public inbox for linux-xfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: xfs@oss.sgi.com
Subject: [PATCH 20/36] db: rewrite IO engine to use libxfs
Date: Wed, 13 Nov 2013 17:40:44 +1100	[thread overview]
Message-ID: <1384324860-25677-21-git-send-email-david@fromorbit.com> (raw)
In-Reply-To: <1384324860-25677-1-git-send-email-david@fromorbit.com>

From: Dave Chinner <dchinner@redhat.com>

Now that we have buffers and xfs_buf_maps, it is relatively easy to
convert the IO engine to use libxfs routines. This gets rid of the
most of the differences between mapped and straight buffer reads,
and tracks xfs_bufs directly in the IO context that is being used.

This is not yet a perfect solution, as xfs_db does different sized
IOs for the same block range which will throw warnings like:

xfs_db> inode 64
7ffff7fde740: Badness in key lookup (length)
bp=(bno 0x40, len 8192 bytes) key=(bno 0x40, len 4096 bytes)
xfs_db>

This is when first displaying an inode in the root inode chunk.
These will need to be dealt with on a case by case basis.

Further, xfs_db can build up a large IO stack by the time it has run
to completion. If we don't unwind this IO stack before we shut down
the libxfs caches, metadump and other db programs will exit with
unreleased buffers and emit warnings like:

cache_purge: shake on cache 0x69e4f0 left 7 nodes!?

Hence we need to unwind the iostack as we shut down.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 db/init.c |  28 ++++++++--
 db/io.c   | 178 +++++++++++++++++---------------------------------------------
 db/io.h   |   4 +-
 3 files changed, 73 insertions(+), 137 deletions(-)

diff --git a/db/init.c b/db/init.c
index 489c9fb..2dc7c87 100644
--- a/db/init.c
+++ b/db/init.c
@@ -54,8 +54,8 @@ init(
 	int		argc,
 	char		**argv)
 {
-	xfs_sb_t	*sbp;
-	char		bufp[BBSIZE];
+	struct xfs_sb	*sbp;
+	struct xfs_buf	*bp;
 	int		c;
 
 	setlocale(LC_ALL, "");
@@ -115,14 +115,25 @@ init(
 		exit(1);
 	}
 
-	if (read_buf(XFS_SB_DADDR, 1, bufp)) {
+	/*
+	 * Read the superblock, but don't validate it - we are a diagnostic
+	 * tool and so need to be able to mount busted filesystems.
+	 */
+	memset(&xmount, 0, sizeof(struct xfs_mount));
+	libxfs_buftarg_init(&xmount, x.ddev, x.logdev, x.rtdev);
+	bp = libxfs_readbuf(xmount.m_ddev_targp, XFS_SB_DADDR,
+			    1 << (XFS_MAX_SECTORSIZE_LOG - BBSHIFT), 0, NULL);
+
+	if (!bp || bp->b_error) {
 		fprintf(stderr, _("%s: %s is invalid (cannot read first 512 "
 			"bytes)\n"), progname, fsdevice);
 		exit(1);
 	}
 
 	/* copy SB from buffer to in-core, converting architecture as we go */
-	libxfs_sb_from_disk(&xmount.m_sb, (struct xfs_dsb *)bufp);
+	libxfs_sb_from_disk(&xmount.m_sb, XFS_BUF_TO_SBP(bp));
+	libxfs_putbuf(bp);
+	libxfs_purgebuf(bp);
 
 	sbp = &xmount.m_sb;
 	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
@@ -186,9 +197,11 @@ main(
 	int	c, i, done = 0;
 	char	*input;
 	char	**v;
+	int	start_iocur_sp;
 
 	pushfile(stdin);
 	init(argc, argv);
+	start_iocur_sp = iocur_sp;
 
 	for (i = 0; !done && i < ncmdline; i++) {
 		v = breakline(cmdline[i], &c);
@@ -211,6 +224,13 @@ main(
 	}
 
 close_devices:
+	/*
+	 * Make sure that we pop the all the buffer contexts we hold so that
+	 * they are released before we purge the caches during unmount.
+	 */
+	while (iocur_sp > start_iocur_sp)
+		pop_cur();
+	libxfs_umount(mp);
 	if (x.ddev)
 		libxfs_device_close(x.ddev);
 	if (x.logdev && x.logdev != x.ddev)
diff --git a/db/io.c b/db/io.c
index 01a5970..ca89354 100644
--- a/db/io.c
+++ b/db/io.c
@@ -104,8 +104,14 @@ pop_cur(void)
 		dbprintf(_("can't pop anything from I/O stack\n"));
 		return;
 	}
-	if (iocur_top->buf)
-		xfree(iocur_top->buf);
+	if (iocur_top->bp) {
+		libxfs_putbuf(iocur_top->bp);
+		iocur_top->bp = NULL;
+	}
+	if (iocur_top->bbmap) {
+		free(iocur_top->bbmap);
+		iocur_top->bbmap = NULL;
+	}
 	if (--iocur_sp >= 0) {
 		iocur_top = iocur_base + iocur_sp;
 		cur_typ = iocur_top->typ;
@@ -147,10 +153,11 @@ print_iocur(
 	dbprintf(_("\tbuffer block %lld (fsbno %lld), %d bb%s\n"), ioc->bb,
 		(xfs_dfsbno_t)XFS_DADDR_TO_FSB(mp, ioc->bb), ioc->blen,
 		ioc->blen == 1 ? "" : "s");
-	if (ioc->use_bbmap) {
+	if (ioc->bbmap) {
 		dbprintf(_("\tblock map"));
-		for (i = 0; i < ioc->blen; i++)
-			dbprintf(" %d:%lld", i, ioc->bbmap.b[i]);
+		for (i = 0; i < ioc->bbmap->nmaps; i++)
+			dbprintf(" %lld:%d", ioc->bbmap->b[i].bm_bn,
+					     ioc->bbmap->b[i].bm_len);
 		dbprintf("\n");
 	}
 	dbprintf(_("\tinode %lld, dir inode %lld, type %s\n"), ioc->ino,
@@ -238,7 +245,7 @@ push_f(
 	else
 		set_cur(iocur_top[-1].typ, iocur_top[-1].bb,
 			iocur_top[-1].blen, DB_RING_IGN,
-			iocur_top[-1].use_bbmap ? &iocur_top[-1].bbmap : NULL);
+			iocur_top[-1].bbmap);
 
 	/* run requested command */
 	if (argc>1)
@@ -280,8 +287,7 @@ forward_f(
 		iocur_ring[ring_current].bb,
 		iocur_ring[ring_current].blen,
 		DB_RING_IGN,
-		iocur_ring[ring_current].use_bbmap ?
-			&iocur_ring[ring_current].bbmap : NULL);
+		iocur_ring[ring_current].bbmap);
 
 	return 0;
 }
@@ -321,8 +327,7 @@ back_f(
 		iocur_ring[ring_current].bb,
 		iocur_ring[ring_current].blen,
 		DB_RING_IGN,
-		iocur_ring[ring_current].use_bbmap ?
-			&iocur_ring[ring_current].bbmap : NULL);
+		iocur_ring[ring_current].bbmap);
 
 	return 0;
 }
@@ -362,7 +367,7 @@ ring_f(
 		iocur_ring[index].bb,
 		iocur_ring[index].blen,
 		DB_RING_IGN,
-		iocur_ring[index].use_bbmap ? &iocur_ring[index].bbmap : NULL);
+		iocur_ring[index].bbmap);
 
 	return 0;
 }
@@ -417,132 +422,37 @@ ring_add(void)
 	}
 }
 
-int
-read_buf(
-	xfs_daddr_t	bbno,
-	int		count,
-	void		*bufp)
-{
-	int		err;
-
-	err = pread64(x.dfd, bufp, BBTOB(count), BBTOB(bbno));
-	if (err < 0)
-		err = errno;
-	else if (err < count)
-		err = -1;
-	return err;
-}
-
-static int
-write_buf(
-	xfs_daddr_t	bbno,
-	int		count,
-	void		*bufp)
-{
-	int		err;
-
-	err = pwrite64(x.dfd, bufp, BBTOB(count), BBTOB(bbno));
-	if (err < 0)
-		err = errno;
-	else if (err < count)
-		err = -1;
-	return err;
-}
-
 static void
 write_cur_buf(void)
 {
 	int ret;
 
-	ret = write_buf(iocur_top->bb, iocur_top->blen, iocur_top->buf);
-
-	if (ret == -1)
-		dbprintf(_("incomplete write, block: %lld\n"),
-			 (iocur_base + iocur_sp)->bb);
-	else if (ret != 0)
+	ret = libxfs_writebufr(iocur_top->bp);
+	if (ret != 0)
 		dbprintf(_("write error: %s\n"), strerror(ret));
 
 	/* re-read buffer from disk */
-	ret = read_buf(iocur_top->bb, iocur_top->blen, iocur_top->buf);
-	if (ret == -1)
-		dbprintf(_("incomplete read, block: %lld\n"),
-			 (iocur_base + iocur_sp)->bb);
-	else if (ret != 0)
+	ret = libxfs_readbufr(mp->m_ddev_targp, iocur_top->bb, iocur_top->bp,
+			      iocur_top->blen, 0);
+	if (ret != 0)
 		dbprintf(_("read error: %s\n"), strerror(ret));
 }
 
-static int
-write_bbs(
-	__int64_t       bbno,
-	int             count,
-	void            *bufp,
-	bbmap_t		*bbmap)
-{
-	int		j;
-	int		rval = EINVAL;	/* initialize for zero `count' case */
-
-	for (j = 0; j < count;) {
-		rval = write_buf(bbmap->b[j].bm_bn, bbmap->b[j].bm_len,
-			     (char *)bufp + BBTOB(j));
-		if (rval)
-			break;
-
-		j += bbmap->b[j].bm_len;
-	}
-	return rval;
-}
-
-static int
-read_bbs(
-	__int64_t	bbno,
-	int		count,
-	void		**bufp,
-	bbmap_t		*bbmap)
-{
-	void		*buf;
-	int		j;
-	int		rval = EINVAL;
-
-	if (count <= 0)
-		count = 1;
-
-	if (*bufp == NULL)
-		buf = xmalloc(BBTOB(count));
-	else
-		buf = *bufp;
-	for (j = 0; j < count;) {
-		rval = read_buf(bbmap->b[j].bm_bn, bbmap->b[j].bm_len,
-			     (char *)buf + BBTOB(j));
-		if (rval)
-			break;
-
-		j += bbmap->b[j].bm_len;
-	}
-	if (*bufp == NULL)
-		*bufp = buf;
-	return rval;
-}
-
 static void
 write_cur_bbs(void)
 {
 	int ret;
 
-	ret = write_bbs(iocur_top->bb, iocur_top->blen, iocur_top->buf,
-			&iocur_top->bbmap);
-	if (ret == -1)
-		dbprintf(_("incomplete write, block: %lld\n"),
-			 (iocur_base + iocur_sp)->bb);
-	else if (ret != 0)
+	ret = libxfs_writebufr(iocur_top->bp);
+	if (ret != 0)
 		dbprintf(_("write error: %s\n"), strerror(ret));
 
+
 	/* re-read buffer from disk */
-	ret = read_bbs(iocur_top->bb, iocur_top->blen, &iocur_top->buf,
-		iocur_top->use_bbmap ? &iocur_top->bbmap : NULL);
-	if (ret == -1)
-		dbprintf(_("incomplete read, block: %lld\n"),
-			 (iocur_base + iocur_sp)->bb);
-	else if (ret != 0)
+	ret = libxfs_readbufr_map(mp->m_ddev_targp, iocur_top->bp,
+				  iocur_top->bbmap->b, iocur_top->bbmap->nmaps,
+				  0);
+	if (ret != 0)
 		dbprintf(_("read error: %s\n"), strerror(ret));
 }
 
@@ -554,7 +464,7 @@ write_cur(void)
 		return;
 	}
 
-	if (iocur_top->use_bbmap)
+	if (iocur_top->bbmap)
 		write_cur_bbs();
 	else
 		write_cur_buf();
@@ -568,6 +478,7 @@ set_cur(
 	int             ring_flag,
 	bbmap_t		*bbmap)
 {
+	struct xfs_buf	*bp;
 	xfs_ino_t	dirino;
 	xfs_ino_t	ino;
 	__uint16_t	mode;
@@ -585,23 +496,28 @@ set_cur(
 
 	if (bbmap) {
 #ifdef DEBUG
+		int i;
 		printf(_("xfs_db got a bbmap for %lld\n"), (long long)d);
+		printf(_("\tblock map"));
+		for (i = 0; i < bbmap->nmaps; i++)
+			printf(" %lld:%d", (long long)bbmap->b[i].bm_bn,
+					   bbmap->b[i].bm_len);
+		printf("\n");
 #endif
-
-		if (read_bbs(d, c, &iocur_top->buf, bbmap))
+		iocur_top->bbmap = malloc(sizeof(struct bbmap));
+		if (!iocur_top->bbmap)
 			return;
-		iocur_top->bbmap = *bbmap;
-		iocur_top->use_bbmap = 1;
+		memcpy(iocur_top->bbmap, bbmap, sizeof(struct bbmap));
+		bp = libxfs_readbuf_map(mp->m_ddev_targp, bbmap->b,
+					bbmap->nmaps, 0, NULL);
 	} else {
-		if (!iocur_top->buf) {
-			iocur_top->buf = malloc(BBTOB(c));
-			if (!iocur_top->buf)
-				return;
-		}
-		if (read_buf(d, c, iocur_top->buf))
-			return;
-		iocur_top->use_bbmap = 0;
+		bp = libxfs_readbuf(mp->m_ddev_targp, d, c, 0, NULL);
+		iocur_top->bbmap = NULL;
 	}
+	if (!bp || bp->b_error)
+		return;
+	iocur_top->buf = bp->b_addr;
+	iocur_top->bp = bp;
 
 	iocur_top->bb = d;
 	iocur_top->blen = c;
diff --git a/db/io.h b/db/io.h
index c7641d5..2c47ccc 100644
--- a/db/io.h
+++ b/db/io.h
@@ -36,8 +36,8 @@ typedef struct iocur {
 	__uint16_t		mode;	/* current inode's mode */
 	xfs_off_t		off;	/* fs offset of "data" in bytes */
 	const struct typ	*typ;	/* type of "data" */
-	int			use_bbmap; /* set if bbmap is valid */
-	bbmap_t			bbmap;	/* map daddr if fragmented */
+	bbmap_t			*bbmap;	/* map daddr if fragmented */
+	struct xfs_buf		*bp;	/* underlying buffer */
 } iocur_t;
 
 #define DB_RING_ADD 1                   /* add to ring on set_cur */
-- 
1.8.4.rc3

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

  parent reply	other threads:[~2013-11-13  6:41 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-13  6:40 [PATCH 00/36 V5] xfsprogs: CRC write support for xfs_db + Dave Chinner
2013-11-13  6:40 ` [PATCH 01/36] xfsprogs: fix automatic dependency generation Dave Chinner
2013-11-13  6:40 ` [PATCH 02/36] xfs: fix some minor sparse warnings Dave Chinner
2013-11-13  6:40 ` [PATCH 03/36] xfs: create a shared header file for format-related information Dave Chinner
2013-11-13  6:40 ` [PATCH 04/36] xfs: split dquot buffer operations out Dave Chinner
2013-11-13  6:40 ` [PATCH 05/36] xfs: decouple inode and bmap btree header files Dave Chinner
2013-11-13  6:40 ` [PATCH 06/36] libxfs: unify xfs_btree.c with kernel code Dave Chinner
2013-11-13  6:40 ` [PATCH 07/36] libxfs: bmap btree owner swap support Dave Chinner
2013-11-13  6:40 ` [PATCH 08/36] libxfs: xfs_rtalloc.c becomes xfs_rtbitmap.c Dave Chinner
2013-11-13  6:40 ` [PATCH 09/36] libxfs: bring across inode buffer readahead verifier changes Dave Chinner
2013-11-13  6:40 ` [PATCH 10/36] libxfs: Minor cleanup and bug fix sync Dave Chinner
2013-11-13  6:40 ` [PATCH 11/36] xfs: remove newlines from strings passed to __xfs_printk Dave Chinner
2013-11-13  6:40 ` [PATCH 12/36] xfs: fix the wrong new_size/rnew_size at xfs_iext_realloc_direct() Dave Chinner
2013-11-13  6:40 ` [PATCH 13/36] xfs: fix node forward in xfs_node_toosmall Dave Chinner
2013-11-13  6:40 ` [PATCH 14/36] xfs: don't emit corruption noise on fs probes Dave Chinner
2013-11-13  6:40 ` [PATCH 15/36] libxfs: fix root inode handling inconsistencies Dave Chinner
2013-11-13  6:40 ` [PATCH 16/36] libxfs: stop caching inode structures Dave Chinner
2013-11-13  6:40 ` [PATCH 17/36] db: separate out straight buffer IO from map based IO Dave Chinner
2013-11-13  6:40 ` [PATCH 18/36] db: rewrite bbmap to use xfs_buf_map Dave Chinner
2013-11-13  6:40 ` [PATCH 19/36] libxfs: refactor libxfs_buf_read_map for xfs_db Dave Chinner
2013-11-13  6:40 ` Dave Chinner [this message]
2013-11-13 16:05   ` [PATCH 20/36] db: rewrite IO engine to use libxfs Christoph Hellwig
2013-11-13  6:40 ` [PATCH 21/36] db: introduce verifier support into set_cur Dave Chinner
2013-11-13  6:40 ` [PATCH 22/36] db: indicate if the CRC on a buffer is correct or not Dave Chinner
2013-11-13  6:40 ` [PATCH 23/36] db: verify and calculate inode CRCs Dave Chinner
2013-11-13  6:40 ` [PATCH 24/36] db: verify and calculate dquot CRCs Dave Chinner
2013-11-13 16:05   ` Christoph Hellwig
2013-11-13  6:40 ` [PATCH 25/36] db: add a special directory buffer verifier Dave Chinner
2013-11-13  6:40 ` [PATCH 26/36] db: add a special attribute " Dave Chinner
2013-11-13  6:40 ` [PATCH 27/36] db: re-enable write support for v5 filesystems Dave Chinner
2013-11-13  6:40 ` [PATCH 28/36] xfs_db: use inode cluster buffers for inode IO Dave Chinner
2013-11-13  6:40 ` [PATCH 29/36] xfs_db: avoid libxfs buffer lookup warnings Dave Chinner
2013-11-13  6:40 ` [PATCH 30/36] libxfs: work around do_div() not handling 32 bit numerators Dave Chinner
2013-11-13  6:40 ` [PATCH 31/36] db: enable metadump on CRC filesystems Dave Chinner
2013-11-13 16:09   ` Christoph Hellwig
2013-11-13 21:00     ` Dave Chinner
2013-11-14 13:34       ` Christoph Hellwig
2013-11-13  6:40 ` [PATCH 32/36] xfs: support larger inode clusters on v5 filesystems Dave Chinner
2013-11-13  6:40 ` [PATCH 33/36] xfsprogs: kill experimental warnings for " Dave Chinner
2013-11-13  6:40 ` [PATCH 34/36] repair: prefetching is turned off unnecessarily Dave Chinner
2013-11-13  6:40 ` [PATCH 35/36] repair: Increase default repair parallelism on large filesystems Dave Chinner
2013-11-13 16:10   ` Christoph Hellwig
2013-11-13 21:01     ` Dave Chinner
2013-11-13  6:41 ` [PATCH 36/36] repair: fix leaf node directory data check Dave Chinner
2013-11-14 16:18 ` [PATCH 00/36 V5] xfsprogs: CRC write support for xfs_db + Rich Johnston

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=1384324860-25677-21-git-send-email-david@fromorbit.com \
    --to=david@fromorbit.com \
    --cc=xfs@oss.sgi.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox