[09/10] xfs_scrub: use scrub barriers to reduce kernel calls

Message ID	172229852474.1353240.7183452625768502480.stgit@frogsfrogsfrogs (mailing list archive)
State	Accepted, archived
Headers	show Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B4262BA38 for <linux-xfs@vger.kernel.org>; Tue, 30 Jul 2024 01:32:25 +0000 (UTC) Date: Mon, 29 Jul 2024 18:32:24 -0700 Subject: [PATCH 09/10] xfs_scrub: use scrub barriers to reduce kernel calls From: "Darrick J. Wong" <djwong@kernel.org> To: djwong@kernel.org, cem@kernel.org Cc: Christoph Hellwig <hch@lst.de>, linux-xfs@vger.kernel.org Message-ID: <172229852474.1353240.7183452625768502480.stgit@frogsfrogsfrogs> In-Reply-To: <172229852355.1353240.6151017907178495656.stgit@frogsfrogsfrogs> References: <172229852355.1353240.6151017907178495656.stgit@frogsfrogsfrogs> User-Agent: StGit/0.19 Precedence: bulk MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit
Series	[01/10] man: document vectored scrub mode \| expand [01/10] man: document vectored scrub mode [02/10] libfrog: support vectored scrub [03/10] xfs_io: support vectored scrub [04/10] xfs_scrub: split the scrub epilogue code into a separate function [05/10] xfs_scrub: split the repair epilogue code into a separate function [06/10] xfs_scrub: convert scrub and repair epilogues to use xfs_scrub_vec [07/10] xfs_scrub: vectorize scrub calls [08/10] xfs_scrub: vectorize repair calls [09/10] xfs_scrub: use scrub barriers to reduce kernel calls [10/10] xfs_scrub: try spot repairs of metadata items to make scrub progress

diff --git a/scrub/phase2.c b/scrub/phase2.c index 57c6d0ef2..d435da071 100644 --- a/scrub/phase2.c +++ b/scrub/phase2.c @@ -91,21 +91,12 @@ scan_ag_metadata( snprintf(descr, DESCR_BUFSZ, _("AG %u"), agno); /* - * First we scrub and fix the AG headers, because we need - * them to work well enough to check the AG btrees. + * First we scrub and fix the AG headers, because we need them to work + * well enough to check the AG btrees. Then scrub the AG btrees. */ scrub_item_schedule_group(&sri, XFROG_SCRUB_GROUP_AGHEADER); - ret = scrub_item_check(ctx, &sri); - if (ret) - goto err; - - /* Repair header damage. */ - ret = repair_item_corruption(ctx, &sri); - if (ret) - goto err; - - /* Now scrub the AG btrees. */ scrub_item_schedule_group(&sri, XFROG_SCRUB_GROUP_PERAG); + ret = scrub_item_check(ctx, &sri); if (ret) goto err; diff --git a/scrub/phase3.c b/scrub/phase3.c index 98e5c5a1f..09a1ea452 100644 --- a/scrub/phase3.c +++ b/scrub/phase3.c @@ -145,25 +145,11 @@ scrub_inode( /* Scrub the inode. */ scrub_item_schedule(&sri, XFS_SCRUB_TYPE_INODE); - error = scrub_item_check_file(ctx, &sri, fd); - if (error) - goto out; - - error = try_inode_repair(ictx, &sri, fd); - if (error) - goto out; /* Scrub all block mappings. */ scrub_item_schedule(&sri, XFS_SCRUB_TYPE_BMBTD); scrub_item_schedule(&sri, XFS_SCRUB_TYPE_BMBTA); scrub_item_schedule(&sri, XFS_SCRUB_TYPE_BMBTC); - error = scrub_item_check_file(ctx, &sri, fd); - if (error) - goto out; - - error = try_inode_repair(ictx, &sri, fd); - if (error) - goto out; /* * Check file data contents, e.g. symlink and directory entries. @@ -182,11 +168,12 @@ scrub_inode( scrub_item_schedule(&sri, XFS_SCRUB_TYPE_XATTR); scrub_item_schedule(&sri, XFS_SCRUB_TYPE_PARENT); + + /* Try to check and repair the file while it's open. */ error = scrub_item_check_file(ctx, &sri, fd); if (error) goto out; - /* Try to repair the file while it's open. */ error = try_inode_repair(ictx, &sri, fd); if (error) goto out; diff --git a/scrub/repair.c b/scrub/repair.c index 6a5fd40fd..8a28f6b13 100644 --- a/scrub/repair.c +++ b/scrub/repair.c @@ -324,6 +324,7 @@ repair_call_kernel( struct scrubv_descr vdesc = SCRUBV_DESCR(&scrubv); struct xfs_scrub_vec *v; unsigned int scrub_type; + bool need_barrier = false; int error; assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL")); @@ -339,6 +340,11 @@ repair_call_kernel( repair_flags)) continue; + if (need_barrier) { + xfrog_scrubv_add_barrier(&scrubv); + need_barrier = false; + } + xfrog_scrubv_add_item(&scrubv, sri, scrub_type, true); if (sri->sri_state[scrub_type] & SCRUB_ITEM_NEEDSREPAIR) @@ -351,6 +357,17 @@ repair_call_kernel( dbg_printf("repair %s flags %xh tries %u\n", descr_render(&dsc), sri->sri_state[scrub_type], sri->sri_tries[scrub_type]); + + /* + * One of the other scrub types depends on this one. Set us up + * to add a repair barrier if we decide to schedule a repair + * after this one. If the UNFIXED flag is set, that means this + * is our last chance to fix things, so we skip the barriers + * just let everything run. + */ + if (!(repair_flags & XRM_FINAL_WARNING) && + (sri->sri_state[scrub_type] & SCRUB_ITEM_BARRIER)) + need_barrier = true; } error = -xfrog_scrubv_metadata(xfdp, &scrubv); @@ -358,6 +375,16 @@ repair_call_kernel( return error; foreach_xfrog_scrubv_vec(&scrubv, vdesc.idx, v) { + /* Deal with barriers separately. */ + if (v->sv_type == XFS_SCRUB_TYPE_BARRIER) { + /* -ECANCELED means the kernel stopped here. */ + if (v->sv_ret == -ECANCELED) + return 0; + if (v->sv_ret) + return -v->sv_ret; + continue; + } + error = repair_epilogue(ctx, &dsc, sri, repair_flags, v); if (error) return error; @@ -446,7 +473,8 @@ repair_item_boost_priorities( * bits are left untouched to force a rescan in phase 4. */ #define MUSTFIX_STATES (SCRUB_ITEM_CORRUPT | \ - SCRUB_ITEM_BOOST_REPAIR) + SCRUB_ITEM_BOOST_REPAIR | \ + SCRUB_ITEM_BARRIER) /* * Figure out which AG metadata must be fixed before we can move on * to the inode scan. @@ -728,7 +756,7 @@ repair_item_class( return 0; if (ctx->mode == SCRUB_MODE_PREEN && !(repair_mask & SCRUB_ITEM_PREEN)) return 0; - if (!scrub_item_schedule_work(sri, repair_mask)) + if (!scrub_item_schedule_work(sri, repair_mask, repair_deps)) return 0; /* diff --git a/scrub/scrub.c b/scrub/scrub.c index d582dafbb..44c404989 100644 --- a/scrub/scrub.c +++ b/scrub/scrub.c @@ -24,6 +24,35 @@ /* Online scrub and repair wrappers. */ +/* + * Bitmap showing the correctness dependencies between scrub types for scrubs. + * Dependencies cannot cross scrub groups. + */ +#define DEP(x) (1U << (x)) +static const unsigned int scrub_deps[XFS_SCRUB_TYPE_NR] = { + [XFS_SCRUB_TYPE_AGF] = DEP(XFS_SCRUB_TYPE_SB), + [XFS_SCRUB_TYPE_AGFL] = DEP(XFS_SCRUB_TYPE_SB) | + DEP(XFS_SCRUB_TYPE_AGF), + [XFS_SCRUB_TYPE_AGI] = DEP(XFS_SCRUB_TYPE_SB), + [XFS_SCRUB_TYPE_BNOBT] = DEP(XFS_SCRUB_TYPE_AGF), + [XFS_SCRUB_TYPE_CNTBT] = DEP(XFS_SCRUB_TYPE_AGF), + [XFS_SCRUB_TYPE_INOBT] = DEP(XFS_SCRUB_TYPE_AGI), + [XFS_SCRUB_TYPE_FINOBT] = DEP(XFS_SCRUB_TYPE_AGI), + [XFS_SCRUB_TYPE_RMAPBT] = DEP(XFS_SCRUB_TYPE_AGF), + [XFS_SCRUB_TYPE_REFCNTBT] = DEP(XFS_SCRUB_TYPE_AGF), + [XFS_SCRUB_TYPE_BMBTD] = DEP(XFS_SCRUB_TYPE_INODE), + [XFS_SCRUB_TYPE_BMBTA] = DEP(XFS_SCRUB_TYPE_INODE), + [XFS_SCRUB_TYPE_BMBTC] = DEP(XFS_SCRUB_TYPE_INODE), + [XFS_SCRUB_TYPE_DIR] = DEP(XFS_SCRUB_TYPE_BMBTD), + [XFS_SCRUB_TYPE_XATTR] = DEP(XFS_SCRUB_TYPE_BMBTA), + [XFS_SCRUB_TYPE_SYMLINK] = DEP(XFS_SCRUB_TYPE_BMBTD), + [XFS_SCRUB_TYPE_PARENT] = DEP(XFS_SCRUB_TYPE_BMBTD), + [XFS_SCRUB_TYPE_QUOTACHECK] = DEP(XFS_SCRUB_TYPE_UQUOTA) | + DEP(XFS_SCRUB_TYPE_GQUOTA) | + DEP(XFS_SCRUB_TYPE_PQUOTA), +}; +#undef DEP + /* Describe the current state of a vectored scrub. */ int format_scrubv_descr( @@ -255,6 +284,20 @@ xfrog_scrubv_add_item( v->sv_flags |= XFS_SCRUB_IFLAG_FORCE_REBUILD; } +/* Add a barrier to the scrub vector. */ +void +xfrog_scrubv_add_barrier( + struct xfrog_scrubv *scrubv) +{ + struct xfs_scrub_vec *v; + + v = xfrog_scrubv_next_vector(scrubv); + + v->sv_type = XFS_SCRUB_TYPE_BARRIER; + v->sv_flags = XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XFAIL | + XFS_SCRUB_OFLAG_XCORRUPT | XFS_SCRUB_OFLAG_INCOMPLETE; +} + /* Do a read-only check of some metadata. */ static int scrub_call_kernel( @@ -267,6 +310,7 @@ scrub_call_kernel( struct scrubv_descr vdesc = SCRUBV_DESCR(&scrubv); struct xfs_scrub_vec *v; unsigned int scrub_type; + bool need_barrier = false; int error; assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL")); @@ -277,8 +321,17 @@ scrub_call_kernel( foreach_scrub_type(scrub_type) { if (!(sri->sri_state[scrub_type] & SCRUB_ITEM_NEEDSCHECK)) continue; + + if (need_barrier) { + xfrog_scrubv_add_barrier(&scrubv); + need_barrier = false; + } + xfrog_scrubv_add_item(&scrubv, sri, scrub_type, false); + if (sri->sri_state[scrub_type] & SCRUB_ITEM_BARRIER) + need_barrier = true; + dbg_printf("check %s flags %xh tries %u\n", descr_render(&dsc), sri->sri_state[scrub_type], sri->sri_tries[scrub_type]); @@ -289,6 +342,16 @@ scrub_call_kernel( return error; foreach_xfrog_scrubv_vec(&scrubv, vdesc.idx, v) { + /* Deal with barriers separately. */ + if (v->sv_type == XFS_SCRUB_TYPE_BARRIER) { + /* -ECANCELED means the kernel stopped here. */ + if (v->sv_ret == -ECANCELED) + return 0; + if (v->sv_ret) + return -v->sv_ret; + continue; + } + error = scrub_epilogue(ctx, &dsc, sri, v); if (error) return error; @@ -383,15 +446,25 @@ scrub_item_call_kernel_again( bool scrub_item_schedule_work( struct scrub_item *sri, - uint8_t state_flags) + uint8_t state_flags, + const unsigned int *schedule_deps) { unsigned int scrub_type; unsigned int nr = 0; foreach_scrub_type(scrub_type) { + unsigned int j; + + sri->sri_state[scrub_type] &= ~SCRUB_ITEM_BARRIER; + if (!(sri->sri_state[scrub_type] & state_flags)) continue; + foreach_scrub_type(j) { + if (schedule_deps[scrub_type] & (1U << j)) + sri->sri_state[j] |= SCRUB_ITEM_BARRIER; + } + sri->sri_tries[scrub_type] = SCRUB_ITEM_MAX_RETRIES; nr++; } @@ -411,7 +484,7 @@ scrub_item_check_file( struct xfs_fd *xfdp = &ctx->mnt; int error = 0; - if (!scrub_item_schedule_work(sri, SCRUB_ITEM_NEEDSCHECK)) + if (!scrub_item_schedule_work(sri, SCRUB_ITEM_NEEDSCHECK, scrub_deps)) return 0; /* diff --git a/scrub/scrub.h b/scrub/scrub.h index 183b89379..c3eed1b26 100644 --- a/scrub/scrub.h +++ b/scrub/scrub.h @@ -30,6 +30,9 @@ enum xfrog_scrub_group; /* This scrub type needs to be checked. */ #define SCRUB_ITEM_NEEDSCHECK (1 << 5) +/* Scrub barrier. */ +#define SCRUB_ITEM_BARRIER (1 << 6) + /* All of the state flags that we need to prioritize repair work. */ #define SCRUB_ITEM_REPAIR_ANY (SCRUB_ITEM_CORRUPT | \ SCRUB_ITEM_PREEN | \ @@ -126,6 +129,20 @@ scrub_item_check(struct scrub_ctx *ctx, struct scrub_item *sri) return scrub_item_check_file(ctx, sri, -1); } +/* Count the number of metadata objects still needing a scrub. */ +static inline unsigned int +scrub_item_count_needscheck( + const struct scrub_item *sri) +{ + unsigned int ret = 0; + unsigned int i; + + foreach_scrub_type(i) + if (sri->sri_state[i] & SCRUB_ITEM_NEEDSCHECK) + ret++; + return ret; +} + void scrub_report_preen_triggers(struct scrub_ctx *ctx); bool can_scrub_fs_metadata(struct scrub_ctx *ctx); diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h index d9de18ce1..c5e0a7c08 100644 --- a/scrub/scrub_private.h +++ b/scrub/scrub_private.h @@ -13,6 +13,7 @@ void xfrog_scrubv_from_item(struct xfrog_scrubv *scrubv, void xfrog_scrubv_add_item(struct xfrog_scrubv *scrubv, const struct scrub_item *sri, unsigned int scrub_type, bool want_repair); +void xfrog_scrubv_add_barrier(struct xfrog_scrubv *scrubv); struct scrubv_descr { struct xfrog_scrubv *scrubv; @@ -116,6 +117,7 @@ scrub_item_schedule_retry(struct scrub_item *sri, unsigned int scrub_type) bool scrub_item_call_kernel_again(struct scrub_item *sri, uint8_t work_mask, const struct scrub_item *old); -bool scrub_item_schedule_work(struct scrub_item *sri, uint8_t state_flags); +bool scrub_item_schedule_work(struct scrub_item *sri, uint8_t state_flags, + const unsigned int *schedule_deps); #endif /* XFS_SCRUB_SCRUB_PRIVATE_H_ */

[09/10] xfs_scrub: use scrub barriers to reduce kernel calls

Commit Message

Patch