Linux-NFS Archive on lore.kernel.org
 help / color / Atom feed
From: Jim Rees <rees@umich.edu>
To: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: linux-nfs@vger.kernel.org
Subject: [PATCH v1 18/25] pnfsblock: encode_layoutcommit
Date: Sun, 17 Jul 2011 19:59:05 -0400
Message-ID: <1310947152-12255-19-git-send-email-rees@umich.edu> (raw)
In-Reply-To: <1310947152-12255-1-git-send-email-rees@umich.edu>

From: Fred Isaman <iisaman@citi.umich.edu>

In blocklayout driver. There are two things happening
while layoutcommit/cleanup.
1. the modified extents are encoded.
2. On cleanup the extents are put back on the layout rw
   extents list, for reads.

In the new system where actual xdr encoding is done in
encode_layoutcommit() directly into xdr buffer, these are
the new commit stages:

1. On setup_layoutcommit, the range is adjusted as before
   and a structure is allocated for communication with
   bl_encode_layoutcommit && bl_cleanup_layoutcommit
   (Generic layer provides a void-star to hang it on)

2. bl_encode_layoutcommit is called to do the actual
   encoding directly into xdr. The commit-extent-list is not
   freed and is stored on above structure.
   FIXME: The code is not yet converted to the new XDR cleanup

3. On cleanup the commit-extent-list is put back by a call
   to set_to_rw() as before, but with no need for XDR decoding
   of the list as before. And the commit-extent-list is freed.
   Finally allocated structure is freed.

[pnfsblock: get rid of deprecated xdr macros]
Signed-off-by: Jim Rees <rees@umich.edu>
[pnfsblock: SQUASHME: port block layout code]
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
[blocklayout: encode_layoutcommit implementation]
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
[pnfsblock: fix bug setting up layoutcommit.]
Signed-off-by: Tao Guo <guotao-U4AKAne5IzAR5TUyvShJeg@public.gmane.org>
[pnfsblock: prevent commit list corruption]
[pnfsblock: fix layoutcommit with an empty opaque]
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <benny@tonian.com>
---
 fs/nfs/blocklayout/blocklayout.c |    2 +
 fs/nfs/blocklayout/blocklayout.h |   12 +++
 fs/nfs/blocklayout/extents.c     |  174 ++++++++++++++++++++++++++++----------
 3 files changed, 144 insertions(+), 44 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 01d85cf..79e147a 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -156,6 +156,8 @@ static void
 bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
 		       const struct nfs4_layoutcommit_args *arg)
 {
+	dprintk("%s enter\n", __func__);
+	encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg);
 }
 
 static void
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index fa3d51d..c526564 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -134,6 +134,15 @@ struct pnfs_block_extent {
 	struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */
 };
 
+/* Shortened extent used by LAYOUTCOMMIT */
+struct pnfs_block_short_extent {
+	struct list_head bse_node;
+	struct nfs4_deviceid bse_devid;	/* STUB - removable??? */
+	struct block_device *bse_mdev;
+	sector_t	bse_f_offset;	/* the starting offset in the file */
+	sector_t	bse_length;	/* the size of the extent */
+};
+
 static inline void
 INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize)
 {
@@ -229,6 +238,9 @@ void bl_put_extent(struct pnfs_block_extent *be);
 struct pnfs_block_extent *alloc_extent(void);
 struct pnfs_block_extent *get_extent(struct pnfs_block_extent *be);
 int is_sector_initialized(struct pnfs_inval_markings *marks, sector_t isect);
+int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+				   struct xdr_stream *xdr,
+				   const struct nfs4_layoutcommit_args *arg);
 int bl_add_merge_extent(struct pnfs_block_layout *bl,
 			 struct pnfs_block_extent *new);
 
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 2bc901b..d2cf22d 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -286,6 +286,47 @@ int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
 	return -ENOMEM;
 }
 
+/* Marks sectors in [offest, offset+length) as having been written to disk.
+ * All lengths should be block aligned.
+ */
+int mark_written_sectors(struct pnfs_inval_markings *marks,
+			 sector_t offset, sector_t length)
+{
+	int status;
+
+	dprintk("%s(offset=%llu,len=%llu) enter\n", __func__,
+		(u64)offset, (u64)length);
+	spin_lock(&marks->im_lock);
+	status = _set_range(&marks->im_tree, EXTENT_WRITTEN, offset, length);
+	spin_unlock(&marks->im_lock);
+	return status;
+}
+
+static void print_short_extent(struct pnfs_block_short_extent *be)
+{
+	dprintk("PRINT SHORT EXTENT extent %p\n", be);
+	if (be) {
+		dprintk("        be_f_offset %llu\n", (u64)be->bse_f_offset);
+		dprintk("        be_length   %llu\n", (u64)be->bse_length);
+	}
+}
+
+void print_clist(struct list_head *list, unsigned int count)
+{
+	struct pnfs_block_short_extent *be;
+	unsigned int i = 0;
+
+	dprintk("****************\n");
+	dprintk("Extent list looks like:\n");
+	list_for_each_entry(be, list, bse_node) {
+		i++;
+		print_short_extent(be);
+	}
+	if (i != count)
+		dprintk("\n\nExpected %u entries\n\n\n", count);
+	dprintk("****************\n");
+}
+
 static void print_bl_extent(struct pnfs_block_extent *be)
 {
 	dprintk("PRINT EXTENT extent %p\n", be);
@@ -386,65 +427,67 @@ bl_add_merge_extent(struct pnfs_block_layout *bl,
 	/* Scan for proper place to insert, extending new to the left
 	 * as much as possible.
 	 */
-	list_for_each_entry_safe(be, tmp, list, be_node) {
-		if (new->be_f_offset < be->be_f_offset)
+	list_for_each_entry_safe_reverse(be, tmp, list, be_node) {
+		if (new->be_f_offset >= be->be_f_offset + be->be_length)
 			break;
-		if (end <= be->be_f_offset + be->be_length) {
-			/* new is a subset of existing be*/
+		if (new->be_f_offset >= be->be_f_offset) {
+			if (end <= be->be_f_offset + be->be_length) {
+				/* new is a subset of existing be*/
+				if (extents_consistent(be, new)) {
+					dprintk("%s: new is subset, ignoring\n",
+						__func__);
+					bl_put_extent(new);
+					return 0;
+				} else {
+					goto out_err;
+				}
+			} else {
+				/* |<--   be   -->|
+				 *          |<--   new   -->| */
+				if (extents_consistent(be, new)) {
+					/* extend new to fully replace be */
+					new->be_length += new->be_f_offset -
+						be->be_f_offset;
+					new->be_f_offset = be->be_f_offset;
+					new->be_v_offset = be->be_v_offset;
+					dprintk("%s: removing %p\n", __func__, be);
+					list_del(&be->be_node);
+					bl_put_extent(be);
+				} else {
+					goto out_err;
+				}
+			}
+		} else if (end >= be->be_f_offset + be->be_length) {
+			/* new extent overlap existing be */
 			if (extents_consistent(be, new)) {
-				dprintk("%s: new is subset, ignoring\n",
-					__func__);
-				bl_put_extent(new);
-				return 0;
-			} else
+				/* extend new to fully replace be */
+				dprintk("%s: removing %p\n", __func__, be);
+				list_del(&be->be_node);
+				bl_put_extent(be);
+			} else {
 				goto out_err;
-		} else if (new->be_f_offset <=
-				be->be_f_offset + be->be_length) {
-			/* new overlaps or abuts existing be */
-			if (extents_consistent(be, new)) {
+			}
+		} else if (end > be->be_f_offset) {
+			/*           |<--   be   -->|
+			 *|<--   new   -->| */
+			if (extents_consistent(new, be)) {
 				/* extend new to fully replace be */
-				new->be_length += new->be_f_offset -
-						  be->be_f_offset;
-				new->be_f_offset = be->be_f_offset;
-				new->be_v_offset = be->be_v_offset;
+				new->be_length += be->be_f_offset + be->be_length -
+					new->be_f_offset - new->be_length;
 				dprintk("%s: removing %p\n", __func__, be);
 				list_del(&be->be_node);
 				bl_put_extent(be);
-			} else if (new->be_f_offset !=
-				   be->be_f_offset + be->be_length)
+			} else {
 				goto out_err;
+			}
 		}
 	}
 	/* Note that if we never hit the above break, be will not point to a
 	 * valid extent.  However, in that case &be->be_node==list.
 	 */
-	list_add_tail(&new->be_node, &be->be_node);
+	list_add(&new->be_node, &be->be_node);
 	dprintk("%s: inserting new\n", __func__);
 	print_elist(list);
-	/* Scan forward for overlaps.  If we find any, extend new and
-	 * remove the overlapped extent.
-	 */
-	be = list_prepare_entry(new, list, be_node);
-	list_for_each_entry_safe_continue(be, tmp, list, be_node) {
-		if (end < be->be_f_offset)
-			break;
-		/* new overlaps or abuts existing be */
-		if (extents_consistent(be, new)) {
-			if (end < be->be_f_offset + be->be_length) {
-				/* extend new to fully cover be */
-				end = be->be_f_offset + be->be_length;
-				new->be_length = end - new->be_f_offset;
-			}
-			dprintk("%s: removing %p\n", __func__, be);
-			list_del(&be->be_node);
-			bl_put_extent(be);
-		} else if (end != be->be_f_offset) {
-			list_del(&new->be_node);
-			goto out_err;
-		}
-	}
-	dprintk("%s: after merging\n", __func__);
-	print_elist(list);
 	/* STUB - The per-list consistency checks have all been done,
 	 * should now check cross-list consistency.
 	 */
@@ -502,6 +545,49 @@ bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
 	return ret;
 }
 
+int
+encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+			       struct xdr_stream *xdr,
+			       const struct nfs4_layoutcommit_args *arg)
+{
+	struct pnfs_block_short_extent *lce, *save;
+	unsigned int count = 0;
+	__be32 *p, *xdr_start;
+
+	dprintk("%s enter\n", __func__);
+	/* BUG - creation of bl_commit is buggy - need to wait for
+	 * entire block to be marked WRITTEN before it can be added.
+	 */
+	spin_lock(&bl->bl_ext_lock);
+	/* Want to adjust for possible truncate */
+	/* We now want to adjust argument range */
+
+	/* XDR encode the ranges found */
+	xdr_start = xdr_reserve_space(xdr, 8);
+	if (!xdr_start)
+		goto out;
+	list_for_each_entry_safe(lce, save, &bl->bl_commit, bse_node) {
+		p = xdr_reserve_space(xdr, 7 * 4 + sizeof(lce->bse_devid.data));
+		if (!p)
+			break;
+		p = xdr_encode_opaque_fixed(p, lce->bse_devid.data, NFS4_DEVICEID4_SIZE);
+		p = xdr_encode_hyper(p, lce->bse_f_offset << SECTOR_SHIFT);
+		p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT);
+		p = xdr_encode_hyper(p, 0LL);
+		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
+		list_del(&lce->bse_node);
+		list_add_tail(&lce->bse_node, &bl->bl_committing);
+		bl->bl_count--;
+		count++;
+	}
+	xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4);
+	xdr_start[1] = cpu_to_be32(count);
+out:
+	spin_unlock(&bl->bl_ext_lock);
+	dprintk("%s found %i ranges\n", __func__, count);
+	return 0;
+}
+
 /* Helper function to set_to_rw that initialize a new extent */
 static void
 _prep_new_extent(struct pnfs_block_extent *new,
-- 
1.7.4.1


  parent reply index

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-17 23:58 [PATCH v1 00/25] add block layout driver to pnfs client Jim Rees
2011-07-17 23:58 ` [PATCH v1 01/25] pnfs: GETDEVICELIST Jim Rees
2011-07-17 23:58 ` [PATCH v1 02/25] pnfs: add set-clear layoutdriver interface Jim Rees
2011-07-17 23:58 ` [PATCH v1 03/25] NFS41: Let layoutcommit handle multiple segments Jim Rees
2011-07-17 23:58 ` [PATCH v1 04/25] NFS41: save layoutcommit cred after first successful layoutget Jim Rees
2011-07-17 23:58 ` [PATCH v1 05/25] pnfs: ask for layout_blksize and save it in nfs_server Jim Rees
2011-07-17 23:58 ` [PATCH v1 06/25] pnfs: cleanup_layoutcommit Jim Rees
2011-07-17 23:58 ` [PATCH v1 07/25] pnfsblock: add blocklayout Kconfig option, Makefile, and stubs Jim Rees
2011-07-17 23:58 ` [PATCH v1 08/25] pnfsblock: basic extent code Jim Rees
2011-07-17 23:58 ` [PATCH v1 09/25] pnfsblock: add device operations Jim Rees
2011-07-17 23:58 ` [PATCH v1 10/25] pnfsblock: remove " Jim Rees
2011-07-17 23:58 ` [PATCH v1 11/25] pnfsblock: lseg alloc and free Jim Rees
2011-07-17 23:58 ` [PATCH v1 12/25] pnfsblock: merge extents Jim Rees
2011-07-17 23:59 ` [PATCH v1 13/25] pnfsblock: call and parse getdevicelist Jim Rees
2011-07-17 23:59 ` [PATCH v1 14/25] pnfsblock: xdr decode pnfs_block_layout4 Jim Rees
2011-07-17 23:59 ` [PATCH v1 15/25] pnfsblock: bl_find_get_extent Jim Rees
2011-07-17 23:59 ` [PATCH v1 16/25] pnfsblock: add extent manipulation functions Jim Rees
2011-07-17 23:59 ` [PATCH v1 17/25] pnfsblock: merge rw extents Jim Rees
2011-07-17 23:59 ` Jim Rees [this message]
2011-07-17 23:59 ` [PATCH v1 19/25] pnfsblock: cleanup_layoutcommit Jim Rees
2011-07-17 23:59 ` [PATCH v1 20/25] pnfsblock: bl_read_pagelist Jim Rees
2011-07-17 23:59 ` [PATCH v1 21/25] pnfsblock: bl_write_pagelist Jim Rees
2011-07-17 23:59 ` [PATCH v1 22/25] pnfsblock: note written INVAL areas for layoutcommit Jim Rees
2011-07-17 23:59 ` [PATCH v1 23/25] pnfsblock: Implement release_inval_marks Jim Rees
2011-07-17 23:59 ` [PATCH v1 24/25] pnfsblock: use pageio_ops api Jim Rees
2011-07-17 23:59 ` [PATCH v1 25/25] pnfsblock: write_pagelist handle zero invalid extents Jim Rees

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=1310947152-12255-19-git-send-email-rees@umich.edu \
    --to=rees@umich.edu \
    --cc=Trond.Myklebust@netapp.com \
    --cc=linux-nfs@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

Linux-NFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nfs/0 linux-nfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nfs linux-nfs/ https://lore.kernel.org/linux-nfs \
		linux-nfs@vger.kernel.org
	public-inbox-index linux-nfs

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-nfs


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git