdGltZXNoYXJlOw0KIAkJS0FTU0VS VChwcmkgPD0gUFJJX01BWF9USU1FU0hBUkUgJiYgcHJpID49IFBSSV9NSU5f VElNRVNIQVJFLA0KIAkJCSgiSW52YWxpZCBwcmlvcml0eSAlZCBvbiB0aW1l c2hhcmUgcnVucSIsIHByaSkpOw0KIAkJLyoNCiAJCSAqIFRoaXMgcXVldWUg Y29udGFpbnMgb25seSBwcmlvcml0aWVzIGJldHdlZW4gTUlOIGFuZCBNQVgN Ci0JCSAqIHJlYWx0aW1lLiAgVXNlIHRoZSB3aG9sZSBxdWV1ZSB0byByZXBy ZXNlbnQgdGhlc2UgdmFsdWVzLg0KKwkJICogdGltZXNoYXJlLiAgVXNlIHRo ZSB3aG9sZSBxdWV1ZSB0byByZXByZXNlbnQgdGhlc2UgdmFsdWVzLg0KIAkJ ICovDQogCQlpZiAoKGZsYWdzICYgKFNSUV9CT1JST1dJTkd8U1JRX1BSRUVN UFRFRCkpID09IDApIHsNCiAJCQlwcmkgPSAocHJpIC0gUFJJX01JTl9USU1F U0hBUkUpIC8gVFNfUlFfUFBROw0KQEAgLTQxNiw4ICs0NDgsMTAgQEANCiAJ CX0gZWxzZQ0KIAkJCXByaSA9IHRkcS0+dGRxX3JpZHg7DQogCQlydW5xX2Fk ZF9wcmkodHMtPnRzX3J1bnEsIHRzLCBwcmksIGZsYWdzKTsNCisJCXJldHVy bjsNCiAJfSBlbHNlDQotCQlydW5xX2FkZCh0cy0+dHNfcnVucSwgdHMsIGZs YWdzKTsNCisJCXRzLT50c19ydW5xID0gJnRkcS0+dGRxX2lkbGU7DQorCXJ1 bnFfYWRkKHRzLT50c19ydW5xLCB0cywgZmxhZ3MpOw0KIH0NCiANCiAvKiAN CkBAIC00NDMsMTMgKzQ3Nyw2IEBADQogCQkJcnVucV9yZW1vdmVfaWR4KHRz LT50c19ydW5xLCB0cywgJnRkcS0+dGRxX3JpZHgpOw0KIAkJZWxzZQ0KIAkJ CXJ1bnFfcmVtb3ZlX2lkeCh0cy0+dHNfcnVucSwgdHMsIE5VTEwpOw0KLQkJ LyoNCi0JCSAqIEZvciB0aW1lc2hhcmUgdGhyZWFkcyB3ZSB1cGRhdGUgdGhl IHByaW9yaXR5IGhlcmUgc28NCi0JCSAqIHRoZSBwcmlvcml0eSByZWZsZWN0 cyB0aGUgdGltZSB3ZSd2ZSBiZWVuIHNsZWVwaW5nLg0KLQkJICovDQotCQl0 cy0+dHNfbHRpY2sgPSB0aWNrczsNCi0JCXNjaGVkX3BjdGNwdV91cGRhdGUo dHMpOw0KLQkJc2NoZWRfcHJpb3JpdHkodHMtPnRzX3RocmVhZCk7DQogCX0g ZWxzZQ0KIAkJcnVucV9yZW1vdmUodHMtPnRzX3J1bnEsIHRzKTsNCiB9DQpA QCAtNDY2LDYgKzQ5Myw4IEBADQogCVREUV9MT0NLX0FTU0VSVCh0ZHEsIE1B X09XTkVEKTsNCiAJVEhSRUFEX0xPQ0tfQVNTRVJUKHRzLT50c190aHJlYWQs IE1BX09XTkVEKTsNCiAJY2xhc3MgPSBQUklfQkFTRSh0cy0+dHNfdGhyZWFk LT50ZF9wcmlfY2xhc3MpOw0KKwl0ZHEtPnRkcV9pbnRlcmxvYWQgKz0gdHMt PnRzX3Njb3JlOw0KKwl0cy0+dHNfZmxhZ3MgfD0gVFNGX0lOVEVSTE9BRDsN CiAJdGRxLT50ZHFfbG9hZCsrOw0KIAlDVFIyKEtUUl9TQ0hFRCwgImNwdSAl ZCBsb2FkOiAlZCIsIFREUV9JRCh0ZHEpLCB0ZHEtPnRkcV9sb2FkKTsNCiAJ aWYgKGNsYXNzICE9IFBSSV9JVEhEICYmDQpAQCAtNDk4LDkgKzUyNywzNyBA QA0KICNlbmRpZg0KIAlLQVNTRVJUKHRkcS0+dGRxX2xvYWQgIT0gMCwNCiAJ ICAgICgidGRxX2xvYWRfcmVtOiBSZW1vdmluZyB3aXRoIDAgbG9hZCBvbiBx dWV1ZSAlZCIsIFREUV9JRCh0ZHEpKSk7DQorCXRzLT50c19mbGFncyAmPSB+ VFNGX0lOVEVSTE9BRDsNCisJdHMtPnRzX3J1bnEgPSBOVUxMOw0KKwl0ZHEt PnRkcV9pbnRlcmxvYWQgLT0gdHMtPnRzX3Njb3JlOw0KIAl0ZHEtPnRkcV9s b2FkLS07DQogCUNUUjEoS1RSX1NDSEVELCAibG9hZDogJWQiLCB0ZHEtPnRk cV9sb2FkKTsNCi0JdHMtPnRzX3J1bnEgPSBOVUxMOw0KK30NCisNCisvKg0K KyAqIENvbXB1dGUgdGhlIG1heGltdW0gc2xpY2Ugd2hlbiB0aGUgaW50ZXJs b2FkIGNoYW5nZXMuICBUaGlzIGdpdmVzIGEgc29mdA0KKyAqIHVwcGVyIGJv dW5kIG9uIGxhdGVuY3kgYXMgdGhlIGxvYWQgaW5jcmVhc2VzLg0KKyAqLw0K K3N0YXRpYyBpbnQNCit0ZHFfc2xpY2Uoc3RydWN0IHRkcSAqdGRxKQ0KK3sN CisJaW50IHNsaWNlOw0KKwlpbnQgbG9hZDsNCisNCisJVERRX0xPQ0tfQVNT RVJUKHRkcSwgTUFfT1dORUQpOw0KKwlpZiAodGRxLT50ZHFfaW50ZXJsb2Fk ID09IDApDQorCQlyZXR1cm4gKHNjaGVkX3NsaWNlX21heCk7DQorCS8qDQor CSAqIEFuIGludGVybG9hZCBvZiAxMDAgaXMgcm91Z2hseSBlcXVpdmFsZW50 IHRvIDEwMCUgY3B1IHV0aWxpemF0aW9uDQorCSAqIHJlcXVlc3RlZC4gIENh bGN1bGF0ZSBob3cgbWFueSB0aW1lcyBvdmVybG9hZGVkIHdlIGFyZSBhbmQg dGhlbg0KKwkgKiBkaXZpZGUgdGhlIGxhdGVuY3kgdGFyZ2V0IGJ5IHRoaXMg bnVtYmVyLiAgTm9uZSBvZiB0aGlzIGlzIHByZWNpc2UNCisJICogYnV0IGl0 IGRvZXMgeWllbGQgZGVjcmVhc2luZyBzbGljZSB2YWx1ZXMgd2l0aGluIHRo ZSBbbWluLCBtYXhdDQorCSAqIHJhbmdlIGFzIGxvYWQgaW5jcmVhc2VzLg0K KwkgKi8NCisJbG9hZCA9ICh0ZHEtPnRkcV9pbnRlcmxvYWQgKyA5OSkgLyAx MDA7DQorCXNsaWNlID0gc2NoZWRfc2xpY2VfbWF4IC8gbG9hZDsNCisJc2xp Y2UgPSBtYXgoc2xpY2UsIHNjaGVkX3NsaWNlX21pbik7DQorCXJldHVybiAo c2xpY2UpOw0KIH0NCiANCiAjaWZkZWYgU01QDQpAQCAtMTA3MCwxNCArMTEy Nyw2IEBADQogCWNwdSA9IHNlbGYgPSBQQ1BVX0dFVChjcHVpZCk7DQogCWlm IChzbXBfc3RhcnRlZCA9PSAwKQ0KIAkJcmV0dXJuIChzZWxmKTsNCi0JLyoN Ci0JICogRG9uJ3QgbWlncmF0ZSBhIHJ1bm5pbmcgdGhyZWFkIGZyb20gc2No ZWRfc3dpdGNoKCkuDQotCSAqLw0KLQlpZiAoZmxhZ3MgJiBTUlFfT1VSU0VM Rikgew0KLQkJQ1RSMShLVFJfVUxFLCAiWUlFTERJTkcgJWQiLA0KLQkJICAg IGN1cnRocmVhZC0+dGRfcHJpb3JpdHkpOw0KLQkJcmV0dXJuIChzZWxmKTsN Ci0JfQ0KIAlwcmkgPSB0cy0+dHNfdGhyZWFkLT50ZF9wcmlvcml0eTsNCiAJ Y3B1ID0gdHMtPnRzX2NwdTsNCiAJLyoNCkBAIC0xMDk0LDcgKzExNDMsOCBA QA0KIAkvKg0KIAkgKiBJZiB3ZSBoYXZlIGFmZmluaXR5LCB0cnkgdG8gcGxh Y2UgaXQgb24gdGhlIGNwdSB3ZSBsYXN0IHJhbiBvbi4NCiAJICovDQotCWlm IChTQ0hFRF9BRkZJTklUWSh0cykgJiYgdGRxLT50ZHFfbG93cHJpID4gcHJp KSB7DQorCWlmIChTQ0hFRF9BRkZJTklUWSh0cykgJiYNCisJICAgICh0ZHEt PnRkcV9sb3dwcmkgPiBwcmkgfHwgdGRxLT50ZHFfaW50ZXJsb2FkIDwgMTAp KSB7DQogCQlDVFI1KEtUUl9VTEUsDQogCQkgICAgImFmZmluaXR5IGZvciAl ZCwgbHRpY2sgJWQgdGlja3MgJWQgcHJpICVkIGN1cnRocmVhZCAlZCIsDQog CQkgICAgdHMtPnRzX2NwdSwgdHMtPnRzX3JsdGljaywgdGlja3MsIHByaSwN CkBAIC0xMTEzLDkgKzExNjMsOSBAQA0KIAkgKiBUaGlzIG1heSBpbXByb3Zl IGxvY2FsaXR5IGFtb25nIHNsZWVwZXJzIGFuZCB3YWtlcnMgd2hlbiB0aGVy ZQ0KIAkgKiBpcyBzaGFyZWQgZGF0YS4NCiAJICovDQotCWlmICh0cnlzZWxm ICYmIHByaSA8IGN1cnRocmVhZC0+dGRfcHJpb3JpdHkpIHsNCi0JCUNUUjEo S1RSX1VMRSwgInRyeXNlbGYgJWQiLA0KLQkJICAgIGN1cnRocmVhZC0+dGRf cHJpb3JpdHkpOw0KKwl0ZHEgPSBURFFfQ1BVKHNlbGYpOw0KKwlpZiAocHJp IDwgY3VydGhyZWFkLT50ZF9wcmlvcml0eSB8fCB0ZHEtPnRkcV9pbnRlcmxv YWQgPCAxMCkgew0KKwkJQ1RSMShLVFJfVUxFLCAidHJ5c2VsZiAlZCIsIGN1 cnRocmVhZC0+dGRfcHJpb3JpdHkpOw0KIAkJcmV0dXJuIChzZWxmKTsNCiAJ fQ0KIAkvKg0KQEAgLTExNzUsNiArMTIyNSw3IEBADQogCXJ1bnFfaW5pdCgm dGRxLT50ZHFfdGltZXNoYXJlKTsNCiAJcnVucV9pbml0KCZ0ZHEtPnRkcV9p ZGxlKTsNCiAJdGRxLT50ZHFfbG9hZCA9IDA7DQorCXRkcS0+dGRxX2ludGVy bG9hZCA9IDA7DQogfQ0KIA0KICNpZmRlZiBTTVANCkBAIC0xMzI0LDEyICsx Mzc1LDEyIEBADQogCSAqIGluIGNhc2Ugd2hpY2ggc2NoZWRfY2xvY2soKSBj YWxsZWQgYmVmb3JlIHNjaGVkX2luaXR0aWNrcygpLg0KIAkgKi8NCiAJcmVh bHN0YXRoeiA9IGh6Ow0KLQlzY2hlZF9zbGljZSA9IChyZWFsc3RhdGh6LzEw KTsJLyogfjEwMG1zICovDQogCXRpY2tpbmNyID0gMSA8PCBTQ0hFRF9USUNL X1NISUZUOw0KIA0KIAkvKiBBZGQgdGhyZWFkMCdzIGxvYWQgc2luY2UgaXQn cyBydW5uaW5nLiAqLw0KIAlURFFfTE9DSyh0ZHEpOw0KIAl0aHJlYWQwLnRk X2xvY2sgPSBURFFfTE9DS1BUUihURFFfU0VMRigpKTsNCisJdGRfc2NoZWQw LnRzX3Njb3JlID0gMDsNCiAJdGRxX2xvYWRfYWRkKHRkcSwgJnRkX3NjaGVk MCk7DQogCVREUV9VTkxPQ0sodGRxKTsNCiB9DQpAQCAtMTM0NCw3ICsxMzk1 LDggQEANCiAJaW50IGluY3I7DQogDQogCXJlYWxzdGF0aHogPSBzdGF0aHog PyBzdGF0aHogOiBoejsNCi0Jc2NoZWRfc2xpY2UgPSAocmVhbHN0YXRoei8x MCk7CS8qIH4xMDBtcyAqLw0KKwlzY2hlZF9zbGljZV9tYXggPSByZWFsc3Rh dGh6IC8gMTU7CS8qIH42Nm1zICovDQorCXNjaGVkX3NsaWNlX21pbiA9IHJl YWxzdGF0aHogLyA1MDsJLyogfjIwbXMgKi8NCiANCiAJLyoNCiAJICogdGlj a2luY3IgaXMgc2hpZnRlZCBvdXQgYnkgMTAgdG8gYXZvaWQgcm91bmRpbmcg ZXJyb3JzIGR1ZSB0bw0KQEAgLTEzNzQsNyArMTQyNiw2IEBADQogI2VuZGlm DQogfQ0KIA0KLQ0KIC8qDQogICogVGhpcyBpcyB0aGUgY29yZSBvZiB0aGUg aW50ZXJhY3Rpdml0eSBhbGdvcml0aG0uICBEZXRlcm1pbmVzIGEgc2NvcmUg YmFzZWQNCiAgKiBvbiBwYXN0IGJlaGF2aW9yLiAgSXQgaXMgdGhlIHJhdGlv IG9mIHNsZWVwIHRpbWUgdG8gcnVuIHRpbWUgc2NhbGVkIHRvDQpAQCAtMTM4 OSwxNSArMTQ0MCw2IEBADQogCWludCBkaXY7DQogDQogCXRzID0gdGQtPnRk X3NjaGVkOw0KLQkvKg0KLQkgKiBUaGUgc2NvcmUgaXMgb25seSBuZWVkZWQg aWYgdGhpcyBpcyBsaWtlbHkgdG8gYmUgYW4gaW50ZXJhY3RpdmUNCi0JICog dGFzay4gIERvbid0IGdvIHRocm91Z2ggdGhlIGV4cGVuc2Ugb2YgY29tcHV0 aW5nIGl0IGlmIHRoZXJlJ3MNCi0JICogbm8gY2hhbmNlLg0KLQkgKi8NCi0J aWYgKHNjaGVkX2ludGVyYWN0IDw9IFNDSEVEX0lOVEVSQUNUX0hBTEYgJiYN Ci0JCXRzLT50c19ydW50aW1lID49IHRzLT50c19zbHB0aW1lKQ0KLQkJCXJl dHVybiAoU0NIRURfSU5URVJBQ1RfSEFMRik7DQotDQogCWlmICh0cy0+dHNf cnVudGltZSA+IHRzLT50c19zbHB0aW1lKSB7DQogCQlkaXYgPSBtYXgoMSwg dHMtPnRzX3J1bnRpbWUgLyBTQ0hFRF9JTlRFUkFDVF9IQUxGKTsNCiAJCXJl dHVybiAoU0NIRURfSU5URVJBQ1RfSEFMRiArDQpAQCAtMTQ0Myw3ICsxNDg1 LDcgQEANCiAJICogc2NvcmUuICBOZWdhdGl2ZSBuaWNlIHZhbHVlcyBtYWtl IGl0IGVhc2llciBmb3IgYSB0aHJlYWQgdG8gYmUNCiAJICogY29uc2lkZXJl ZCBpbnRlcmFjdGl2ZS4NCiAJICovDQotCXNjb3JlID0gaW1heCgwLCBzY2hl ZF9pbnRlcmFjdF9zY29yZSh0ZCkgLSB0ZC0+dGRfcHJvYy0+cF9uaWNlKTsN CisJc2NvcmUgPSBpbWF4KDAsIHRkLT50ZF9zY2hlZC0+dHNfc2NvcmUgLSB0 ZC0+dGRfcHJvYy0+cF9uaWNlKTsNCiAJaWYgKHNjb3JlIDwgc2NoZWRfaW50 ZXJhY3QpIHsNCiAJCXByaSA9IFBSSV9NSU5fUkVBTFRJTUU7DQogCQlwcmkg Kz0gKChQUklfTUFYX1JFQUxUSU1FIC0gUFJJX01JTl9SRUFMVElNRSkgLyBz Y2hlZF9pbnRlcmFjdCkNCkBAIC0xNDc3LDEyICsxNTE5LDE1IEBADQogc2No ZWRfaW50ZXJhY3RfdXBkYXRlKHN0cnVjdCB0aHJlYWQgKnRkKQ0KIHsNCiAJ c3RydWN0IHRkX3NjaGVkICp0czsNCisJc3RydWN0IHRkcSAqdGRxOw0KIAl1 X2ludCBzdW07DQorCWludCBzY29yZTsNCiANCisJVEhSRUFEX0xPQ0tfQVNT RVJUKHRkLCBNQV9PV05FRCk7DQogCXRzID0gdGQtPnRkX3NjaGVkOw0KIAlz dW0gPSB0cy0+dHNfcnVudGltZSArIHRzLT50c19zbHB0aW1lOw0KIAlpZiAo c3VtIDwgU0NIRURfU0xQX1JVTl9NQVgpDQotCQlyZXR1cm47DQorCQlnb3Rv IHNjb3JlOw0KIAkvKg0KIAkgKiBUaGlzIG9ubHkgaGFwcGVucyBmcm9tIHR3 byBwbGFjZXM6DQogCSAqIDEpIFdlIGhhdmUgYWRkZWQgYW4gdW51c3VhbCBh bW91bnQgb2YgcnVuIHRpbWUgZnJvbSBmb3JrX2V4aXQuDQpAQCAtMTQ5MCwx MyArMTUzNSwxMyBAQA0KIAkgKi8NCiAJaWYgKHN1bSA+IFNDSEVEX1NMUF9S VU5fTUFYICogMikgew0KIAkJaWYgKHRzLT50c19ydW50aW1lID4gdHMtPnRz X3NscHRpbWUpIHsNCi0JCQl0cy0+dHNfcnVudGltZSA9IFNDSEVEX1NMUF9S VU5fTUFYOw0KKwkJCXRzLT50c19ydW50aW1lID0gU0NIRURfU0xQX1JVTl9N QVggLyAyOw0KIAkJCXRzLT50c19zbHB0aW1lID0gMTsNCiAJCX0gZWxzZSB7 DQotCQkJdHMtPnRzX3NscHRpbWUgPSBTQ0hFRF9TTFBfUlVOX01BWDsNCisJ CQl0cy0+dHNfc2xwdGltZSA9IFNDSEVEX1NMUF9SVU5fTUFYIC8gMjsNCiAJ CQl0cy0+dHNfcnVudGltZSA9IDE7DQogCQl9DQotCQlyZXR1cm47DQorCQln b3RvIHNjb3JlOw0KIAl9DQogCS8qDQogCSAqIElmIHdlIGhhdmUgZXhjZWVk ZWQgYnkgbW9yZSB0aGFuIDEvNXRoIHRoZW4gdGhlIGFsZ29yaXRobSBiZWxv dw0KQEAgLTE1MDYsMTAgKzE1NTEsMTkgQEANCiAJaWYgKHN1bSA+IChTQ0hF RF9TTFBfUlVOX01BWCAvIDUpICogNikgew0KIAkJdHMtPnRzX3J1bnRpbWUg Lz0gMjsNCiAJCXRzLT50c19zbHB0aW1lIC89IDI7DQotCQlyZXR1cm47DQor CQlnb3RvIHNjb3JlOw0KIAl9DQogCXRzLT50c19ydW50aW1lID0gKHRzLT50 c19ydW50aW1lIC8gNSkgKiA0Ow0KIAl0cy0+dHNfc2xwdGltZSA9ICh0cy0+ dHNfc2xwdGltZSAvIDUpICogNDsNCitzY29yZToNCisJc2NvcmUgPSBzY2hl ZF9pbnRlcmFjdF9zY29yZSh0ZCk7DQorCWlmICh0cy0+dHNfZmxhZ3MgJiBU U0ZfSU5URVJMT0FEKSB7DQorCQl0ZHEgPSBURFFfQ1BVKHRzLT50c19jcHUp Ow0KKwkJVERRX0xPQ0tfQVNTRVJUKHRkcSwgTUFfT1dORUQpOw0KKwkJdGRx LT50ZHFfaW50ZXJsb2FkIC09IHRzLT50c19zY29yZTsNCisJCXRkcS0+dGRx X2ludGVybG9hZCArPSBzY29yZTsNCisJfQ0KKwl0cy0+dHNfc2NvcmUgPSBz Y29yZTsNCiB9DQogDQogLyoNCkBAIC0xNTU5LDcgKzE2MTMsNyBAQA0KIHsN CiANCiAJLyogQ29udmVydCBzY2hlZF9zbGljZSB0byBoeiAqLw0KLQlyZXR1 cm4gKGh6LyhyZWFsc3RhdGh6L3NjaGVkX3NsaWNlKSk7DQorCXJldHVybiAo aHovKHJlYWxzdGF0aHovc2NoZWRfc2xpY2VfbWF4KSk7DQogfQ0KIA0KIC8q DQpAQCAtMTU5OCwxNiArMTY1MiwxOSBAQA0KIHNjaGVkX3RocmVhZF9wcmlv cml0eShzdHJ1Y3QgdGhyZWFkICp0ZCwgdV9jaGFyIHByaW8pDQogew0KIAlz dHJ1Y3QgdGRfc2NoZWQgKnRzOw0KKwlzdHJ1Y3QgdGRxICp0ZHE7DQogDQog CUNUUjYoS1RSX1NDSEVELCAic2NoZWRfcHJpbzogJXAoJXMpIHByaW8gJWQg bmV3cHJpbyAlZCBieSAlcCglcykiLA0KIAkgICAgdGQsIHRkLT50ZF9wcm9j LT5wX2NvbW0sIHRkLT50ZF9wcmlvcml0eSwgcHJpbywgY3VydGhyZWFkLA0K IAkgICAgY3VydGhyZWFkLT50ZF9wcm9jLT5wX2NvbW0pOw0KIAl0cyA9IHRk LT50ZF9zY2hlZDsNCisJdGRxID0gVERRX0NQVSh0cy0+dHNfY3B1KTsNCiAJ VEhSRUFEX0xPQ0tfQVNTRVJUKHRkLCBNQV9PV05FRCk7DQotCWlmICh0ZC0+ dGRfcHJpb3JpdHkgPT0gcHJpbykNCisJaWYgKHRkLT50ZF9wcmlvcml0eSA8 PSBwcmlvKSB7DQorCQl0ZC0+dGRfcHJpb3JpdHkgPSBwcmlvOw0KIAkJcmV0 dXJuOw0KLQ0KLQlpZiAoVERfT05fUlVOUSh0ZCkgJiYgcHJpbyA8IHRkLT50 ZF9wcmlvcml0eSkgew0KKwl9DQorCWlmIChURF9PTl9SVU5RKHRkKSkgew0K IAkJLyoNCiAJCSAqIElmIHRoZSBwcmlvcml0eSBoYXMgYmVlbiBlbGV2YXRl ZCBkdWUgdG8gcHJpb3JpdHkNCiAJCSAqIHByb3BhZ2F0aW9uLCB3ZSBtYXkg aGF2ZSB0byBtb3ZlIG91cnNlbHZlcyB0byBhIG5ldw0KQEAgLTE2MTcsMTYg KzE2NzQsMTQgQEANCiAJCXNjaGVkX3JlbSh0ZCk7DQogCQl0ZC0+dGRfcHJp b3JpdHkgPSBwcmlvOw0KIAkJc2NoZWRfYWRkKHRkLCBTUlFfQk9SUk9XSU5H KTsNCi0JfSBlbHNlIHsNCiAjaWZkZWYgU01QDQotCQlzdHJ1Y3QgdGRxICp0 ZHE7DQotDQotCQl0ZHEgPSBURFFfQ1BVKHRzLT50c19jcHUpOw0KKwl9IGVs c2UgaWYgKFREX0lTX1JVTk5JTkcodGQpKSB7DQogCQlpZiAocHJpbyA8IHRk cS0+dGRxX2xvd3ByaSkNCiAJCQl0ZHEtPnRkcV9sb3dwcmkgPSBwcmlvOw0K KwkJdGQtPnRkX3ByaW9yaXR5ID0gcHJpbzsNCiAjZW5kaWYNCisJfSBlbHNl DQogCQl0ZC0+dGRfcHJpb3JpdHkgPSBwcmlvOw0KLQl9DQogfQ0KIA0KIC8q DQpAQCAtMTc3Miw2ICsxODI3LDggQEANCiANCiAJdGRuID0gVERRX0NQVSh0 ZC0+dGRfc2NoZWQtPnRzX2NwdSk7DQogI2lmZGVmIFNNUA0KKwkvKiBUaGUg bG9hZCBpcyBiZWluZyByZW1vdmVkIGZyb20gdGhlIGN1cnJlbnQgY3B1LiAq Lw0KKwl0ZHFfbG9hZF9yZW0odGRxLCB0ZC0+dGRfc2NoZWQpOw0KIAkvKg0K IAkgKiBEbyB0aGUgbG9jayBkYW5jZSByZXF1aXJlZCB0byBhdm9pZCBMT1Iu ICBXZSBncmFiIGFuIGV4dHJhDQogCSAqIHNwaW5sb2NrIG5lc3RpbmcgdG8g cHJldmVudCBwcmVlbXB0aW9uIHdoaWxlIHdlJ3JlDQpAQCAtMTg2MywxMiAr MTkyMCwxMSBAQA0KIAkJVERfU0VUX0NBTl9SVU4odGQpOw0KIAl9IGVsc2Ug aWYgKFREX0lTX1JVTk5JTkcodGQpKSB7DQogCQlNUEFTUyh0ZC0+dGRfbG9j ayA9PSBURFFfTE9DS1BUUih0ZHEpKTsNCi0JCXRkcV9sb2FkX3JlbSh0ZHEs IHRzKTsNCiAJCXNycWZsYWcgPSAoZmxhZ3MgJiBTV19QUkVFTVBUKSA/DQog CQkgICAgU1JRX09VUlNFTEZ8U1JRX1lJRUxESU5HfFNSUV9QUkVFTVBURUQg Og0KIAkJICAgIFNSUV9PVVJTRUxGfFNSUV9ZSUVMRElORzsNCiAJCWlmICh0 cy0+dHNfY3B1ID09IGNwdWlkKQ0KLQkJCXRkcV9hZGQodGRxLCB0ZCwgc3Jx ZmxhZyk7DQorCQkJdGRxX3J1bnFfYWRkKHRkcSwgdHMsIHNycWZsYWcpOw0K IAkJZWxzZQ0KIAkJCW10eCA9IHNjaGVkX3N3aXRjaF9taWdyYXRlKHRkcSwg dGQsIHNycWZsYWcpOw0KIAl9IGVsc2Ugew0KQEAgLTE5NzAsMjIgKzIwMjYs MTggQEANCiAJVEhSRUFEX0xPQ0tfQVNTRVJUKHRkLCBNQV9PV05FRCk7DQog CXRzID0gdGQtPnRkX3NjaGVkOw0KIAkvKg0KLQkgKiBJZiB3ZSBzbGVwdCBm b3IgbW9yZSB0aGFuIGEgdGljayB1cGRhdGUgb3VyIGludGVyYWN0aXZpdHkg YW5kDQotCSAqIHByaW9yaXR5Lg0KKwkgKiBVcGRhdGUgaW50ZXJhY3Rpdml0 eSBhbmQgcHJpb3JpdHkgYWZ0ZXIgYSBzbGVlcC4NCiAJICovDQogCXNscHRp Y2sgPSB0ZC0+dGRfc2xwdGljazsNCiAJdGQtPnRkX3NscHRpY2sgPSAwOw0K LQlpZiAoc2xwdGljayAmJiBzbHB0aWNrICE9IHRpY2tzKSB7DQotCQl1X2lu dCBoenRpY2tzOw0KLQ0KLQkJaHp0aWNrcyA9ICh0aWNrcyAtIHNscHRpY2sp IDw8IFNDSEVEX1RJQ0tfU0hJRlQ7DQotCQl0cy0+dHNfc2xwdGltZSArPSBo enRpY2tzOw0KKwlpZiAoc2xwdGljayAmJiBzbHB0aWNrICE9IHRpY2tzKSAg ew0KKwkJdHMtPnRzX3NscHRpbWUgKz0gKHRpY2tzIC0gc2xwdGljaykgPDwg U0NIRURfVElDS19TSElGVDsNCiAJCXNjaGVkX2ludGVyYWN0X3VwZGF0ZSh0 ZCk7DQogCQlzY2hlZF9wY3RjcHVfdXBkYXRlKHRzKTsNCiAJCXNjaGVkX3By aW9yaXR5KHRkKTsNCisJCS8qIFJlc2V0IHRoZSBzbGljZSB2YWx1ZSBhZnRl ciB3ZSBzbGVlcC4gKi8NCisJCXRzLT50c19zbGljZSA9IDA7DQogCX0NCi0J LyogUmVzZXQgdGhlIHNsaWNlIHZhbHVlIGFmdGVyIHdlIHNsZWVwLiAqLw0K LQl0cy0+dHNfc2xpY2UgPSBzY2hlZF9zbGljZTsNCiAJc2NoZWRfYWRkKHRk LCBTUlFfQk9SSU5HKTsNCiB9DQogDQpAQCAtMjA0MCw3ICsyMDkyLDYgQEAN CiAJICovDQogCXRzMi0+dHNfc2xwdGltZSA9IHRzLT50c19zbHB0aW1lOw0K IAl0czItPnRzX3J1bnRpbWUgPSB0cy0+dHNfcnVudGltZTsNCi0JdHMyLT50 c19zbGljZSA9IDE7CS8qIEF0dGVtcHQgdG8gcXVpY2tseSBsZWFybiBpbnRl cmFjdGl2aXR5LiAqLw0KIH0NCiANCiAvKg0KQEAgLTIxODgsMjUgKzIyMzks MjYgQEANCiAJfQ0KIAl0cyA9IHRkLT50ZF9zY2hlZDsNCiAJLyoNCi0JICog V2Ugb25seSBkbyBzbGljaW5nIGNvZGUgZm9yIFRJTUVTSEFSRSB0aHJlYWRz Lg0KLQkgKi8NCi0JaWYgKHRkLT50ZF9wcmlfY2xhc3MgIT0gUFJJX1RJTUVT SEFSRSkNCi0JCXJldHVybjsNCi0JLyoNCiAJICogV2UgdXNlZCBhIHRpY2s7 IGNoYXJnZSBpdCB0byB0aGUgdGhyZWFkIHNvIHRoYXQgd2UgY2FuIGNvbXB1 dGUgb3VyDQogCSAqIGludGVyYWN0aXZpdHkuDQogCSAqLw0KIAl0ZC0+dGRf c2NoZWQtPnRzX3J1bnRpbWUgKz0gdGlja2luY3I7DQogCXNjaGVkX2ludGVy YWN0X3VwZGF0ZSh0ZCk7DQogCS8qDQorCSAqIFdlIG9ubHkgZG8gc2xpY2lu ZyBjb2RlIGZvciBUSU1FU0hBUkUgdGhyZWFkcy4NCisJICovDQorCWlmICh0 ZC0+dGRfcHJpX2NsYXNzICE9IFBSSV9USU1FU0hBUkUpDQorCQlyZXR1cm47 DQorCXNjaGVkX3ByaW9yaXR5KHRkKTsNCisJLyoNCiAJICogV2UgdXNlZCB1 cCBvbmUgdGltZSBzbGljZS4NCiAJICovDQotCWlmICgtLXRzLT50c19zbGlj ZSA+IDApDQorCWlmICgrK3RzLT50c19zbGljZSA8IHRkcV9zbGljZSh0ZHEp KQ0KIAkJcmV0dXJuOw0KIAkvKg0KLQkgKiBXZSdyZSBvdXQgb2YgdGltZSwg cmVjb21wdXRlIHByaW9yaXRpZXMgYW5kIHJlcXVldWUuDQorCSAqIFdlJ3Jl IG91dCBvZiB0aW1lLCBmb3JjZSBhIHJlcXVldWUgbGF0ZXIuDQogCSAqLw0K LQlzY2hlZF9wcmlvcml0eSh0ZCk7DQorCXRzLT50c19zbGljZSA9IDA7DQog CXRkLT50ZF9mbGFncyB8PSBUREZfTkVFRFJFU0NIRUQ7DQogfQ0KIA0KQEAg LTIzMjgsMTEgKzIzODAsMTAgQEANCiB0ZHFfYWRkKHN0cnVjdCB0ZHEgKnRk cSwgc3RydWN0IHRocmVhZCAqdGQsIGludCBmbGFncykNCiB7DQogCXN0cnVj dCB0ZF9zY2hlZCAqdHM7DQotCWludCBjbGFzczsNCiAjaWZkZWYgU01QDQor CWludCBjbGFzczsNCiAJaW50IGNwdW1hc2s7DQogI2VuZGlmDQotDQogCVRE UV9MT0NLX0FTU0VSVCh0ZHEsIE1BX09XTkVEKTsNCiAJS0FTU0VSVCgodGQt PnRkX2luaGliaXRvcnMgPT0gMCksDQogCSAgICAoInNjaGVkX2FkZDogdHJ5 aW5nIHRvIHJ1biBpbmhpYml0ZWQgdGhyZWFkIikpOw0KQEAgLTIzNDIsMjAg KzIzOTMsMTAgQEANCiAJICAgICgic2NoZWRfYWRkOiB0aHJlYWQgc3dhcHBl ZCBvdXQiKSk7DQogDQogCXRzID0gdGQtPnRkX3NjaGVkOw0KLQljbGFzcyA9 IFBSSV9CQVNFKHRkLT50ZF9wcmlfY2xhc3MpOw0KLSAgICAgICAgVERfU0VU X1JVTlEodGQpOw0KLQlpZiAodHMtPnRzX3NsaWNlID09IDApDQotCQl0cy0+ dHNfc2xpY2UgPSBzY2hlZF9zbGljZTsNCi0JLyoNCi0JICogUGljayB0aGUg cnVuIHF1ZXVlIGJhc2VkIG9uIHByaW9yaXR5Lg0KLQkgKi8NCi0JaWYgKHRk LT50ZF9wcmlvcml0eSA8PSBQUklfTUFYX1JFQUxUSU1FKQ0KLQkJdHMtPnRz X3J1bnEgPSAmdGRxLT50ZHFfcmVhbHRpbWU7DQotCWVsc2UgaWYgKHRkLT50 ZF9wcmlvcml0eSA8PSBQUklfTUFYX1RJTUVTSEFSRSkNCi0JCXRzLT50c19y dW5xID0gJnRkcS0+dGRxX3RpbWVzaGFyZTsNCi0JZWxzZQ0KLQkJdHMtPnRz X3J1bnEgPSAmdGRxLT50ZHFfaWRsZTsNCisJdGRxX3J1bnFfYWRkKHRkcSwg dHMsIGZsYWdzKTsNCisJdGRxX2xvYWRfYWRkKHRkcSwgdHMpOw0KICNpZmRl ZiBTTVANCisJY2xhc3MgPSBQUklfQkFTRSh0ZC0+dGRfcHJpX2NsYXNzKTsN CiAJY3B1bWFzayA9IDEgPDwgdHMtPnRzX2NwdTsNCiAJLyoNCiAJICogSWYg d2UgaGFkIGJlZW4gaWRsZSwgY2xlYXIgb3VyIGJpdCBpbiB0aGUgZ3JvdXAg YW5kIHBvdGVudGlhbGx5DQpAQCAtMjM3OCw4ICsyNDE5LDYgQEANCiAJaWYg KHRkLT50ZF9wcmlvcml0eSA8IHRkcS0+dGRxX2xvd3ByaSkNCiAJCXRkcS0+ dGRxX2xvd3ByaSA9IHRkLT50ZF9wcmlvcml0eTsNCiAjZW5kaWYNCi0JdGRx X3J1bnFfYWRkKHRkcSwgdHMsIGZsYWdzKTsNCi0JdGRxX2xvYWRfYWRkKHRk cSwgdHMpOw0KIH0NCiANCiAvKg0KQEAgLTI2NjAsOCArMjY5OSwxMCBAQA0K ICAgICAiU2NoZWR1bGVyIik7DQogU1lTQ1RMX1NUUklORyhfa2Vybl9zY2hl ZCwgT0lEX0FVVE8sIG5hbWUsIENUTEZMQUdfUkQsICJVTEUiLCAwLA0KICAg ICAiU2NoZWR1bGVyIG5hbWUiKTsNCi1TWVNDVExfSU5UKF9rZXJuX3NjaGVk LCBPSURfQVVUTywgc2xpY2UsIENUTEZMQUdfUlcsICZzY2hlZF9zbGljZSwg MCwNCi0gICAgIlNsaWNlIHNpemUgZm9yIHRpbWVzaGFyZSB0aHJlYWRzIik7 DQorU1lTQ1RMX0lOVChfa2Vybl9zY2hlZCwgT0lEX0FVVE8sIHNsaWNlLCBD VExGTEFHX1JXLCAmc2NoZWRfc2xpY2VfbWF4LCAwLA0KKyAgICAiTWF4aW11 bSBzbGljZSBzaXplIGZvciB0aW1lc2hhcmUgdGhyZWFkcyIpOw0KK1NZU0NU TF9JTlQoX2tlcm5fc2NoZWQsIE9JRF9BVVRPLCBzbGljZV9taW4sIENUTEZM QUdfUlcsICZzY2hlZF9zbGljZV9taW4sIDAsDQorICAgICJNaW5pbXVtIHNs aWNlIHNpemUgZm9yIHRpbWVzaGFyZSB0aHJlYWRzIik7DQogU1lTQ1RMX0lO VChfa2Vybl9zY2hlZCwgT0lEX0FVVE8sIGludGVyYWN0LCBDVExGTEFHX1JX LCAmc2NoZWRfaW50ZXJhY3QsIDAsDQogICAgICAiSW50ZXJhY3Rpdml0eSBz Y29yZSB0aHJlc2hvbGQiKTsNCiBTWVNDVExfSU5UKF9rZXJuX3NjaGVkLCBP SURfQVVUTywgcHJlZW1wdF90aHJlc2gsIENUTEZMQUdfUlcsICZwcmVlbXB0 X3RocmVzaCwNCkBAIC0yNjcxLDcgKzI3MTIsNiBAQA0KICAgICAiUGljayB0 aGUgdGFyZ2V0IGNwdSBiYXNlZCBvbiBwcmlvcml0eSByYXRoZXIgdGhhbiBs b2FkLiIpOw0KIFNZU0NUTF9JTlQoX2tlcm5fc2NoZWQsIE9JRF9BVVRPLCBh ZmZpbml0eSwgQ1RMRkxBR19SVywgJmFmZmluaXR5LCAwLA0KICAgICAiTnVt YmVyIG9mIGh6IHRpY2tzIHRvIGtlZXAgdGhyZWFkIGFmZmluaXR5IGZvciIp Ow0KLVNZU0NUTF9JTlQoX2tlcm5fc2NoZWQsIE9JRF9BVVRPLCB0cnlzZWxm LCBDVExGTEFHX1JXLCAmdHJ5c2VsZiwgMCwgIiIpOw0KIFNZU0NUTF9JTlQo X2tlcm5fc2NoZWQsIE9JRF9BVVRPLCBiYWxhbmNlLCBDVExGTEFHX1JXLCAm cmViYWxhbmNlLCAwLA0KICAgICAiRW5hYmxlcyB0aGUgbG9uZy10ZXJtIGxv YWQgYmFsYW5jZXIiKTsNCiBTWVNDVExfSU5UKF9rZXJuX3NjaGVkLCBPSURf QVVUTywgYmFsYW5jZV9pbnRlcnZhbCwgQ1RMRkxBR19SVywNCg== --0-298094039-1194126005=:544-- From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 23:06:37 2007 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 B9DCD16A46C for ; Sat, 3 Nov 2007 23:06:37 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.183]) by mx1.freebsd.org (Postfix) with ESMTP id 7988C13C49D for ; Sat, 3 Nov 2007 23:06:37 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: by py-out-1112.google.com with SMTP id u77so2361904pyb for ; Sat, 03 Nov 2007 16:06:24 -0700 (PDT) Received: by 10.35.116.12 with SMTP id t12mr3846356pym.1194124585769; Sat, 03 Nov 2007 14:16:25 -0700 (PDT) Received: by 10.35.110.17 with HTTP; Sat, 3 Nov 2007 14:16:25 -0700 (PDT) Message-ID: <8cb6106e0711031416l4183e2beueb87fade0d56f504@mail.gmail.com> Date: Sat, 3 Nov 2007 17:16:25 -0400 From: "Josh Carroll" To: "Jeff Roberson" In-Reply-To: <20071103121921.M544@10.0.0.1> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> <8cb6106e0711021839i4714bdfbh74d412b3e14e808@mail.gmail.com> <8cb6106e0711031227t1e829969s2e6062e1db5167af@mail.gmail.com> <20071103121921.M544@10.0.0.1> Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: josh.carroll@gmail.com List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 03 Nov 2007 23:06:37 -0000 > What was the -j value and number of processors? -j 8. I did the following (one warm up, 3 times in a row after that, averaged): cd /usr/src rm -rf /usr/obj/* make clean time make -j8 -DNOCLEAN buildworld The system is a Q6600, so 4 cores. Thanks, Josh From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 23:30:09 2007 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 4500E16A417 for ; Sat, 3 Nov 2007 23:30:09 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.179]) by mx1.freebsd.org (Postfix) with ESMTP id ED05B13C48D for ; Sat, 3 Nov 2007 23:30:08 +0000 (UTC) (envelope-from josh.carroll@gmail.com) Received: by py-out-1112.google.com with SMTP id u77so2369472pyb for ; Sat, 03 Nov 2007 16:29:59 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=Een5jtcms8F+NGVosdOCVbUOZyZVuA3p4pq+cB0EB7s=; b=GZIglKT5XWA3oNjtRnpaSI4XcVn2ffmKHW/t3UNZr6Bw1gi+lXOEw0QXi4QwEopUqovOkQmMvVzL/sT/KZ4d2SLu3FPlAjIURb1WXOAN3EBW+lu5pesjmGVhyG49IC+IZSCF+cOD7oWM7JPS+hEH6AO/W5+fnRKXLv1F7wz6ut4= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=KXYPyMqXCCsHpwyEn9TuiLx/x0w3Y/5M6HYC8uX1F1RS6cATd3Me+66/REtkLDpaQEF8DJi+Db5rj/RwXK9rdWaBqzkKL4jdDphw034Cqny/4n5IiCvMcjpCkZdwMtbqYQmMNljp3dPWdKCK6a1RyGwELi1C7GbwyyfXV5nIZ1c= Received: by 10.35.92.18 with SMTP id u18mr3980319pyl.1194132599464; Sat, 03 Nov 2007 16:29:59 -0700 (PDT) Received: by 10.35.110.17 with HTTP; Sat, 3 Nov 2007 16:29:59 -0700 (PDT) Message-ID: <8cb6106e0711031629j68e181ccra0f16ee6f42ed982@mail.gmail.com> Date: Sat, 3 Nov 2007 19:29:59 -0400 From: "Josh Carroll" To: "Jeff Roberson" In-Reply-To: <20071102150028.R544@10.0.0.1> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: josh.carroll@gmail.com List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 03 Nov 2007 23:30:09 -0000 > What would be interesting to know is if the sum of the temperatures is any > different. 4BSD gets a much more random distribution of load because a > thread is run on whatever cpu context switches next. ULE will have > specific load patterns since it scans lists of cpus in a fixed order to > assign load. So that means it prefers to run on lower numbered cpus if > they are idle. This should have a side effect of allowing unused cores to > powerdown more frequently than with 4BSD although I have not verified this > in practice. The sum of the core temperatures when the system is idle is the same for both ULE and 4BSD. 125 C in my case (31.25 C average). Under load, the sum (again for both) is 184 C. So you're absolutely correct, while one core seems to get these short bursts (probably my rrd script doing its thing), perhaps this is shared over the cores with 4BSD. The overall temperature remains the same. Josh From owner-freebsd-performance@FreeBSD.ORG Sat Nov 3 23:52:33 2007 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 44F9A16A418 for ; Sat, 3 Nov 2007 23:52:33 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from webaccess-cl.virtdom.com (webaccess-cl.virtdom.com [216.240.101.25]) by mx1.freebsd.org (Postfix) with ESMTP id E3DEE13C4A3 for ; Sat, 3 Nov 2007 23:52:32 +0000 (UTC) (envelope-from jroberson@chesapeake.net) Received: from [192.168.1.100] (cpe-24-94-75-93.hawaii.res.rr.com [24.94.75.93]) (authenticated bits=0) by webaccess-cl.virtdom.com (8.13.6/8.13.6) with ESMTP id lA3Npi66074036 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NO); Sat, 3 Nov 2007 19:51:45 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Sat, 3 Nov 2007 15:53:44 -0800 (PST) From: Jeff Roberson X-X-Sender: jroberson@10.0.0.1 To: Josh Carroll In-Reply-To: <8cb6106e0711031629j68e181ccra0f16ee6f42ed982@mail.gmail.com> Message-ID: <20071103155130.Y544@10.0.0.1> References: <8cb6106e0710230902x4edf2c8eu2d912d5de1f5d4a2@mail.gmail.com> <20071024111105.M598@10.0.0.1> <8cb6106e0710241229i12852d8cq436f4c955ac62c56@mail.gmail.com> <20071024133240.X598@10.0.0.1> <8cb6106e0710251925s2db0117cvcb67321b08d7b2a1@mail.gmail.com> <20071102102331.G544@10.0.0.1> <8cb6106e0711021306w10c48a15s99eab526064ac814@mail.gmail.com> <20071102150028.R544@10.0.0.1> <8cb6106e0711031629j68e181ccra0f16ee6f42ed982@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: ULE vs. 4BSD in RELENG_7 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: Sat, 03 Nov 2007 23:52:33 -0000 On Sat, 3 Nov 2007, Josh Carroll wrote: >> What would be interesting to know is if the sum of the temperatures is any >> different. 4BSD gets a much more random distribution of load because a >> thread is run on whatever cpu context switches next. ULE will have >> specific load patterns since it scans lists of cpus in a fixed order to >> assign load. So that means it prefers to run on lower numbered cpus if >> they are idle. This should have a side effect of allowing unused cores to >> powerdown more frequently than with 4BSD although I have not verified this >> in practice. > > The sum of the core temperatures when the system is idle is the same > for both ULE and 4BSD. 125 C in my case (31.25 C average). Under load, > the sum (again for both) is 184 C. So you're absolutely correct, while > one core seems to get these short bursts (probably my rrd script doing > its thing), perhaps this is shared over the cores with 4BSD. The > overall temperature remains the same. That's great to know. It would be possible to develop load balancing algorithms that attempt to keep as many cores as possible idling without sacraficing too much performance to improve power usage. This is something I've been thinking about as part of load balancing and topology improvements for 8.0. It's important to note that temperature of individual cores may not be the best estimate of power usage by that core since you would expect heat to travel well across a package leading to elevated temperatures for otherwise idle parts. Jeff > > Josh > _______________________________________________ > 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" >