From patchwork Tue Aug 2 14:04:07 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yu Kuai X-Patchwork-Id: 12934677 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6A5F7C3F6B0 for ; Tue, 2 Aug 2022 13:52:44 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S236965AbiHBNwm (ORCPT ); Tue, 2 Aug 2022 09:52:42 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50132 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S236730AbiHBNwe (ORCPT ); Tue, 2 Aug 2022 09:52:34 -0400 Received: from dggsgout12.his.huawei.com (unknown [45.249.212.56]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AAB0525C61; Tue, 2 Aug 2022 06:52:24 -0700 (PDT) Received: from mail02.huawei.com (unknown [172.30.67.153]) by dggsgout12.his.huawei.com (SkyGuard) with ESMTP id 4LxxGd3rLJz6R5Mt; Tue, 2 Aug 2022 21:51:05 +0800 (CST) Received: from huaweicloud.com (unknown [10.175.127.227]) by APP3 (Coremail) with SMTP id _Ch0CgDXLsMQLOlivtl0AA--.20757S5; Tue, 02 Aug 2022 21:52:21 +0800 (CST) From: Yu Kuai To: tj@kernel.org, mkoutny@suse.com, axboe@kernel.dk, ming.lei@redhat.com Cc: cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, yukuai3@huawei.com, yukuai1@huaweicloud.com, yi.zhang@huawei.com Subject: [PATCH v7 1/9] blk-throttle: fix that io throttle can only work for single bio Date: Tue, 2 Aug 2022 22:04:07 +0800 Message-Id: <20220802140415.2960284-2-yukuai1@huaweicloud.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20220802140415.2960284-1-yukuai1@huaweicloud.com> References: <20220802140415.2960284-1-yukuai1@huaweicloud.com> MIME-Version: 1.0 X-CM-TRANSID: _Ch0CgDXLsMQLOlivtl0AA--.20757S5 X-Coremail-Antispam: 1UD129KBjvJXoWxXF45Ww1DJw1UCF1kZry8uFg_yoW5Kw47pF WxGFZ8Wr4kWrsrtrs8JF1IvFWrt3yrAr98Gay3Ga13Ars0grn0grn7urWF93y3uF9xuayv vrn2gr97Ca1UGrJanT9S1TB71UUUUUUqnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUBE14x267AKxVW5JVWrJwAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_Jr4l82xGYIkIc2 x26xkF7I0E14v26r1I6r4UM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8wA2z4x0 Y4vE2Ix0cI8IcVAFwI0_tr0E3s1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j6F4UJw A2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oVCq3wAS 0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0I7IYx2 IY67AKxVWUJVWUGwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r4UM4x0 Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwACI402YVCY1x02628vn2kIc2 xKxwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7xkEbVWUJVW8JwC20s026c02F40E14v2 6r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E67AF67kF1VAFwI0_Jw0_GFylIxkGc2 Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWUJVWUCwCI42IY6xIIjxv20xvEc7CjxVAFwI0_ Gr0_Cr1lIxAIcVCF04k26cxKx2IYs7xG6r1j6r1xMIIF0xvEx4A2jsIE14v26r1j6r4UMI IF0xvEx4A2jsIEc7CjxVAFwI0_Gr0_Gr1UYxBIdaVFxhVjvjDU0xZFpf9x0JUqAp5UUUUU = X-CM-SenderInfo: 51xn3trlr6x35dzhxuhorxvhhfrp/ X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org From: Yu Kuai Test scripts: cd /sys/fs/cgroup/blkio/ echo "8:0 1024" > blkio.throttle.write_bps_device echo $$ > cgroup.procs dd if=/dev/zero of=/dev/sda bs=10k count=1 oflag=direct & dd if=/dev/zero of=/dev/sda bs=10k count=1 oflag=direct & Test result: 10240 bytes (10 kB, 10 KiB) copied, 10.0134 s, 1.0 kB/s 10240 bytes (10 kB, 10 KiB) copied, 10.0135 s, 1.0 kB/s The problem is that the second bio is finished after 10s instead of 20s. Root cause: 1) second bio will be flaged: __blk_throtl_bio while (true) { ... if (sq->nr_queued[rw]) -> some bio is throttled already break }; bio_set_flag(bio, BIO_THROTTLED); -> flag the bio 2) flaged bio will be dispatched without waiting: throtl_dispatch_tg tg_may_dispatch tg_with_in_bps_limit if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) *wait = 0; -> wait time is zero return true; commit 9f5ede3c01f9 ("block: throttle split bio in case of iops limit") support to count splited bios for iops limit, thus it adds flaged bio checking in tg_with_in_bps_limit() so that splited bios will only count once for bps limit, however, it introduce a new problem that io throttle won't work if multiple bios are throttled. In order to fix the problem, at first, don't skip flaged bio in tg_with_in_bps_limit(), however, this will break that splited bios should only count once for bps limit. And this patch tries to avoid over-accounting by decrementing it first in __blk_throtl_bio(), and then counting it again while dispatching it. Fixes: 9f5ede3c01f9 ("block: throttle split bio in case of iops limit") Signed-off-by: Yu Kuai Reviewed-by: Ming Lei --- block/blk-throttle.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 9f5fe62afff9..2957e2c643f4 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -811,7 +811,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, unsigned int bio_size = throtl_bio_data_size(bio); /* no need to throttle if this bio's bytes have been accounted */ - if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) { + if (bps_limit == U64_MAX) { if (wait) *wait = 0; return true; @@ -921,11 +921,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) unsigned int bio_size = throtl_bio_data_size(bio); /* Charge the bio to the group */ - if (!bio_flagged(bio, BIO_THROTTLED)) { - tg->bytes_disp[rw] += bio_size; - tg->last_bytes_disp[rw] += bio_size; - } - + tg->bytes_disp[rw] += bio_size; + tg->last_bytes_disp[rw] += bio_size; tg->io_disp[rw]++; tg->last_io_disp[rw]++; @@ -2121,6 +2118,23 @@ bool __blk_throtl_bio(struct bio *bio) tg->last_low_overflow_time[rw] = jiffies; throtl_downgrade_check(tg); throtl_upgrade_check(tg); + + /* + * Splited bios can be re-entered because iops limit should be + * counted again, however, bps limit should not. Since bps limit + * will be counted again while dispatching it, compensate the + * over-accounting here. Noted that compensation can fail if + * new slice is started. + */ + if (bio_flagged(bio, BIO_THROTTLED)) { + unsigned int bio_size = throtl_bio_data_size(bio); + + if (tg->bytes_disp[rw] >= bio_size) + tg->bytes_disp[rw] -= bio_size; + if (tg->last_bytes_disp[rw] >= bio_size) + tg->last_bytes_disp[rw] -= bio_size; + } + /* throtl is FIFO - if bios are already queued, should queue */ if (sq->nr_queued[rw]) break;