Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752487AbcDJJfT (ORCPT ); Sun, 10 Apr 2016 05:35:19 -0400 Received: from mail-wm0-f50.google.com ([74.125.82.50]:34491 "EHLO mail-wm0-f50.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751439AbcDJJfQ (ORCPT ); Sun, 10 Apr 2016 05:35:16 -0400 Message-ID: <1460280912.4251.27.camel@gmail.com> Subject: Re: [regression] cross core scheduling frequency drop bisected to 0c313cb20732 From: Mike Galbraith To: "Rafael J. Wysocki" Cc: "Rafael J. Wysocki" , Peter Zijlstra , "Rafael J. Wysocki" , LKML , Linux PM list , Doug Smythies , Rik van Riel Date: Sun, 10 Apr 2016 11:35:12 +0200 In-Reply-To: References: <1460092854.4051.1.camel@gmail.com> <20160408064510.GK3448@twins.programming.kicks-ass.net> <1460098254.5582.17.camel@gmail.com> <2428384.mEkP3EOpsR@vostro.rjw.lan> <1460184056.3765.160.camel@gmail.com> <1460214622.3714.8.camel@gmail.com> <1460219974.3700.39.camel@gmail.com> Content-Type: multipart/mixed; boundary="=-+mPqGqRbFkKsG8+AZvW8" X-Mailer: Evolution 3.16.5 Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4513 Lines: 93 --=-+mPqGqRbFkKsG8+AZvW8 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit On Sun, 2016-04-10 at 05:44 +0200, Rafael J. Wysocki wrote: > On Sat, Apr 9, 2016 at 6:39 PM, Mike Galbraith < > umgwanakikbuti@gmail.com> wrote: > > > > Hm, setting gov=performance, and taking the average of 3 30 second > > interval PkgWatt samples as pipe-test runs.. > > > > 714KHz/28.03Ws = 25.46 > > 877KHz/30.28Ws = 28.96 > > > > ..for pipe-test, the tradeoff look a bit more like red than green. > > Well, fair enough, but that's just pipe-test, and what about the > people who don't see the performance gain and see the energy loss, > like Doug? Perhaps Doug sees increased power because he's not throttling no_hz, whereas I am, so he burns more power getting _to_ idle? Dunno, maybe he'll try the attached. If it's a general case energy loser, so be it, numbers talk, bs walks and all that ;-) > Essentially, this trades performance gains in somewhat special > workloads for increased energy consumption in idle. Those workloads > need not be run by everybody, but idle is. Cross core scheduling is routine business, we do truckloads of that for good reason, and lots of stuff does wakeups at high frequency. > That said I applied the patch you're complaining about mostly because > the commit that introduced the change in question in 4.5 claimed that > it wouldn't affect idle power on systems with reasonably fast C1, but > that didn't pass the reality test. I'm not totally against restoring > that change, but it would need to be based on very solid evidence. Understood. My box seems to be saying we can hug the trees hardest by telling the CPU get work done as quickly as possible, but I don't have much experience at tree hugging measurement. Performance wise, tasks talking via localhost is definitely not special. tbench 1 2 4 8 base 752 1283 2250 3362 select_idle_sibling() off 735 1344 2080 2884 delta .977 1.047 .924 .857 select_idle_sibling() on, 0c313cb20732 reverted 816 1317 2240 3388 delta 1.085 1.026 .995 1.007 vs base delta 1.110 .979 1.076 1.174 vs off (^hm) -Mike --=-+mPqGqRbFkKsG8+AZvW8 Content-Disposition: attachment; filename="sched-throttle-nohz.patch" Content-Type: text/x-patch; name="sched-throttle-nohz.patch"; charset="UTF-8" Content-Transfer-Encoding: base64 c2NoZWQ6IHJhdGVsaW1pdCBub2h6CgpFbnRlcmluZyBub2h6IGNvZGUgb24gZXZlcnkgbWljcm8t aWRsZSBpcyB0b28gZXhwZW5zaXZlIHRvIGJlYXIuCgpTaWduZWQtb2ZmLWJ5OiBNaWtlIEdhbGJy YWl0aCA8ZWZhdWx0QGdteC5kZT4KLS0tCiBpbmNsdWRlL2xpbnV4L3NjaGVkLmggICAgfCAgICA1 ICsrKysrCiBrZXJuZWwvc2NoZWQvY29yZS5jICAgICAgfCAgICA4ICsrKysrKysrCiBrZXJuZWwv dGltZS90aWNrLXNjaGVkLmMgfCAgICAyICstCiAzIGZpbGVzIGNoYW5nZWQsIDE0IGluc2VydGlv bnMoKyksIDEgZGVsZXRpb24oLSkKCi0tLSBhL2luY2x1ZGUvbGludXgvc2NoZWQuaAorKysgYi9p bmNsdWRlL2xpbnV4L3NjaGVkLmgKQEAgLTIyODYsNiArMjI4NiwxMSBAQCBzdGF0aWMgaW5saW5l IGludCBzZXRfY3B1c19hbGxvd2VkX3B0cihzCiAjaWZkZWYgQ09ORklHX05PX0haX0NPTU1PTgog dm9pZCBjYWxjX2xvYWRfZW50ZXJfaWRsZSh2b2lkKTsKIHZvaWQgY2FsY19sb2FkX2V4aXRfaWRs ZSh2b2lkKTsKKyNpZmRlZiBDT05GSUdfU01QCitleHRlcm4gaW50IHNjaGVkX25lZWRzX2NwdShp bnQgY3B1KTsKKyNlbHNlCitzdGF0aWMgaW5saW5lIGludCBzY2hlZF9uZWVkc19jcHUoaW50IGNw dSkgeyByZXR1cm4gMDsgfQorI2VuZGlmCiAjZWxzZQogc3RhdGljIGlubGluZSB2b2lkIGNhbGNf bG9hZF9lbnRlcl9pZGxlKHZvaWQpIHsgfQogc3RhdGljIGlubGluZSB2b2lkIGNhbGNfbG9hZF9l eGl0X2lkbGUodm9pZCkgeyB9Ci0tLSBhL2tlcm5lbC9zY2hlZC9jb3JlLmMKKysrIGIva2VybmVs L3NjaGVkL2NvcmUuYwpAQCAtNTc3LDYgKzU3NywxNCBAQCBzdGF0aWMgaW5saW5lIGJvb2wgZ290 X25vaHpfaWRsZV9raWNrKHZvCiAJcmV0dXJuIGZhbHNlOwogfQogCitpbnQgc2NoZWRfbmVlZHNf Y3B1KGludCBjcHUpCit7CisJaWYgKHRpY2tfbm9oel9mdWxsX2NwdShjcHUpKQorCQlyZXR1cm4g MDsKKworCXJldHVybiAgY3B1X3JxKGNwdSktPmF2Z19pZGxlIDwgc3lzY3RsX3NjaGVkX21pZ3Jh dGlvbl9jb3N0OworfQorCiAjZWxzZSAvKiBDT05GSUdfTk9fSFpfQ09NTU9OICovCiAKIHN0YXRp YyBpbmxpbmUgYm9vbCBnb3Rfbm9oel9pZGxlX2tpY2sodm9pZCkKLS0tIGEva2VybmVsL3RpbWUv dGljay1zY2hlZC5jCisrKyBiL2tlcm5lbC90aW1lL3RpY2stc2NoZWQuYwpAQCAtNjc2LDcgKzY3 Niw3IEBAIHN0YXRpYyBrdGltZV90IHRpY2tfbm9oel9zdG9wX3NjaGVkX3RpY2sKIAl9IHdoaWxl IChyZWFkX3NlcXJldHJ5KCZqaWZmaWVzX2xvY2ssIHNlcSkpOwogCXRzLT5sYXN0X2ppZmZpZXMg PSBiYXNlamlmZjsKIAotCWlmIChyY3VfbmVlZHNfY3B1KGJhc2Vtb25vLCAmbmV4dF9yY3UpIHx8 CisJaWYgKHNjaGVkX25lZWRzX2NwdShjcHUpIHx8IHJjdV9uZWVkc19jcHUoYmFzZW1vbm8sICZu ZXh0X3JjdSkgfHwKIAkgICAgYXJjaF9uZWVkc19jcHUoKSB8fCBpcnFfd29ya19uZWVkc19jcHUo KSkgewogCQluZXh0X3RpY2sgPSBiYXNlbW9ubyArIFRJQ0tfTlNFQzsKIAl9IGVsc2Ugewo= --=-+mPqGqRbFkKsG8+AZvW8--