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=-8.8 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED, USER_AGENT_GIT 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 DE8A9C67863 for ; Wed, 24 Oct 2018 10:37:43 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id A5EBE20824 for ; Wed, 24 Oct 2018 10:37:43 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org A5EBE20824 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=huawei.com 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 S1727367AbeJXTFP (ORCPT ); Wed, 24 Oct 2018 15:05:15 -0400 Received: from szxga05-in.huawei.com ([45.249.212.191]:13687 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726428AbeJXTFO (ORCPT ); Wed, 24 Oct 2018 15:05:14 -0400 Received: from DGGEMS406-HUB.china.huawei.com (unknown [172.30.72.59]) by Forcepoint Email with ESMTP id 8B7C864DF7A58; Wed, 24 Oct 2018 18:37:38 +0800 (CST) Received: from szvp000201624.huawei.com (10.120.216.130) by DGGEMS406-HUB.china.huawei.com (10.3.19.206) with Microsoft SMTP Server id 14.3.408.0; Wed, 24 Oct 2018 18:37:32 +0800 From: Chao Yu To: CC: , , , Chao Yu Subject: [PATCH 2/3] f2fs: support subsectional garbage collection Date: Wed, 24 Oct 2018 18:37:27 +0800 Message-ID: <20181024103728.9870-2-yuchao0@huawei.com> X-Mailer: git-send-email 2.18.0.rc1 In-Reply-To: <20181024103728.9870-1-yuchao0@huawei.com> References: <20181024103728.9870-1-yuchao0@huawei.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.120.216.130] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Section is minimal garbage collection unit of f2fs, in zoned block device, or ancient block mapping flash device, in order to improve GC efficiency, we can align GC unit to lower device erase unit, normally, it consists of multiple of segments. Once background or foreground GC triggers, it brings a large number of IOs, which will impact user IO, and also occupy cpu/memory resource intensively. So, to reduce impact of GC on large size section, this patch supports subsectional GC, in one cycle of GC, it only migrate partial segment{s} in victim section. Currently, by default, we use sbi->segs_per_sec as migration granularity. Signed-off-by: Chao Yu --- fs/f2fs/f2fs.h | 3 +++ fs/f2fs/gc.c | 43 ++++++++++++++++++++++++++++++++++++------- fs/f2fs/super.c | 3 +++ 3 files changed, 42 insertions(+), 7 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e57e7874d162..b9cec3f2184c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1266,6 +1266,7 @@ struct f2fs_sb_info { struct f2fs_gc_kthread *gc_thread; /* GC thread */ unsigned int cur_victim_sec; /* current victim section num */ unsigned int gc_mode; /* current GC state */ + unsigned int next_victim_seg[2]; /* next segment in victim section */ /* for skip statistic */ unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */ unsigned long long skipped_gc_rwsem; /* FG_GC only */ @@ -1275,6 +1276,8 @@ struct f2fs_sb_info { /* maximum # of trials to find a victim segment for SSR and GC */ unsigned int max_victim_search; + /* migration granularity of garbage collection, unit: segment */ + unsigned int migration_granularity; /* * for stat information. diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 34b9d56f5f9e..d5d8c433178b 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -333,6 +333,22 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (p.max_search == 0) goto out; + if (__is_large_section(sbi) && p.alloc_mode == LFS) { + if (sbi->next_victim_seg[BG_GC] != NULL_SEGNO) { + p.min_segno = sbi->next_victim_seg[BG_GC]; + *result = p.min_segno; + sbi->next_victim_seg[BG_GC] = NULL_SEGNO; + goto got_result; + } + if (gc_type == FG_GC && + sbi->next_victim_seg[FG_GC] != NULL_SEGNO) { + p.min_segno = sbi->next_victim_seg[FG_GC]; + *result = p.min_segno; + sbi->next_victim_seg[FG_GC] = NULL_SEGNO; + goto got_result; + } + } + last_victim = sm->last_victim[p.gc_mode]; if (p.alloc_mode == LFS && gc_type == FG_GC) { p.min_segno = check_bg_victims(sbi); @@ -395,6 +411,8 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, } if (p.min_segno != NULL_SEGNO) { got_it: + *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; +got_result: if (p.alloc_mode == LFS) { secno = GET_SEC_FROM_SEG(sbi, p.min_segno); if (gc_type == FG_GC) @@ -402,7 +420,6 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, else set_bit(secno, dirty_i->victim_secmap); } - *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; trace_f2fs_get_victim(sbi->sb, type, gc_type, &p, sbi->cur_victim_sec, @@ -1093,15 +1110,18 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, struct blk_plug plug; unsigned int segno = start_segno; unsigned int end_segno = start_segno + sbi->segs_per_sec; - int seg_freed = 0; + int seg_freed = 0, migrated = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; int submitted = 0; + if (__is_large_section(sbi)) + end_segno = rounddown(end_segno, sbi->segs_per_sec); + /* readahead multi ssa blocks those have contiguous address */ if (__is_large_section(sbi)) f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), - sbi->segs_per_sec, META_SSA, true); + end_segno - segno, META_SSA, true); /* reference all summary page */ while (segno < end_segno) { @@ -1130,18 +1150,23 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, GET_SUM_BLOCK(sbi, segno)); f2fs_put_page(sum_page, 0); - if (get_valid_blocks(sbi, segno, false) == 0 || - !PageUptodate(sum_page) || - unlikely(f2fs_cp_error(sbi))) + if (get_valid_blocks(sbi, segno, false) == 0) goto next; + if (__is_large_section(sbi) && + migrated >= sbi->migration_granularity) + goto skip; + + if (!PageUptodate(sum_page) || unlikely(f2fs_cp_error(sbi))) + goto skip; + sum = page_address(sum_page); if (type != GET_SUM_TYPE((&sum->footer))) { f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent segment (%u) " "type [%d, %d] in SSA and SIT", segno, type, GET_SUM_TYPE((&sum->footer))); set_sbi_flag(sbi, SBI_NEED_FSCK); - goto next; + goto skip; } /* @@ -1163,7 +1188,11 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, if (gc_type == FG_GC && get_valid_blocks(sbi, segno, false) == 0) seg_freed++; + migrated++; next: + if (__is_large_section(sbi) && segno + 1 < end_segno) + sbi->next_victim_seg[gc_type] = segno + 1; +skip: f2fs_put_page(sum_page, 0); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 5b297f3b55e4..c85e3a17aaa0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2692,7 +2692,10 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->node_ino_num = le32_to_cpu(raw_super->node_ino); sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino); sbi->cur_victim_sec = NULL_SECNO; + sbi->next_victim_seg[BG_GC] = NULL_SEGNO; + sbi->next_victim_seg[FG_GC] = NULL_SEGNO; sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; + sbi->migration_granularity = sbi->segs_per_sec; sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; -- 2.18.0.rc1