From patchwork Mon Jul 13 21:13:18 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Guoqing Jiang X-Patchwork-Id: 11661021 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 77EF0618 for ; Mon, 13 Jul 2020 21:13:56 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 593162082E for ; Mon, 13 Jul 2020 21:13:56 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=cloud.ionos.com header.i=@cloud.ionos.com header.b="KqHuHUAn" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726446AbgGMVNz (ORCPT ); Mon, 13 Jul 2020 17:13:55 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35798 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726400AbgGMVNz (ORCPT ); Mon, 13 Jul 2020 17:13:55 -0400 Received: from mail-ej1-x642.google.com (mail-ej1-x642.google.com [IPv6:2a00:1450:4864:20::642]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3872CC061755 for ; Mon, 13 Jul 2020 14:13:55 -0700 (PDT) Received: by mail-ej1-x642.google.com with SMTP id dp18so19019433ejc.8 for ; Mon, 13 Jul 2020 14:13:55 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cloud.ionos.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=nvoC+buu5tasYx6T8UBAK6LFJaCdJgALnFZc/9QT04M=; b=KqHuHUAnCR/6DqOS8U6H/f4y0mOneoVWxjNEMglmjVVvv85PlkzQpvQpgroFZXq0fO VmcvAZhanPBHQIcMFmxQ2Dhc/ODSYB8f6SPRqwdvCM7uQ2dzsjm+DZZwK+hX7MW+ynKA +SR3UBOH9tYA5GYDXl+jTn/oOeTMGa/YjjydtcmT3vmWPWsZ3ipVnnSFnGNBhXHvBGyf tR0i7mRp8W+h3t6j8dCmuz0l30ZKldDV11JTB4MBlJ/yIGGO38c+aGfNkZIDmjjigTh0 cjbQMHHzijLU5jDisAmDVC8sxZB+KcRgFmXnsmCOdhmV08O0H/aQreF1JUFCOWvEvCgH ko6Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=nvoC+buu5tasYx6T8UBAK6LFJaCdJgALnFZc/9QT04M=; b=XBCcIUZ/MHr1/9KoULuboH1nnbdR56zOWJWnViDXGdYFaEt0GzrMSGJh/8guH+2aws eua/cJnPZ2YmAZISMD3WSspjwakDrvlm2IVHBEkmdPG/0myUT5gf5dsO1rOxPXHn/5Z4 O0V72OHBHN3y71AM8zuUZ0p0au2ekjrnZZFAzyG4oGd0WOCGIRKDiBfBVzdnG037hQgY h0NNQmbRnEJ0aNT3eoZBQGHuHjfaaCot8GHrG+Nm9IiWVSx0elr7JSGQpEatQEIGwT9b 3LgL5/Vo+yuFEQoRHpIkYQsaS/Gf6jgZj1e+xOx9YjRKcNnbCuhYy/xQbStjtGAUsu/Y XzIQ== X-Gm-Message-State: AOAM533m/yP2pe9o3k7oOLAGZA+OoT/uZiva4tm+e6ZnLwDLRR/sDf/r WCBcvAX6Lxyh4GWTkbJpS8APLQ== X-Google-Smtp-Source: ABdhPJxxM+lXnY1Pv5jC54SILewDa0FsTTF0olUY17HzRDOMvh8J3mDj/T/HYIIXLvmQ1k48kM7r6w== X-Received: by 2002:a17:906:7c07:: with SMTP id t7mr1626502ejo.487.1594674833855; Mon, 13 Jul 2020 14:13:53 -0700 (PDT) Received: from ls00508.pb.local ([2001:1438:4010:2540:a1ab:24b8:5892:2244]) by smtp.gmail.com with ESMTPSA id d5sm12715770eds.40.2020.07.13.14.13.53 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 13 Jul 2020 14:13:53 -0700 (PDT) From: Guoqing Jiang To: axboe@kernel.dk Cc: linux-block@vger.kernel.org, Guoqing Jiang , Florian-Ewald Mueller Subject: [PATCH RFC V2 1/4] block: add a statistic table for io latency Date: Mon, 13 Jul 2020 23:13:18 +0200 Message-Id: <20200713211321.21123-2-guoqing.jiang@cloud.ionos.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> References: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Usually, we get the status of block device by cat stat file, but we can only know the total time with that file. And we would like to know more accurate statistic, such as each latency range, which helps people to diagnose if there is issue about the hardware. Also a new config option is introduced to control if people want to know the additional statistics or not, and we use the option for io sector in next patch. Signed-off-by: Florian-Ewald Mueller Signed-off-by: Guoqing Jiang --- block/Kconfig | 8 ++++++++ block/blk-core.c | 34 ++++++++++++++++++++++++++++++++++ block/genhd.c | 26 ++++++++++++++++++++++++++ include/linux/part_stat.h | 7 +++++++ 4 files changed, 75 insertions(+) diff --git a/block/Kconfig b/block/Kconfig index bbad5e8bbffe..360f63111e2d 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -176,6 +176,14 @@ config BLK_DEBUG_FS Unless you are building a kernel for a tiny system, you should say Y here. +config BLK_ADDITIONAL_DISKSTAT + bool "Block layer additional diskstat" + default n + help + Enabling this option adds io latency statistics for each block device. + + If unsure, say N. + config BLK_DEBUG_FS_ZONED bool default BLK_DEBUG_FS && BLK_DEV_ZONED diff --git a/block/blk-core.c b/block/blk-core.c index d9d632639bd1..036eb04782de 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1411,6 +1411,34 @@ static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) } } +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT +/* + * Either account additional stat for request if req is not NULL or account for bio. + */ +static void blk_additional_latency(struct hd_struct *part, const int sgrp, + struct request *req, unsigned long start_jiffies) +{ + unsigned int idx; + unsigned long duration, now = READ_ONCE(jiffies); + + if (req) + duration = jiffies_to_nsecs(now) - req->start_time_ns; + else + duration = jiffies_to_nsecs(now - start_jiffies); + + duration /= NSEC_PER_MSEC; + duration /= HZ_TO_MSEC_NUM; + if (likely(duration > 0)) { + idx = ilog2(duration); + if (idx > ADD_STAT_NUM - 1) + idx = ADD_STAT_NUM - 1; + } else + idx = 0; + part_stat_inc(part, latency_table[idx][sgrp]); + +} +#endif + static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { @@ -1440,6 +1468,9 @@ void blk_account_io_done(struct request *req, u64 now) part = req->part; update_io_ticks(part, jiffies, true); +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT + blk_additional_latency(part, sgrp, req, 0); +#endif part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); @@ -1488,6 +1519,9 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op, part_stat_lock(); update_io_ticks(part, now, true); +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT + blk_additional_latency(part, sgrp, NULL, start_time); +#endif part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); diff --git a/block/genhd.c b/block/genhd.c index c42a49f2f537..f5d2f110fb34 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1420,6 +1420,29 @@ static struct device_attribute dev_attr_fail_timeout = __ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store); #endif +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT +static ssize_t io_latency_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + size_t count = 0; + int i, sgrp; + + for (i = 0; i < ADD_STAT_NUM; i++) { + count += scnprintf(buf + count, PAGE_SIZE - count, "%5d ms: ", + (1 << i) * HZ_TO_MSEC_NUM); + for (sgrp = 0; sgrp < NR_STAT_GROUPS; sgrp++) + count += scnprintf(buf + count, PAGE_SIZE - count, "%lu ", + part_stat_read(p, latency_table[i][sgrp])); + count += scnprintf(buf + count, PAGE_SIZE - count, "\n"); + } + + return count; +} + +static struct device_attribute dev_attr_io_latency = + __ATTR(io_latency, 0444, io_latency_show, NULL); +#endif + static struct attribute *disk_attrs[] = { &dev_attr_range.attr, &dev_attr_ext_range.attr, @@ -1438,6 +1461,9 @@ static struct attribute *disk_attrs[] = { #endif #ifdef CONFIG_FAIL_IO_TIMEOUT &dev_attr_fail_timeout.attr, +#endif +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT + &dev_attr_io_latency.attr, #endif NULL }; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 24125778ef3e..fe3def8c69d7 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -9,6 +9,13 @@ struct disk_stats { unsigned long sectors[NR_STAT_GROUPS]; unsigned long ios[NR_STAT_GROUPS]; unsigned long merges[NR_STAT_GROUPS]; +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT +/* + * We measure latency (ms) for 1, 2, ..., 1024 and >=1024. + */ +#define ADD_STAT_NUM 12 + unsigned long latency_table[ADD_STAT_NUM][NR_STAT_GROUPS]; +#endif unsigned long io_ticks; local_t in_flight[2]; }; From patchwork Mon Jul 13 21:13:19 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Guoqing Jiang X-Patchwork-Id: 11661023 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id A49EE722 for ; Mon, 13 Jul 2020 21:13:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8BB932082E for ; Mon, 13 Jul 2020 21:13:57 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=cloud.ionos.com header.i=@cloud.ionos.com header.b="TsUXx9Vk" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726506AbgGMVN5 (ORCPT ); Mon, 13 Jul 2020 17:13:57 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35802 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726400AbgGMVN4 (ORCPT ); Mon, 13 Jul 2020 17:13:56 -0400 Received: from mail-ej1-x643.google.com (mail-ej1-x643.google.com [IPv6:2a00:1450:4864:20::643]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 33769C061755 for ; Mon, 13 Jul 2020 14:13:56 -0700 (PDT) Received: by mail-ej1-x643.google.com with SMTP id y10so19073585eje.1 for ; Mon, 13 Jul 2020 14:13:56 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cloud.ionos.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=a/VznLOsshgoMt5W+c7bCNEFnLgiMUJ304FQKLIA/e4=; b=TsUXx9VkJKt1VECQilTb5T661s6RQMsV9Mw9r4xMyxPiKQAqU125t+LjkavZtLKwih uNhcx/gK2RTHzIaDOE3VjeLV+9nNIsb3+3vf0bjfy04VfY5UnF5Q3IL6EFqFmDZJ5MZz eTmFq5dtHEKies3o2lh1P1counpy5DwGNvtHcMJoPtvujmPsSlYmSCPl5IGJWD0Jb5Xr UBn92s891s4Fdg/3YirwvtW3tL9rpThK7PACtkoKLTvcoMHHGqElqG2+t6qt5Cc6J63f kFS5WwMv3IYLYknCENG6vYhojkIlXjnQUPcXqiipsHp5bVVgFKBaMo1njhHSawnCROG2 DUIg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=a/VznLOsshgoMt5W+c7bCNEFnLgiMUJ304FQKLIA/e4=; b=C2Dx/tkjzIpTZ2caCEqxlz6bR4kiWvAc6upS/QJC67AN9GE50UL89PTqLtqPlTRE+s IZumj+dF65uclT0XqaZrnvQ3/GDckneG5iJfA1gu8DpIwvi2dzRPMwvqju2ZmD0FW0qg EZ7BOO2kg0IMeulxHfn45uNe8ErhFrP+Mxi1k9iU2k40uDoVVpudczzr1mjrvGIQn3IM AmUr9GJrY4c7wPB51IQYLnR8CwVi9E+n4ecWxCl37bENERD/LsqmAAlGBOfZ/m0lUdtu qDr9OdMWIe2WBH5TH183IA+AnCoIOgJ7KLPHxnRktFJ0TGjR4icjceYYTlmO0B41PwwE tTlQ== X-Gm-Message-State: AOAM533vzjV0fNNGONMaf1VyrOAy+NUpGKLYcqFKGyJUu6MxtNnlTVIw QKMj2zM3aGDpmvrC0gZ19U1llA== X-Google-Smtp-Source: ABdhPJxkdlyc07zyQ6n4STS3RogHmpzreiV3pvGXqJ4rYEBGyDgOBIXgxOMmBA4PVKSgD4n6UXrrBA== X-Received: by 2002:a17:907:20ba:: with SMTP id pw26mr1510594ejb.425.1594674834836; Mon, 13 Jul 2020 14:13:54 -0700 (PDT) Received: from ls00508.pb.local ([2001:1438:4010:2540:a1ab:24b8:5892:2244]) by smtp.gmail.com with ESMTPSA id d5sm12715770eds.40.2020.07.13.14.13.53 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 13 Jul 2020 14:13:54 -0700 (PDT) From: Guoqing Jiang To: axboe@kernel.dk Cc: linux-block@vger.kernel.org, Guoqing Jiang , Florian-Ewald Mueller Subject: [PATCH RFC V2 2/4] block: add a statistic table for io sector Date: Mon, 13 Jul 2020 23:13:19 +0200 Message-Id: <20200713211321.21123-3-guoqing.jiang@cloud.ionos.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> References: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org With the sector table, so we can know the distribution of different IO size from upper layer, which means we could have the opportunity to tune the performance based on the mostly issued IOs. Signed-off-by: Florian-Ewald Mueller Signed-off-by: Guoqing Jiang --- block/Kconfig | 3 ++- block/blk-core.c | 16 ++++++++++++++++ block/genhd.c | 21 +++++++++++++++++++++ include/linux/part_stat.h | 3 ++- 4 files changed, 41 insertions(+), 2 deletions(-) diff --git a/block/Kconfig b/block/Kconfig index 360f63111e2d..c9b9f99152d8 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -180,7 +180,8 @@ config BLK_ADDITIONAL_DISKSTAT bool "Block layer additional diskstat" default n help - Enabling this option adds io latency statistics for each block device. + Enabling this option adds io latency and io size statistics for each + block device. If unsure, say N. diff --git a/block/blk-core.c b/block/blk-core.c index 036eb04782de..b67aedfbcefc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1437,6 +1437,16 @@ static void blk_additional_latency(struct hd_struct *part, const int sgrp, part_stat_inc(part, latency_table[idx][sgrp]); } + +static void blk_additional_sector(struct hd_struct *part, const int sgrp, + unsigned int sectors) +{ + unsigned int KB = sectors / 2, idx; + + idx = (KB > 0) ? ilog2(KB) : 0; + idx = (idx > (ADD_STAT_NUM - 1)) ? (ADD_STAT_NUM - 1) : idx; + part_stat_inc(part, size_table[idx][sgrp]); +} #endif static void blk_account_io_completion(struct request *req, unsigned int bytes) @@ -1447,6 +1457,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) part_stat_lock(); part = req->part; +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT + blk_additional_sector(part, sgrp, bytes >> SECTOR_SHIFT); +#endif part_stat_add(part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } @@ -1502,6 +1515,9 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, update_io_ticks(part, now, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); +#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT + blk_additional_sector(part, sgrp, sectors); +#endif part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); diff --git a/block/genhd.c b/block/genhd.c index f5d2f110fb34..cb9394521a8f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1441,6 +1441,26 @@ static ssize_t io_latency_show(struct device *dev, struct device_attribute *attr static struct device_attribute dev_attr_io_latency = __ATTR(io_latency, 0444, io_latency_show, NULL); + +static ssize_t io_size_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + size_t count = 0; + int i, sgrp; + + for (i = 0; i < ADD_STAT_NUM; i++) { + count += scnprintf(buf + count, PAGE_SIZE - count, "%5d KB: ", 1 << i); + for (sgrp = 0; sgrp < NR_STAT_GROUPS; sgrp++) + count += scnprintf(buf + count, PAGE_SIZE - count, "%lu ", + part_stat_read(p, size_table[i][sgrp])); + count += scnprintf(buf + count, PAGE_SIZE - count, "\n"); + } + + return count; +} + +static struct device_attribute dev_attr_io_size = + __ATTR(io_size, 0444, io_size_show, NULL); #endif static struct attribute *disk_attrs[] = { @@ -1464,6 +1484,7 @@ static struct attribute *disk_attrs[] = { #endif #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT &dev_attr_io_latency.attr, + &dev_attr_io_size.attr, #endif NULL }; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index fe3def8c69d7..2b056cd70d1f 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -11,10 +11,11 @@ struct disk_stats { unsigned long merges[NR_STAT_GROUPS]; #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT /* - * We measure latency (ms) for 1, 2, ..., 1024 and >=1024. + * We measure latency (ms) and size (sector) for 1, 2, ..., 1024 and >=1024. */ #define ADD_STAT_NUM 12 unsigned long latency_table[ADD_STAT_NUM][NR_STAT_GROUPS]; + unsigned long size_table[ADD_STAT_NUM][NR_STAT_GROUPS]; #endif unsigned long io_ticks; local_t in_flight[2]; From patchwork Mon Jul 13 21:13:20 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Guoqing Jiang X-Patchwork-Id: 11661025 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 62BC4722 for ; Mon, 13 Jul 2020 21:13:58 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 49F8F2082F for ; Mon, 13 Jul 2020 21:13:58 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=cloud.ionos.com header.i=@cloud.ionos.com header.b="MO5/M9Ys" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726400AbgGMVN5 (ORCPT ); Mon, 13 Jul 2020 17:13:57 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35808 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726325AbgGMVN5 (ORCPT ); Mon, 13 Jul 2020 17:13:57 -0400 Received: from mail-ej1-x643.google.com (mail-ej1-x643.google.com [IPv6:2a00:1450:4864:20::643]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 271B3C061755 for ; Mon, 13 Jul 2020 14:13:57 -0700 (PDT) Received: by mail-ej1-x643.google.com with SMTP id ga4so19034500ejb.11 for ; Mon, 13 Jul 2020 14:13:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cloud.ionos.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=SM540rLfgV/tYozAN91I2JvPbEReIqvVWiYDvaIIHmw=; b=MO5/M9YsMF9s5UbN1r+DMMBRCJmRqda78rR/kqap75ZCO0772TODQcdyy38BSJNt+U GTJaTRN1Ffg/f6JCPLz5q3zhJUi+hNbBja67iBz3Nia5VRJBkqEvoVz29nwaeiEdOEnA 2R0u9Zi4hjzkfwb194dLCNjaEdg+9OaXOKs85utR7J0Y2cM467KK6AnMSHcMoXAboo0b wKOtEEU+5SU5usfgLEdk37emU16CBxRk8pWDv8e2+xsLT23bpmXwlFTPMJab19u9mWJz CE3F/bGioF6ryodrnrux2e+wUcbfmuGeT4i0FmjeNWpLc0GnF5zaov9VEgbBtftLRtYj 7S3g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=SM540rLfgV/tYozAN91I2JvPbEReIqvVWiYDvaIIHmw=; b=RJDEjz2iQzZK0C00r0+6v7ymd7U4VEUcIVqSY70Ih0x2QOALjUYCJ8N4A7fhCbCeqk KZ8eVlwRHz784CN2z0Oh2zS2q/lxjRe3J5Nz+0r3fBTCxdG5ydsEIBo5g8KzxAn1NRbw yyGOo12AY+XUJmZgW2sJLJmWp4M7lq/aCguHfzmK3ASvj1TbJs+s3IiOM8PvhwX3VHDy eWFm+hhRoB7qlOrf8gzrT4qvmiEIhnCGXdGwMcegAtz5F6eAIVPgQvLjSzXyv22KHRWK WrIPvNPqpUatPyBvwHsjE4N11ZimQGSgBaCMQp6e3jyY5lmiQmjWDMssN8MoM6KcDBEV 0yoA== X-Gm-Message-State: AOAM532Mnq6/whPPh9h1HyhHrq7yTiBIDZ4a5AH2ECzvqjSTwb6XBfcg kgwjMZh0tlzh4E9y6uXTsNj+7Q== X-Google-Smtp-Source: ABdhPJz2zxaxOeCUof/2E4cEGINfMzYgbWqbzympMWIkmCITcaTzN5s48NaX/cLGZ5KezPwm6mAKog== X-Received: by 2002:a17:906:e25a:: with SMTP id gq26mr1592704ejb.152.1594674835798; Mon, 13 Jul 2020 14:13:55 -0700 (PDT) Received: from ls00508.pb.local ([2001:1438:4010:2540:a1ab:24b8:5892:2244]) by smtp.gmail.com with ESMTPSA id d5sm12715770eds.40.2020.07.13.14.13.54 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 13 Jul 2020 14:13:55 -0700 (PDT) From: Guoqing Jiang To: axboe@kernel.dk Cc: linux-block@vger.kernel.org, Guoqing Jiang Subject: [PATCH RFC V2 3/4] block: add io_extra_stats node Date: Mon, 13 Jul 2020 23:13:20 +0200 Message-Id: <20200713211321.21123-4-guoqing.jiang@cloud.ionos.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> References: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Even we have introduced a Kconfig option (default N) to control the accounting of additional data, but the option still could be enabled occasionally while user doesn't care about the size and latency of io, and they could suffer from the additional overhead. So introduce a specific sysfs node to avoid such mistake. Signed-off-by: Guoqing Jiang --- Documentation/block/queue-sysfs.rst | 6 ++++++ block/blk-sysfs.c | 8 ++++++++ include/linux/blkdev.h | 2 ++ 3 files changed, 16 insertions(+) diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst index 6a8513af9201..e7b5e0d77385 100644 --- a/Documentation/block/queue-sysfs.rst +++ b/Documentation/block/queue-sysfs.rst @@ -99,6 +99,12 @@ iostats (RW) This file is used to control (on/off) the iostats accounting of the disk. +io_extra_stats (RW) +------------------- +This file is used to control (on/off) the additional accounting of the +io size and io latency of disk, and BLK_ADDITIONAL_DISKSTAT should be +enabled if you want the additional accounting. + logical_block_size (RO) ----------------------- This is the logical block size of the device, in bytes. diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index be67952e7be2..98bd788e32c3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -287,6 +287,7 @@ queue_store_##name(struct request_queue *q, const char *page, size_t count) \ QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1); QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0); QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0); +QUEUE_SYSFS_BIT_FNS(io_extra_stats, IO_EXTRA_STAT, 0); #undef QUEUE_SYSFS_BIT_FNS static ssize_t queue_zoned_show(struct request_queue *q, char *page) @@ -686,6 +687,12 @@ static struct queue_sysfs_entry queue_iostats_entry = { .store = queue_store_iostats, }; +static struct queue_sysfs_entry queue_io_extra_stats_entry = { + .attr = {.name = "io_extra_stats", .mode = 0644 }, + .show = queue_show_io_extra_stats, + .store = queue_store_io_extra_stats, +}; + static struct queue_sysfs_entry queue_random_entry = { .attr = {.name = "add_random", .mode = 0644 }, .show = queue_show_random, @@ -777,6 +784,7 @@ static struct attribute *queue_attrs[] = { &queue_wb_lat_entry.attr, &queue_poll_delay_entry.attr, &queue_io_timeout_entry.attr, + &queue_io_extra_stats_entry.attr, #ifdef CONFIG_BLK_DEV_THROTTLING_LOW &throtl_sample_time_entry.attr, #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 69ad13dacd48..640190678bbc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -610,6 +610,7 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ +#define QUEUE_FLAG_IO_EXTRA_STAT 28 /* extra IO accounting for latency and size */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) @@ -652,6 +653,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) +#define blk_queue_extra_io_stat(q) test_bit(QUEUE_FLAG_IO_EXTRA_STAT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); From patchwork Mon Jul 13 21:13:21 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Guoqing Jiang X-Patchwork-Id: 11661027 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 28036618 for ; Mon, 13 Jul 2020 21:13:59 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 104FF2082F for ; Mon, 13 Jul 2020 21:13:59 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=cloud.ionos.com header.i=@cloud.ionos.com header.b="KelQ9BQt" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726514AbgGMVN6 (ORCPT ); Mon, 13 Jul 2020 17:13:58 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35812 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726325AbgGMVN6 (ORCPT ); Mon, 13 Jul 2020 17:13:58 -0400 Received: from mail-ej1-x641.google.com (mail-ej1-x641.google.com [IPv6:2a00:1450:4864:20::641]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C2E9BC061755 for ; Mon, 13 Jul 2020 14:13:57 -0700 (PDT) Received: by mail-ej1-x641.google.com with SMTP id y10so19073667eje.1 for ; Mon, 13 Jul 2020 14:13:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cloud.ionos.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=wJMcJABSB/bCBpwMur78CQyT/owz2aaF5PWtEB9Jy/E=; b=KelQ9BQts1V2yhZzjuoSfy9mCLYfZtbGEavD0oO3ekJLWW+4hfYIu5OrdHBmQni+cL DWpQ9GIVNJ/j5Fk+iLvaq+/fcCNy3Wie0CNYWWubvMjC6trtIXJ1+lyT79t4Uibwyatq vkv4k7hmkKXIyjq7krAZRVtnJAs9aQ0UpjeaVI8lsvAR8ityfem1AU4eCxLjtd6B94uu 1gpIxsDrtqS+vBbd1WKUGVvMISlwce0yE4bc7sR9AOMUw0s7LIS6X8JePWx116zTdFJa amLtrM0yi2adeY2WIkEN+4mDr8HtrH37w9dVb1J11dVJxeRSHDkzxxx4hIGsxAwX/mfd RwcQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=wJMcJABSB/bCBpwMur78CQyT/owz2aaF5PWtEB9Jy/E=; b=UsUR4AkxqMV46xNKmYJYBAr5Q+bddbvtO5/a+mQyJuyRwPePt3Yer1cZKTYbcWagmi h4z0YEMceHFXVoucB5C/e8oZ6DENsuwy2OrBQw41zScm/M1KRI7Jj217piX6buQR4rUw x1gKXckRSe5fb25/Q8efSXXvqgVEdI9FdfyDJCuo8C6I8YYsvg56IE+Oy8ilU7B/G6Nq O0ypfejAe7vGr5YDEJ/16rqEp66xhFsID3IowpnF9+bTynZHlwKQiuJiiu3b1qYI7UPX x4ygMV1TwxWexsJvuVMJPTn6FuRifVZMAtnenBpCEL8BY/5Pd5povJyQmrR8PkH9yVav sQXA== X-Gm-Message-State: AOAM533djDkJuv+9Mgchhbhewt/OR/l9NIV4pkdj4P1uyyVJb/g+6TaV GjeSyA2nK2gszQ3U5RTQ4VzL/Q== X-Google-Smtp-Source: ABdhPJySb9EyALbUVk4lMtN3lDF0dPtJ9EMxIr67gF6NR7n2N1g7t2ihMIf7t4S+qidOVWy9M+v+ZA== X-Received: by 2002:a17:906:8688:: with SMTP id g8mr1511529ejx.505.1594674836490; Mon, 13 Jul 2020 14:13:56 -0700 (PDT) Received: from ls00508.pb.local ([2001:1438:4010:2540:a1ab:24b8:5892:2244]) by smtp.gmail.com with ESMTPSA id d5sm12715770eds.40.2020.07.13.14.13.55 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 13 Jul 2020 14:13:56 -0700 (PDT) From: Guoqing Jiang To: axboe@kernel.dk Cc: linux-block@vger.kernel.org, Guoqing Jiang Subject: [PATCH RFC V2 4/4] block: call blk_additional_{latency,sector} only when io_extra_stats is true Date: Mon, 13 Jul 2020 23:13:21 +0200 Message-Id: <20200713211321.21123-5-guoqing.jiang@cloud.ionos.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> References: <20200713211321.21123-1-guoqing.jiang@cloud.ionos.com> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org If ADDITIONAL_DISKSTAT is enabled carelessly, then it is bad to people who don't want the additional overhead. Now add check before call blk_additional_{latency,sector}, which guarntee only those who really know about the attribute can account the additional data. Signed-off-by: Guoqing Jiang --- block/blk-core.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index b67aedfbcefc..171e99ed820b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1458,7 +1458,8 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) part_stat_lock(); part = req->part; #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT - blk_additional_sector(part, sgrp, bytes >> SECTOR_SHIFT); + if (blk_queue_extra_io_stat(req->q)) + blk_additional_sector(part, sgrp, bytes >> SECTOR_SHIFT); #endif part_stat_add(part, sectors[sgrp], bytes >> 9); part_stat_unlock(); @@ -1482,7 +1483,8 @@ void blk_account_io_done(struct request *req, u64 now) update_io_ticks(part, jiffies, true); #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT - blk_additional_latency(part, sgrp, req, 0); + if (blk_queue_extra_io_stat(req->q)) + blk_additional_latency(part, sgrp, req, 0); #endif part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); @@ -1516,7 +1518,8 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT - blk_additional_sector(part, sgrp, sectors); + if (blk_queue_extra_io_stat(disk->queue)) + blk_additional_sector(part, sgrp, sectors); #endif part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -1536,7 +1539,8 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op, part_stat_lock(); update_io_ticks(part, now, true); #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT - blk_additional_latency(part, sgrp, NULL, start_time); + if (blk_queue_extra_io_stat(disk->queue)) + blk_additional_latency(part, sgrp, NULL, start_time); #endif part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(part, in_flight[op_is_write(op)]);