From patchwork Tue Jun 6 19:40:43 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shaohua Li X-Patchwork-Id: 9769907 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id F011860353 for ; Tue, 6 Jun 2017 19:41:28 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id DDD2528397 for ; Tue, 6 Jun 2017 19:41:28 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id CFB88284DA; Tue, 6 Jun 2017 19:41:28 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 6C20427C05 for ; Tue, 6 Jun 2017 19:41:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751462AbdFFTlP (ORCPT ); Tue, 6 Jun 2017 15:41:15 -0400 Received: from mail.kernel.org ([198.145.29.99]:46814 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751458AbdFFTkr (ORCPT ); Tue, 6 Jun 2017 15:40:47 -0400 Received: from shli-virt.localdomain (unknown [199.201.64.130]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 5640623A02; Tue, 6 Jun 2017 19:40:46 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 5640623A02 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=fail smtp.mailfrom=shli@fb.com From: Shaohua Li To: linux-block@vger.kernel.org Cc: tj@kernel.org, axboe@fb.com, Kernel-team@fb.com, Shaohua Li Subject: [PATCH] blk-throttle: set default latency baseline for harddisk Date: Tue, 6 Jun 2017 12:40:43 -0700 Message-Id: X-Mailer: git-send-email 2.11.0 Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Shaohua Li hard disk IO latency varies a lot depending on spindle move. The latency range could be from several microseconds to several milliseconds. It's pretty hard to get the baseline latency used by io.low. We will use a different stragety here. The idea is only using IO with spindle move to determine if cgroup IO is in good state. For HD, if io latency is small (< 1ms), we ignore the IO. Such IO is likely from sequential IO, and is helpless to help determine if a cgroup's IO is impacted by other cgroups. With this, we only account IO with big latency. Then we can choose a hardcoded baseline latency for HD (4ms, which is typical IO latency with seek). With all these settings, the io.low latency works for both HD and SSD. Signed-off-by: Shaohua Li --- block/blk-throttle.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index fc13dd0..fb6a0bf 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -27,6 +27,13 @@ static int throtl_quantum = 32; #define MIN_THROTL_IOPS (10) #define DFL_LATENCY_TARGET (-1L) #define DFL_IDLE_THRESHOLD (0) +#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */ +#define LATENCY_FILTERED_SSD (0) +/* + * For HD, very small latency comes from sequential IO. Such IO is helpless to + * help determine if its IO is impacted by others, hence we ignore the IO + */ +#define LATENCY_FILTERED_HD (1000L) /* 1ms */ #define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT) @@ -212,6 +219,7 @@ struct throtl_data struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE]; struct latency_bucket __percpu *latency_buckets; unsigned long last_calculate_time; + unsigned long filtered_latency; bool track_bio_latency; }; @@ -2281,7 +2289,7 @@ void blk_throtl_bio_endio(struct bio *bio) throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat), bio_op(bio), lat); - if (tg->latency_target) { + if (tg->latency_target && lat >= tg->td->filtered_latency) { int bucket; unsigned int threshold; @@ -2417,14 +2425,20 @@ void blk_throtl_exit(struct request_queue *q) void blk_throtl_register_queue(struct request_queue *q) { struct throtl_data *td; + int i; td = q->td; BUG_ON(!td); - if (blk_queue_nonrot(q)) + if (blk_queue_nonrot(q)) { td->throtl_slice = DFL_THROTL_SLICE_SSD; - else + td->filtered_latency = LATENCY_FILTERED_SSD; + } else { td->throtl_slice = DFL_THROTL_SLICE_HD; + td->filtered_latency = LATENCY_FILTERED_HD; + for (i = 0; i < LATENCY_BUCKET_SIZE; i++) + td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY; + } #ifndef CONFIG_BLK_DEV_THROTTLING_LOW /* if no low limit, use previous default */ td->throtl_slice = DFL_THROTL_SLICE_HD;