From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Lezcano Subject: Re: [PATCH v4] cpuidle: Fix last_residency division Date: Thu, 30 Jun 2016 16:57:34 +0200 Message-ID: <5775335E.2040003@linaro.org> References: <1467297253-2171-1-git-send-email-shreyas@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8"; Format="flowed" Content-Transfer-Encoding: base64 Return-path: In-Reply-To: <1467297253-2171-1-git-send-email-shreyas@linux.vnet.ibm.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: linuxppc-dev-bounces+glppe-linuxppc-embedded-2=m.gmane.org@lists.ozlabs.org Sender: "Linuxppc-dev" To: "Shreyas B. Prabhu" , rjw@rjwysocki.net Cc: nicolas.pitre@linaro.org, arnd@arndb.de, linux-pm@vger.kernel.org, David.Laight@ACULAB.COM, anton@samba.org, linuxppc-dev@lists.ozlabs.org List-Id: linux-pm@vger.kernel.org T24gMDYvMzAvMjAxNiAwNDozNCBQTSwgU2hyZXlhcyBCLiBQcmFiaHUgd3JvdGU6Cj4gU25vb3pl IGlzIGEgcG9sbCBpZGxlIHN0YXRlIGluIHBvd2VybnYgYW5kIHBzZXJpZXMgcGxhdGZvcm1zLiBT bm9vemUKPiBoYXMgYSB0aW1lb3V0IHNvIHRoYXQgaWYgYSBjcHUgc3RheXMgaW4gc25vb3plIGZv ciBtb3JlIHRoYW4gdGFyZ2V0Cj4gcmVzaWRlbmN5IG9mIHRoZSBuZXh0IGF2YWlsYWJsZSBpZGxl IHN0YXRlLCB0aGVuIGl0IHdvdWxkIGV4aXQgdGhlcmVieQo+IGdpdmluZyBjaGFuY2UgdG8gdGhl IGNwdWlkbGUgZ292ZXJub3IgdG8gcmUtZXZhbHVhdGUgYW5kCj4gcHJvbW90ZSB0aGUgY3B1IHRv IGEgZGVlcGVyIGlkbGUgc3RhdGUuIFRoZXJlZm9yZSB3aGVuZXZlciBzbm9vemUgZXhpdHMKPiBk dWUgdG8gdGhpcyB0aW1lb3V0LCBpdHMgbGFzdF9yZXNpZGVuY3kgd2lsbCBiZSB0YXJnZXRfcmVz aWRlbmN5IG9mIG5leHQKPiBkZWVwZXIgc3RhdGUuCj4KPiBjb21taXQgZTkzZTU5Y2U1Yjg1ICgi Y3B1aWRsZTogUmVwbGFjZSBrdGltZV9nZXQoKSB3aXRoIGxvY2FsX2Nsb2NrKCkiKQo+IGNoYW5n ZWQgdGhlIG1hdGggYXJvdW5kIGxhc3RfcmVzaWRlbmN5IGNhbGN1bGF0aW9uLiBTcGVjaWZpY2Fs bHksIHdoaWxlCj4gY29udmVydGluZyBsYXN0X3Jlc2lkZW5jeSB2YWx1ZSBmcm9tIG5hbm9zZWNv bmRzIHRvIG1pY3Jvc2Vjb25kcyBpdCBkb2VzCj4gcmlnaHQgc2hpZnQgYnkgMTAuIER1ZSB0byB0 aGlzLCBpbiBzbm9vemUgdGltZW91dCBleGl0IHNjZW5hcmlvcwo+IGxhc3RfcmVzaWRlbmN5IGNh bGN1bGF0ZWQgaXMgcm91Z2hseSAyLjMlIGxlc3MgdGhhbiB0YXJnZXRfcmVzaWRlbmN5IG9mCj4g bmV4dCBhdmFpbGFibGUgc3RhdGUuIFRoaXMgcGF0dGVybiBpcyBwaWNrZWQgdXAgZ2V0X3R5cGlj YWxfaW50ZXJ2YWwoKQo+IGluIHRoZSBtZW51IGdvdmVybm9yIGFuZCB0aGVyZWZvcmUgZXhwZWN0 ZWRfaW50ZXJ2YWwgaW4gbWVudV9zZWxlY3QoKSBpcwo+IGZyZXF1ZW50bHkgbGVzcyB0aGFuIHRo ZSB0YXJnZXRfcmVzaWRlbmN5IG9mIGFueSBzdGF0ZSBidXQgc25vb3plLgo+Cj4gRHVlIHRvIHRo aXMgd2UgYXJlIGVudGVyaW5nIHNub296ZSBhdCBhIGhpZ2hlciByYXRlLCB0aGVyZWJ5IGFmZmVj dGluZwo+IHRoZSBzaW5nbGUgdGhyZWFkIHBlcmZvcm1hbmNlLgo+Cj4gRml4IHRoaXMgYnkgdXNp bmcgYSBiZXR0ZXIgYXBwcm94aW1hdGlvbiBmb3IgZGl2aXNpb24gYnkgMTAwMC4KPgo+IFJlcG9y dGVkLWJ5OiBBbnRvbiBCbGFuY2hhcmQgPGFudG9uQHNhbWJhLm9yZz4KPiBCaXNlY3RlZC1ieTog U2hpbHBhc3JpIEcgQmhhdCA8c2hpbHBhLmJoYXRAbGludXgudm5ldC5pYm0uY29tPgo+IFN1Z2dl c3RlZC1ieSBEYXZpZCBMYWlnaHQgPGRhdmlkLmxhaWdodEBhY3VsYWIuY29tPgo+IFNpZ25lZC1v ZmYtYnk6IFNocmV5YXMgQi4gUHJhYmh1IDxzaHJleWFzQGxpbnV4LnZuZXQuaWJtLmNvbT4KPiAt LS0KPiBDaGFuZ2VzIGluIHY0Cj4gPT09PT09PT09PT09PQo+ICAgLSBJbmNyZWFzaW5nIHRoZSB0 aHJlc2hvbGQgdXB0byB3aGljaCBhcHByb3hpbWF0aW9uIGNhbiBiZSB1c2VkLgo+ICAgLSBSZW1v dmVkIGV4cGxpY2l0IGNhc3QuIEluc3RlYWQgYWRkZWQgYSBjb21tZW50IHNheWluZyB3aHkgY2Fz dAo+ICAgICBpcyBzYWZlLgo+Cj4gQ2hhbmdlcyBpbiB2Mwo+ID09PT09PT09PT09PT0KPiAgIC0g VXNpbmcgYXBwcm94aW1hdGlvbiBzdWdnZXN0ZWQgYnkgRGF2aWQKPgo+IENoYW5nZXMgaW4gdjIK PiA9PT09PT09PT09PT09Cj4gICAtIEZpeGluZyBpdCBpbiB0aGUgY3B1aWRsZSBjb3JlIGNvZGUg aW5zdGVhZCBvZiBkcml2ZXIgY29kZS4KPgo+ICAgZHJpdmVycy9jcHVpZGxlL2NwdWlkbGUuYyB8 IDExICsrKy0tLS0tLS0tCj4gICBkcml2ZXJzL2NwdWlkbGUvY3B1aWRsZS5oIHwgMzggKysrKysr KysrKysrKysrKysrKysrKysrKysrKysrKysrKysrKysKPiAgIDIgZmlsZXMgY2hhbmdlZCwgNDEg aW5zZXJ0aW9ucygrKSwgOCBkZWxldGlvbnMoLSkKPgo+IGRpZmYgLS1naXQgYS9kcml2ZXJzL2Nw dWlkbGUvY3B1aWRsZS5jIGIvZHJpdmVycy9jcHVpZGxlL2NwdWlkbGUuYwo+IGluZGV4IGE0ZDAw NTkuLmY1NWFkMDEgMTAwNjQ0Cj4gLS0tIGEvZHJpdmVycy9jcHVpZGxlL2NwdWlkbGUuYwo+ICsr KyBiL2RyaXZlcnMvY3B1aWRsZS9jcHVpZGxlLmMKPiBAQCAtMTc0LDcgKzE3NCw2IEBAIGludCBj cHVpZGxlX2VudGVyX3N0YXRlKHN0cnVjdCBjcHVpZGxlX2RldmljZSAqZGV2LCBzdHJ1Y3QgY3B1 aWRsZV9kcml2ZXIgKmRydiwKPiAgIAlzdHJ1Y3QgY3B1aWRsZV9zdGF0ZSAqdGFyZ2V0X3N0YXRl ID0gJmRydi0+c3RhdGVzW2luZGV4XTsKPiAgIAlib29sIGJyb2FkY2FzdCA9ICEhKHRhcmdldF9z dGF0ZS0+ZmxhZ3MgJiBDUFVJRExFX0ZMQUdfVElNRVJfU1RPUCk7Cj4gICAJdTY0IHRpbWVfc3Rh cnQsIHRpbWVfZW5kOwo+IC0JczY0IGRpZmY7Cj4KPiAgIAkvKgo+ICAgCSAqIFRlbGwgdGhlIHRp bWUgZnJhbWV3b3JrIHRvIHN3aXRjaCB0byBhIGJyb2FkY2FzdCB0aW1lciBiZWNhdXNlIG91cgo+ IEBAIC0yMTgsMTQgKzIxNywxMCBAQCBpbnQgY3B1aWRsZV9lbnRlcl9zdGF0ZShzdHJ1Y3QgY3B1 aWRsZV9kZXZpY2UgKmRldiwgc3RydWN0IGNwdWlkbGVfZHJpdmVyICpkcnYsCj4gICAJCWxvY2Fs X2lycV9lbmFibGUoKTsKPgo+ICAgCS8qCj4gLQkgKiBsb2NhbF9jbG9jaygpIHJldHVybnMgdGhl IHRpbWUgaW4gbmFub3NlY29uZCwgbGV0J3Mgc2hpZnQKPiAtCSAqIGJ5IDEwIChkaXZpZGUgYnkg MTAyNCkgdG8gaGF2ZSBtaWNyb3NlY29uZCBiYXNlZCB0aW1lLgo+ICsJICogbG9jYWxfY2xvY2so KSByZXR1cm5zIHRoZSB0aW1lIGluIG5hbm9zZWNvbmRzLCBjb252ZXJ0IGl0IHRvCj4gKwkgKiBt aWNyb3NlY29uZCBiYXNlZCB0aW1lLgo+ICAgCSAqLwo+IC0JZGlmZiA9ICh0aW1lX2VuZCAtIHRp bWVfc3RhcnQpID4+IDEwOwo+IC0JaWYgKGRpZmYgPiBJTlRfTUFYKQo+IC0JCWRpZmYgPSBJTlRf TUFYOwo+IC0KPiAtCWRldi0+bGFzdF9yZXNpZGVuY3kgPSAoaW50KSBkaWZmOwo+ICsJZGV2LT5s YXN0X3Jlc2lkZW5jeSA9IGNvbnZlcnRfbnNlY190b191c2VjKHRpbWVfZW5kIC0gdGltZV9zdGFy dCk7Cj4KPiAgIAlpZiAoZW50ZXJlZF9zdGF0ZSA+PSAwKSB7Cj4gICAJCS8qIFVwZGF0ZSBjcHVp ZGxlIGNvdW50ZXJzICovCj4gZGlmZiAtLWdpdCBhL2RyaXZlcnMvY3B1aWRsZS9jcHVpZGxlLmgg Yi9kcml2ZXJzL2NwdWlkbGUvY3B1aWRsZS5oCj4gaW5kZXggZjg3ZjM5OS4uYTAyN2IzNSAxMDA2 NDQKPiAtLS0gYS9kcml2ZXJzL2NwdWlkbGUvY3B1aWRsZS5oCj4gKysrIGIvZHJpdmVycy9jcHVp ZGxlL2NwdWlkbGUuaAo+IEBAIC02OCw0ICs2OCw0MiBAQCBzdGF0aWMgaW5saW5lIHZvaWQgY3B1 aWRsZV9jb3VwbGVkX3VucmVnaXN0ZXJfZGV2aWNlKHN0cnVjdCBjcHVpZGxlX2RldmljZSAqZGV2 KQo+ICAgfQo+ICAgI2VuZGlmCj4KPiArLyoKPiArICogVG8gZW5zdXJlIHRoYXQgdGhlcmUgaXMg bm8gb3ZlcmZsb3cgd2hpbGUgYXBwcm94aW1hdGlvbgo+ICsgKiBmb3IgZGl2aWRpbmcgdmFsIGJ5 IDEwMDAsIHdlIG11c3QgcmVzcGVjdCAtCj4gKyAqIHZhbCArICh2YWwgPj4gNSkgPD0gMHhGRkZG RkZGRgo+ICsgKiB2YWwgKyB2YWwvMzIgPD0gMHhGRkZGRkZGRgo+ICsgKiB2YWwgPD0gKDB4RkZG RkZGRkYgKiAzMikgLyAzMwo+ICsgKiB2YWwgPD0gMHhGODNFMEY4Mgo+ICsgKiBIZW5jZSB0aGUg dGhyZXNob2xkIGZvciB2YWwgYmVsb3cgd2hpY2ggd2UgY2FuIHVzZSB0aGUKPiArICogYXBwcm94 aW1hdGlvbiBpcyAweEY4M0UwRjgyCj4gKyAqLwo+ICsjZGVmaW5lIERJVl9BUFBST1hJTUFUSU9O X1RIUkVTSE9MRCAweEY4M0UwRjgyVUwKPiArCj4gKy8qCj4gKyAqIFVzZWQgZm9yIGNhbGN1bGF0 aW5nIGxhc3RfcmVzaWRlbmN5IGluIHVzZWMuIE9wdGltaXplZCBmb3IgY2FzZQo+ICsgKiB3aGVy ZSBsYXN0X3Jlc2lkZW5jeSBpbiBuc2VjcyBpcyA8IERJVl9BUFBST1hJTUFUSU9OX1RIUkVTSE9M RAo+ICsgKiBBcHByb3hpbWF0ZWQgdmFsdWUgaGFzIGxlc3MgdGhhbiAxJSBlcnJvci4KPiArICov Cj4gK3N0YXRpYyBpbmxpbmUgaW50IGNvbnZlcnRfbnNlY190b191c2VjKHU2NCBuc2VjKQo+ICt7 Cj4gKwlpZiAobGlrZWx5KG5zZWMgPCBESVZfQVBQUk9YSU1BVElPTl9USFJFU0hPTEQpKSB7Cj4g KwkJdTMyIHVzZWMgPSBuc2VjOwo+ICsKPiArCQl1c2VjICs9IHVzZWMgPj4gNTsKPiArCQl1c2Vj ID0gdXNlYyA+PiAxMDsKPiArCj4gKwkJLyogQ2FuIHNhZmVseSBjYXN0IHRvIGludCBzaW5jZSB1 c2VjIGlzIDwgSU5UX01BWCAqLwo+ICsJCXJldHVybiB1c2VjOwo+ICsJfSBlbHNlIHsKPiArCQl1 NjQgdXNlYyA9IGRpdl91NjQobnNlYywgMTAwMCk7Cj4gKwo+ICsJCWlmICh1c2VjID4gSU5UX01B WCkKPiArCQkJdXNlYyA9IElOVF9NQVg7Cj4gKwo+ICsJCS8qIENhbiBzYWZlbHkgY2FzdCB0byBp bnQgc2luY2UgdXNlYyBpcyA8IElOVF9NQVggKi8KPiArCQlyZXR1cm4gdXNlYzsKPiArCX0KPiAr fQoKCldoYXQgYm90aGVycyBtZSB3aXRoIHRoaXMgZGl2aXNpb24gaXMgdGhlIGJlbmVmaXQgb2Yg YWRkaW5nIGFuIGV4dHJhIAp1bHRyYSBvcHRpbWl6ZWQgZGl2aXNpb24gYnkgMTAwMCBpbiBjcHVp ZGxlLmggd2hpbGUgd2UgaGF2ZSBhbHJlYWR5IAprdGltZV9kaXZucyB3aGljaCBpcyBvcHRpbWl6 ZWQgaW4ga3RpbWUuaC4KCldoeSBub3Q6Cgp0cyA9IG5zX3RvX2t0aW1lKGxvY2FsX2Nsb2NrKCkp OwoKLi4uCgp0ZSA9IG5zX3RvX2t0aW1lKGxvY2FsX2Nsb2NrKCkpOwoKCmRpZmYgPSBrdGltZV91 c19kZWx0YSh0ZSwgdHMpOwoKCgoKCi0tIAogIDxodHRwOi8vd3d3LmxpbmFyby5vcmcvPiBMaW5h cm8ub3JnIOKUgiBPcGVuIHNvdXJjZSBzb2Z0d2FyZSBmb3IgQVJNIFNvQ3MKCkZvbGxvdyBMaW5h cm86ICA8aHR0cDovL3d3dy5mYWNlYm9vay5jb20vcGFnZXMvTGluYXJvPiBGYWNlYm9vayB8Cjxo dHRwOi8vdHdpdHRlci5jb20vIyEvbGluYXJvb3JnPiBUd2l0dGVyIHwKPGh0dHA6Ly93d3cubGlu YXJvLm9yZy9saW5hcm8tYmxvZy8+IEJsb2cKCl9fX19fX19fX19fX19fX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fCkxpbnV4cHBjLWRldiBtYWlsaW5nIGxpc3QKTGludXhwcGMtZGV2 QGxpc3RzLm96bGFicy5vcmcKaHR0cHM6Ly9saXN0cy5vemxhYnMub3JnL2xpc3RpbmZvL2xpbnV4 cHBjLWRldg== From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wm0-x229.google.com (mail-wm0-x229.google.com [IPv6:2a00:1450:400c:c09::229]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3rgN1w4Px0zDr30 for ; Fri, 1 Jul 2016 00:57:40 +1000 (AEST) Received: by mail-wm0-x229.google.com with SMTP id f126so225479626wma.1 for ; Thu, 30 Jun 2016 07:57:39 -0700 (PDT) Subject: Re: [PATCH v4] cpuidle: Fix last_residency division To: "Shreyas B. Prabhu" , rjw@rjwysocki.net References: <1467297253-2171-1-git-send-email-shreyas@linux.vnet.ibm.com> Cc: linux-pm@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, anton@samba.org, mpe@ellerman.id.au, bsingharora@gmail.com, David.Laight@ACULAB.COM, arnd@arndb.de, nicolas.pitre@linaro.org From: Daniel Lezcano Message-ID: <5775335E.2040003@linaro.org> Date: Thu, 30 Jun 2016 16:57:34 +0200 MIME-Version: 1.0 In-Reply-To: <1467297253-2171-1-git-send-email-shreyas@linux.vnet.ibm.com> Content-Type: text/plain; charset=UTF-8; format=flowed List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On 06/30/2016 04:34 PM, Shreyas B. Prabhu wrote: > Snooze is a poll idle state in powernv and pseries platforms. Snooze > has a timeout so that if a cpu stays in snooze for more than target > residency of the next available idle state, then it would exit thereby > giving chance to the cpuidle governor to re-evaluate and > promote the cpu to a deeper idle state. Therefore whenever snooze exits > due to this timeout, its last_residency will be target_residency of next > deeper state. > > commit e93e59ce5b85 ("cpuidle: Replace ktime_get() with local_clock()") > changed the math around last_residency calculation. Specifically, while > converting last_residency value from nanoseconds to microseconds it does > right shift by 10. Due to this, in snooze timeout exit scenarios > last_residency calculated is roughly 2.3% less than target_residency of > next available state. This pattern is picked up get_typical_interval() > in the menu governor and therefore expected_interval in menu_select() is > frequently less than the target_residency of any state but snooze. > > Due to this we are entering snooze at a higher rate, thereby affecting > the single thread performance. > > Fix this by using a better approximation for division by 1000. > > Reported-by: Anton Blanchard > Bisected-by: Shilpasri G Bhat > Suggested-by David Laight > Signed-off-by: Shreyas B. Prabhu > --- > Changes in v4 > ============= > - Increasing the threshold upto which approximation can be used. > - Removed explicit cast. Instead added a comment saying why cast > is safe. > > Changes in v3 > ============= > - Using approximation suggested by David > > Changes in v2 > ============= > - Fixing it in the cpuidle core code instead of driver code. > > drivers/cpuidle/cpuidle.c | 11 +++-------- > drivers/cpuidle/cpuidle.h | 38 ++++++++++++++++++++++++++++++++++++++ > 2 files changed, 41 insertions(+), 8 deletions(-) > > diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c > index a4d0059..f55ad01 100644 > --- a/drivers/cpuidle/cpuidle.c > +++ b/drivers/cpuidle/cpuidle.c > @@ -174,7 +174,6 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, > struct cpuidle_state *target_state = &drv->states[index]; > bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); > u64 time_start, time_end; > - s64 diff; > > /* > * Tell the time framework to switch to a broadcast timer because our > @@ -218,14 +217,10 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, > local_irq_enable(); > > /* > - * local_clock() returns the time in nanosecond, let's shift > - * by 10 (divide by 1024) to have microsecond based time. > + * local_clock() returns the time in nanoseconds, convert it to > + * microsecond based time. > */ > - diff = (time_end - time_start) >> 10; > - if (diff > INT_MAX) > - diff = INT_MAX; > - > - dev->last_residency = (int) diff; > + dev->last_residency = convert_nsec_to_usec(time_end - time_start); > > if (entered_state >= 0) { > /* Update cpuidle counters */ > diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h > index f87f399..a027b35 100644 > --- a/drivers/cpuidle/cpuidle.h > +++ b/drivers/cpuidle/cpuidle.h > @@ -68,4 +68,42 @@ static inline void cpuidle_coupled_unregister_device(struct cpuidle_device *dev) > } > #endif > > +/* > + * To ensure that there is no overflow while approximation > + * for dividing val by 1000, we must respect - > + * val + (val >> 5) <= 0xFFFFFFFF > + * val + val/32 <= 0xFFFFFFFF > + * val <= (0xFFFFFFFF * 32) / 33 > + * val <= 0xF83E0F82 > + * Hence the threshold for val below which we can use the > + * approximation is 0xF83E0F82 > + */ > +#define DIV_APPROXIMATION_THRESHOLD 0xF83E0F82UL > + > +/* > + * Used for calculating last_residency in usec. Optimized for case > + * where last_residency in nsecs is < DIV_APPROXIMATION_THRESHOLD > + * Approximated value has less than 1% error. > + */ > +static inline int convert_nsec_to_usec(u64 nsec) > +{ > + if (likely(nsec < DIV_APPROXIMATION_THRESHOLD)) { > + u32 usec = nsec; > + > + usec += usec >> 5; > + usec = usec >> 10; > + > + /* Can safely cast to int since usec is < INT_MAX */ > + return usec; > + } else { > + u64 usec = div_u64(nsec, 1000); > + > + if (usec > INT_MAX) > + usec = INT_MAX; > + > + /* Can safely cast to int since usec is < INT_MAX */ > + return usec; > + } > +} What bothers me with this division is the benefit of adding an extra ultra optimized division by 1000 in cpuidle.h while we have already ktime_divns which is optimized in ktime.h. Why not: ts = ns_to_ktime(local_clock()); ... te = ns_to_ktime(local_clock()); diff = ktime_us_delta(te, ts); -- Linaro.org │ Open source software for ARM SoCs Follow Linaro: Facebook | Twitter | Blog