All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Subject: [PATCH 19/42] xfs: factor xfs_bmap_btalloc()
Date: Fri, 10 Feb 2023 09:18:02 +1100	[thread overview]
Message-ID: <20230209221825.3722244-20-david@fromorbit.com> (raw)
In-Reply-To: <20230209221825.3722244-1-david@fromorbit.com>

From: Dave Chinner <dchinner@redhat.com>

There are several different contexts xfs_bmap_btalloc() handles, and
large chunks of the code execute independent allocation contexts.
Try to untangle this mess a bit.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c | 355 +++++++++++++++++++++++----------------
 1 file changed, 207 insertions(+), 148 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index baf11bc4d091..a28d57b82396 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3196,13 +3196,13 @@ xfs_bmap_select_minlen(
 	}
 }
 
-STATIC int
+static int
 xfs_bmap_btalloc_select_lengths(
 	struct xfs_bmalloca	*ap,
 	struct xfs_alloc_arg	*args,
 	xfs_extlen_t		*blen)
 {
-	struct xfs_mount	*mp = ap->ip->i_mount;
+	struct xfs_mount	*mp = args->mp;
 	struct xfs_perag	*pag;
 	xfs_agnumber_t		agno, startag;
 	int			notinit = 0;
@@ -3216,7 +3216,7 @@ xfs_bmap_btalloc_select_lengths(
 	}
 
 	args->total = ap->total;
-	startag = XFS_FSB_TO_AGNO(mp, args->fsbno);
+	startag = XFS_FSB_TO_AGNO(mp, ap->blkno);
 	if (startag == NULLAGNUMBER)
 		startag = 0;
 
@@ -3258,7 +3258,7 @@ xfs_bmap_btalloc_filestreams(
 	args->type = XFS_ALLOCTYPE_NEAR_BNO;
 	args->total = ap->total;
 
-	start_agno = XFS_FSB_TO_AGNO(mp, args->fsbno);
+	start_agno = XFS_FSB_TO_AGNO(mp, ap->blkno);
 	if (start_agno == NULLAGNUMBER)
 		start_agno = 0;
 
@@ -3496,170 +3496,229 @@ xfs_bmap_exact_minlen_extent_alloc(
 
 #endif
 
-STATIC int
-xfs_bmap_btalloc(
-	struct xfs_bmalloca	*ap)
+/*
+ * If we are not low on available data blocks and we are allocating at
+ * EOF, optimise allocation for contiguous file extension and/or stripe
+ * alignment of the new extent.
+ *
+ * NOTE: ap->aeof is only set if the allocation length is >= the
+ * stripe unit and the allocation offset is at the end of file.
+ */
+static int
+xfs_bmap_btalloc_at_eof(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_extlen_t		blen,
+	int			stripe_align)
 {
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	struct xfs_alloc_arg	args = { .tp = ap->tp, .mp = mp };
-	xfs_alloctype_t		atype = 0;
-	xfs_agnumber_t		ag;
-	xfs_fileoff_t		orig_offset;
-	xfs_extlen_t		orig_length;
-	xfs_extlen_t		blen;
-	xfs_extlen_t		nextminlen = 0;
-	int			isaligned = 0;
+	struct xfs_mount	*mp = args->mp;
+	xfs_alloctype_t		atype;
 	int			error;
-	int			stripe_align;
 
-	ASSERT(ap->length);
-	orig_offset = ap->offset;
-	orig_length = ap->length;
+	/*
+	 * If there are already extents in the file, try an exact EOF block
+	 * allocation to extend the file as a contiguous extent. If that fails,
+	 * or it's the first allocation in a file, just try for a stripe aligned
+	 * allocation.
+	 */
+	if (ap->offset) {
+		xfs_extlen_t	nextminlen = 0;
 
-	stripe_align = xfs_bmap_compute_alignments(ap, &args);
+		atype = args->type;
+		args->type = XFS_ALLOCTYPE_THIS_BNO;
+		args->alignment = 1;
 
+		/*
+		 * Compute the minlen+alignment for the next case.  Set slop so
+		 * that the value of minlen+alignment+slop doesn't go up between
+		 * the calls.
+		 */
+		if (blen > stripe_align && blen <= args->maxlen)
+			nextminlen = blen - stripe_align;
+		else
+			nextminlen = args->minlen;
+		if (nextminlen + stripe_align > args->minlen + 1)
+			args->minalignslop = nextminlen + stripe_align -
+					args->minlen - 1;
+		else
+			args->minalignslop = 0;
+
+		args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, args->fsbno));
+		error = xfs_alloc_vextent_this_ag(args);
+		xfs_perag_put(args->pag);
+		if (error)
+			return error;
+
+		if (args->fsbno != NULLFSBLOCK)
+			return 0;
+		/*
+		 * Exact allocation failed. Reset to try an aligned allocation
+		 * according to the original allocation specification.
+		 */
+		args->pag = NULL;
+		args->type = atype;
+		args->fsbno = ap->blkno;
+		args->alignment = stripe_align;
+		args->minlen = nextminlen;
+		args->minalignslop = 0;
+	} else {
+		args->alignment = stripe_align;
+		atype = args->type;
+		/*
+		 * Adjust minlen to try and preserve alignment if we
+		 * can't guarantee an aligned maxlen extent.
+		 */
+		if (blen > args->alignment &&
+		    blen <= args->maxlen + args->alignment)
+			args->minlen = blen - args->alignment;
+		args->minalignslop = 0;
+	}
+
+	error = xfs_alloc_vextent(args);
+	if (error)
+		return error;
+
+	if (args->fsbno != NULLFSBLOCK)
+		return 0;
+
+	/*
+	 * Allocation failed, so turn return the allocation args to their
+	 * original non-aligned state so the caller can proceed on allocation
+	 * failure as if this function was never called.
+	 */
+	args->type = atype;
+	args->fsbno = ap->blkno;
+	args->alignment = 1;
+	return 0;
+}
+
+static int
+xfs_bmap_btalloc_best_length(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	int			stripe_align)
+{
+	struct xfs_mount	*mp = args->mp;
+	xfs_extlen_t		blen = 0;
+	int			error;
+
+	/*
+	 * Determine the initial block number we will target for allocation.
+	 */
 	if ((ap->datatype & XFS_ALLOC_USERDATA) &&
 	    xfs_inode_is_filestream(ap->ip)) {
-		ag = xfs_filestream_lookup_ag(ap->ip);
-		ag = (ag != NULLAGNUMBER) ? ag : 0;
-		ap->blkno = XFS_AGB_TO_FSB(mp, ag, 0);
+		xfs_agnumber_t	agno = xfs_filestream_lookup_ag(ap->ip);
+		if (agno == NULLAGNUMBER)
+			agno = 0;
+		ap->blkno = XFS_AGB_TO_FSB(mp, agno, 0);
 	} else {
 		ap->blkno = XFS_INO_TO_FSB(mp, ap->ip->i_ino);
 	}
-
 	xfs_bmap_adjacent(ap);
+	args->fsbno = ap->blkno;
 
-	args.fsbno = ap->blkno;
-	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
+	/*
+	 * Search for an allocation group with a single extent large enough for
+	 * the request.  If one isn't found, then adjust the minimum allocation
+	 * size to the largest space found.
+	 */
+	if ((ap->datatype & XFS_ALLOC_USERDATA) &&
+	    xfs_inode_is_filestream(ap->ip))
+		error = xfs_bmap_btalloc_filestreams(ap, args, &blen);
+	else
+		error = xfs_bmap_btalloc_select_lengths(ap, args, &blen);
+	if (error)
+		return error;
+
+	/*
+	 * Don't attempt optimal EOF allocation if previous allocations barely
+	 * succeeded due to being near ENOSPC. It is highly unlikely we'll get
+	 * optimal or even aligned allocations in this case, so don't waste time
+	 * trying.
+	 */
+	if (ap->aeof && !(ap->tp->t_flags & XFS_TRANS_LOWMODE)) {
+		error = xfs_bmap_btalloc_at_eof(ap, args, blen, stripe_align);
+		if (error)
+			return error;
+		if (args->fsbno != NULLFSBLOCK)
+			return 0;
+	}
+
+	error = xfs_alloc_vextent(args);
+	if (error)
+		return error;
+	if (args->fsbno != NULLFSBLOCK)
+		return 0;
+
+	/*
+	 * Try a locality first full filesystem minimum length allocation whilst
+	 * still maintaining necessary total block reservation requirements.
+	 */
+	if (args->minlen > ap->minlen) {
+		args->minlen = ap->minlen;
+		args->type = XFS_ALLOCTYPE_START_BNO;
+		args->fsbno = ap->blkno;
+		error = xfs_alloc_vextent(args);
+		if (error)
+			return error;
+	}
+	if (args->fsbno != NULLFSBLOCK)
+		return 0;
+
+	/*
+	 * We are now critically low on space, so this is a last resort
+	 * allocation attempt: no reserve, no locality, blocking, minimum
+	 * length, full filesystem free space scan. We also indicate to future
+	 * allocations in this transaction that we are critically low on space
+	 * so they don't waste time on allocation modes that are unlikely to
+	 * succeed.
+	 */
+	args->fsbno = 0;
+	args->type = XFS_ALLOCTYPE_FIRST_AG;
+	args->total = ap->minlen;
+	error = xfs_alloc_vextent(args);
+	if (error)
+		return error;
+	ap->tp->t_flags |= XFS_TRANS_LOWMODE;
+	return 0;
+}
+
+static int
+xfs_bmap_btalloc(
+	struct xfs_bmalloca	*ap)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	struct xfs_alloc_arg	args = {
+		.tp		= ap->tp,
+		.mp		= mp,
+		.fsbno		= NULLFSBLOCK,
+		.oinfo		= XFS_RMAP_OINFO_SKIP_UPDATE,
+		.minleft	= ap->minleft,
+		.wasdel		= ap->wasdel,
+		.resv		= XFS_AG_RESV_NONE,
+		.datatype	= ap->datatype,
+		.alignment	= 1,
+		.minalignslop	= 0,
+	};
+	xfs_fileoff_t		orig_offset;
+	xfs_extlen_t		orig_length;
+	int			error;
+	int			stripe_align;
+
+	ASSERT(ap->length);
+	orig_offset = ap->offset;
+	orig_length = ap->length;
+
+	stripe_align = xfs_bmap_compute_alignments(ap, &args);
 
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
-	blen = 0;
 
-	/*
-	 * Search for an allocation group with a single extent large
-	 * enough for the request.  If one isn't found, then adjust
-	 * the minimum allocation size to the largest space found.
-	 */
-	if ((ap->datatype & XFS_ALLOC_USERDATA) &&
-	    xfs_inode_is_filestream(ap->ip))
-		error = xfs_bmap_btalloc_filestreams(ap, &args, &blen);
-	else
-		error = xfs_bmap_btalloc_select_lengths(ap, &args, &blen);
+	error = xfs_bmap_btalloc_best_length(ap, &args, stripe_align);
 	if (error)
 		return error;
 
-	/*
-	 * If we are not low on available data blocks, and the underlying
-	 * logical volume manager is a stripe, and the file offset is zero then
-	 * try to allocate data blocks on stripe unit boundary. NOTE: ap->aeof
-	 * is only set if the allocation length is >= the stripe unit and the
-	 * allocation offset is at the end of file.
-	 */
-	if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
-		if (!ap->offset) {
-			args.alignment = stripe_align;
-			atype = args.type;
-			isaligned = 1;
-			/*
-			 * Adjust minlen to try and preserve alignment if we
-			 * can't guarantee an aligned maxlen extent.
-			 */
-			if (blen > args.alignment &&
-			    blen <= args.maxlen + args.alignment)
-				args.minlen = blen - args.alignment;
-			args.minalignslop = 0;
-		} else {
-			/*
-			 * First try an exact bno allocation.
-			 * If it fails then do a near or start bno
-			 * allocation with alignment turned on.
-			 */
-			atype = args.type;
-			args.type = XFS_ALLOCTYPE_THIS_BNO;
-			args.alignment = 1;
-
-			/*
-			 * Compute the minlen+alignment for the
-			 * next case.  Set slop so that the value
-			 * of minlen+alignment+slop doesn't go up
-			 * between the calls.
-			 */
-			if (blen > stripe_align && blen <= args.maxlen)
-				nextminlen = blen - stripe_align;
-			else
-				nextminlen = args.minlen;
-			if (nextminlen + stripe_align > args.minlen + 1)
-				args.minalignslop =
-					nextminlen + stripe_align -
-					args.minlen - 1;
-			else
-				args.minalignslop = 0;
-
-			args.pag = xfs_perag_get(mp,
-					XFS_FSB_TO_AGNO(mp, args.fsbno));
-			error = xfs_alloc_vextent_this_ag(&args);
-			xfs_perag_put(args.pag);
-			if (error)
-				return error;
-
-			if (args.fsbno != NULLFSBLOCK)
-				goto out_success;
-			/*
-			 * Exact allocation failed. Now try with alignment
-			 * turned on.
-			 */
-			args.pag = NULL;
-			args.type = atype;
-			args.fsbno = ap->blkno;
-			args.alignment = stripe_align;
-			args.minlen = nextminlen;
-			args.minalignslop = 0;
-			isaligned = 1;
-		}
-	} else {
-		args.alignment = 1;
-		args.minalignslop = 0;
-	}
-
-	error = xfs_alloc_vextent(&args);
-	if (error)
-		return error;
-
-	if (isaligned && args.fsbno == NULLFSBLOCK) {
-		/*
-		 * allocation failed, so turn off alignment and
-		 * try again.
-		 */
-		args.type = atype;
-		args.fsbno = ap->blkno;
-		args.alignment = 0;
-		if ((error = xfs_alloc_vextent(&args)))
-			return error;
-	}
-	if (args.fsbno == NULLFSBLOCK &&
-	    args.minlen > ap->minlen) {
-		args.minlen = ap->minlen;
-		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = ap->blkno;
-		if ((error = xfs_alloc_vextent(&args)))
-			return error;
-	}
-	if (args.fsbno == NULLFSBLOCK) {
-		args.fsbno = 0;
-		args.type = XFS_ALLOCTYPE_FIRST_AG;
-		args.total = ap->minlen;
-		if ((error = xfs_alloc_vextent(&args)))
-			return error;
-		ap->tp->t_flags |= XFS_TRANS_LOWMODE;
-	}
-	args.minleft = ap->minleft;
-	args.wasdel = ap->wasdel;
-	args.resv = XFS_AG_RESV_NONE;
-	args.datatype = ap->datatype;
-
 	if (args.fsbno != NULLFSBLOCK) {
-out_success:
 		xfs_bmap_process_allocated_extent(ap, &args, orig_offset,
 			orig_length);
 	} else {
-- 
2.39.0


  parent reply	other threads:[~2023-02-09 22:18 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-09 22:17 [PATCH v3 00/42] xfs: per-ag centric allocation alogrithms Dave Chinner
2023-02-09 22:17 ` [PATCH 01/42] xfs: fix low space alloc deadlock Dave Chinner
2023-02-09 22:17 ` [PATCH 02/42] xfs: prefer free inodes at ENOSPC over chunk allocation Dave Chinner
2023-02-09 22:17 ` [PATCH 03/42] xfs: block reservation too large for minleft allocation Dave Chinner
2023-02-09 22:17 ` [PATCH 04/42] xfs: drop firstblock constraints from allocation setup Dave Chinner
2023-02-09 22:17 ` [PATCH 05/42] xfs: t_firstblock is tracking AGs not blocks Dave Chinner
2023-02-09 22:17 ` [PATCH 06/42] xfs: don't assert fail on transaction cancel with deferred ops Dave Chinner
2023-02-09 22:17 ` [PATCH 07/42] xfs: active perag reference counting Dave Chinner
2023-02-11  4:06   ` Darrick J. Wong
2023-02-09 22:17 ` [PATCH 08/42] xfs: rework the perag trace points to be perag centric Dave Chinner
2023-02-09 22:17 ` [PATCH 09/42] xfs: convert xfs_imap() to take a perag Dave Chinner
2023-02-09 22:17 ` [PATCH 10/42] xfs: use active perag references for inode allocation Dave Chinner
2023-02-09 22:17 ` [PATCH 11/42] xfs: inobt can use perags in many more places than it does Dave Chinner
2023-02-09 22:17 ` [PATCH 12/42] xfs: convert xfs_ialloc_next_ag() to an atomic Dave Chinner
2023-02-09 22:17 ` [PATCH 13/42] xfs: perags need atomic operational state Dave Chinner
2023-02-09 22:17 ` [PATCH 14/42] xfs: introduce xfs_for_each_perag_wrap() Dave Chinner
2023-02-09 22:17 ` [PATCH 15/42] xfs: rework xfs_alloc_vextent() Dave Chinner
2023-02-09 22:17 ` [PATCH 16/42] xfs: factor xfs_alloc_vextent_this_ag() for _iterate_ags() Dave Chinner
2023-02-09 22:18 ` [PATCH 17/42] xfs: combine __xfs_alloc_vextent_this_ag and xfs_alloc_ag_vextent Dave Chinner
2023-02-09 22:18 ` [PATCH 18/42] xfs: use xfs_alloc_vextent_this_ag() where appropriate Dave Chinner
2023-02-09 22:18 ` Dave Chinner [this message]
2023-02-09 22:18 ` [PATCH 20/42] xfs: use xfs_alloc_vextent_first_ag() " Dave Chinner
2023-02-09 22:18 ` [PATCH 21/42] xfs: use xfs_alloc_vextent_start_bno() " Dave Chinner
2023-02-09 22:18 ` [PATCH 22/42] xfs: introduce xfs_alloc_vextent_near_bno() Dave Chinner
2023-02-09 22:18 ` [PATCH 23/42] xfs: introduce xfs_alloc_vextent_exact_bno() Dave Chinner
2023-02-09 22:18 ` [PATCH 24/42] xfs: introduce xfs_alloc_vextent_prepare() Dave Chinner
2023-02-09 22:18 ` [PATCH 25/42] xfs: move allocation accounting to xfs_alloc_vextent_set_fsbno() Dave Chinner
2023-02-09 22:18 ` [PATCH 26/42] xfs: fold xfs_alloc_ag_vextent() into callers Dave Chinner
2023-02-09 22:18 ` [PATCH 27/42] xfs: move the minimum agno checks into xfs_alloc_vextent_check_args Dave Chinner
2023-02-09 22:18 ` [PATCH 28/42] xfs: convert xfs_alloc_vextent_iterate_ags() to use perag walker Dave Chinner
2023-02-09 22:18 ` [PATCH 29/42] xfs: convert trim to use for_each_perag_range Dave Chinner
2023-02-09 22:18 ` [PATCH 30/42] xfs: factor out filestreams from xfs_bmap_btalloc_nullfb Dave Chinner
2023-02-09 22:18 ` [PATCH 31/42] xfs: get rid of notinit from xfs_bmap_longest_free_extent Dave Chinner
2023-02-09 22:18 ` [PATCH 32/42] xfs: use xfs_bmap_longest_free_extent() in filestreams Dave Chinner
2023-02-09 22:18 ` [PATCH 33/42] xfs: move xfs_bmap_btalloc_filestreams() to xfs_filestreams.c Dave Chinner
2023-02-09 22:18 ` [PATCH 34/42] xfs: merge filestream AG lookup into xfs_filestream_select_ag() Dave Chinner
2023-02-09 22:18 ` [PATCH 35/42] xfs: merge new filestream AG selection " Dave Chinner
2023-02-09 22:18 ` [PATCH 36/42] xfs: remove xfs_filestream_select_ag() longest extent check Dave Chinner
2023-02-09 22:18 ` [PATCH 37/42] xfs: factor out MRU hit case in xfs_filestream_select_ag Dave Chinner
2023-02-09 22:18 ` [PATCH 38/42] xfs: track an active perag reference in filestreams Dave Chinner
2023-02-09 22:18 ` [PATCH 39/42] xfs: use for_each_perag_wrap in xfs_filestream_pick_ag Dave Chinner
2023-02-09 22:18 ` [PATCH 40/42] xfs: pass perag to filestreams tracing Dave Chinner
2023-02-09 22:18 ` [PATCH 41/42] xfs: return a referenced perag from filestreams allocator Dave Chinner
2023-02-09 22:18 ` [PATCH 42/42] xfs: refactor the filestreams allocator pick functions Dave Chinner
2023-02-10  3:09 ` [PATCH v3 00/42] xfs: per-ag centric allocation alogrithms Darrick J. Wong
2023-02-10  5:00   ` Dave Chinner
  -- strict thread matches above, loose matches on Subject: below --
2023-01-18 22:44 [PATCH " Dave Chinner
2023-01-18 22:44 ` [PATCH 19/42] xfs: factor xfs_bmap_btalloc() Dave Chinner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230209221825.3722244-20-david@fromorbit.com \
    --to=david@fromorbit.com \
    --cc=linux-xfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.