From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=DKIM_SIGNED,DKIM_VALID, DKIM_VALID_AU,MAILING_LIST_MULTI,SPF_PASS,T_DKIMWL_WL_HIGH,USER_AGENT_MUTT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 45EDFC3279B for ; Fri, 6 Jul 2018 23:23:51 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id F037A224E8 for ; Fri, 6 Jul 2018 23:23:50 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=kernel.org header.i=@kernel.org header.b="XbFMdZmu" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org F037A224E8 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933146AbeGFXXr (ORCPT ); Fri, 6 Jul 2018 19:23:47 -0400 Received: from mail.kernel.org ([198.145.29.99]:60108 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932478AbeGFXXq (ORCPT ); Fri, 6 Jul 2018 19:23:46 -0400 Received: from localhost (unknown [104.132.1.88]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id F0D95224B2; Fri, 6 Jul 2018 23:23:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1530919426; bh=rlkGh3YWAC+h0j6uU8f93iEfNkqyLIrIKloVJja7yhA=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=XbFMdZmul7z8wZUCiZC33NP8/5S8cRdcxh1oW1vwk89IAsZfy1GIIXA/o9KpH+Q8E iiMPY0nL5m7OepTcxniy6UExFF2t/Y4jzDGfg87fX5RSjIPA0HCcvWZ9DytHppjC00 U0AOHGeAwoVMGl5BTqmiQ29PrZO7R8o9q4JqngZg= Date: Fri, 6 Jul 2018 16:23:45 -0700 From: Jaegeuk Kim To: Chao Yu Cc: linux-f2fs-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org, chao@kernel.org Subject: Re: [PATCH 2/2] f2fs: issue small discard by LBA order Message-ID: <20180706232345.GE77984@jaegeuk-macbookpro.roam.corp.google.com> References: <20180705113701.3466-1-yuchao0@huawei.com> <20180705113701.3466-2-yuchao0@huawei.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20180705113701.3466-2-yuchao0@huawei.com> User-Agent: Mutt/1.8.2 (2017-04-18) Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 07/05, Chao Yu wrote: > For small granularity discard which size is smaller than 64KB, if we > issue those kind of discards orderly by size, their IOs will be spread > into entire logical address, so that in FTL, L2P table will be updated > randomly, result bad wear rate in the table. > > In this patch, we choose to issue small discard by LBA order, by this > way, we can expect that L2P table updates from adjacent discard IOs can > be merged in the cache, so it can reduce lifetime wearing of flash. > > Signed-off-by: Chao Yu > --- > fs/f2fs/f2fs.h | 2 ++ > fs/f2fs/segment.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 73 insertions(+) > > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h > index 47ac0a9b022f..8d592029328a 100644 > --- a/fs/f2fs/f2fs.h > +++ b/fs/f2fs/f2fs.h > @@ -290,6 +290,7 @@ struct discard_policy { > unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */ > bool io_aware; /* issue discard in idle time */ > bool sync; /* submit discard with REQ_SYNC flag */ > + bool ordered; /* issue discard by lba order */ > unsigned int granularity; /* discard granularity */ > }; > > @@ -306,6 +307,7 @@ struct discard_cmd_control { > unsigned int max_discards; /* max. discards to be issued */ > unsigned int discard_granularity; /* discard granularity */ > unsigned int undiscard_blks; /* # of undiscard blocks */ > + unsigned int next_pos; /* next discard position */ > atomic_t issued_discard; /* # of issued discard */ > atomic_t issing_discard; /* # of issing discard */ > atomic_t discard_cmd_cnt; /* # of cached cmd count */ > diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c > index f95bf618bc1e..df0d91dfb8ac 100644 > --- a/fs/f2fs/segment.c > +++ b/fs/f2fs/segment.c > @@ -18,6 +18,7 @@ > #include > #include > #include > +#include Why? > > #include "f2fs.h" > #include "segment.h" > @@ -936,6 +937,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, > /* common policy */ > dpolicy->type = discard_type; > dpolicy->sync = true; > + dpolicy->ordered = false; > dpolicy->granularity = granularity; > > dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; > @@ -947,6 +949,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, > dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; > dpolicy->io_aware = true; > dpolicy->sync = false; > + dpolicy->ordered = true; > if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) { > dpolicy->granularity = 1; > dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME; > @@ -1202,6 +1205,69 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, > return 0; > } > > +static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, > + struct discard_policy *dpolicy) > +{ > + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; > + struct discard_cmd *prev_dc = NULL, *next_dc = NULL; > + struct rb_node **insert_p = NULL, *insert_parent = NULL; > + struct discard_cmd *dc; > + struct blk_plug plug; > + unsigned int pos = dcc->next_pos; > + unsigned int issued = 0, iter = 0; > + bool io_interrupted; > + > + mutex_lock(&dcc->cmd_lock); > + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, > + NULL, pos, > + (struct rb_entry **)&prev_dc, > + (struct rb_entry **)&next_dc, > + &insert_p, &insert_parent, true); > + if (!dc) > + dc = next_dc; > + > + blk_start_plug(&plug); > + > + while (dc) { > + struct rb_node *node; > + > + if (dc->state != D_PREP) > + goto next; > +retry: > + io_interrupted = false; > + > + if (dpolicy->io_aware && !is_idle(sbi)) { > + io_interrupted = true; > + goto skip; Please don't try, if user is doing something. > + } > + > + __submit_discard_cmd(sbi, dpolicy, dc); > + issued++; > + dcc->next_pos = dc->lstart + dc->len; > +skip: > + if (++iter >= dpolicy->max_requests) > + break; > + > + if (io_interrupted) > + goto retry; > +next: > + node = rb_next(&dc->rb_node); > + dc = rb_entry_safe(node, struct discard_cmd, rb_node); > + } > + > + blk_finish_plug(&plug); > + > + if (!dc) > + dcc->next_pos = 0; > + > + mutex_unlock(&dcc->cmd_lock); > + > + if (!issued && io_interrupted) > + issued = -1; > + > + return issued; > +} > + > static int __issue_discard_cmd(struct f2fs_sb_info *sbi, > struct discard_policy *dpolicy) > { > @@ -1215,6 +1281,10 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, > for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { > if (i + 1 < dpolicy->granularity) > break; > + > + if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) > + return __issue_discard_cmd_orderly(sbi, dpolicy); So, at this moment, we usually expect there'd be a bunch of small candidates only, and thus, it'd be better to issue small chunks in LBA order? > + > pend_list = &dcc->pend_list[i]; > > mutex_lock(&dcc->cmd_lock); > @@ -1786,6 +1856,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) > dcc->nr_discards = 0; > dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg; > dcc->undiscard_blks = 0; > + dcc->next_pos = 0; > dcc->root = RB_ROOT; > dcc->rbtree_check = false; > > -- > 2.18.0.rc1