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, peter honeyman <honey@citi.umich.edu>
Subject: [PATCH v2 19/25] pnfsblock: cleanup_layoutcommit
Date: Thu, 21 Jul 2011 15:34:19 -0400
Message-ID: <1311276865-29484-20-git-send-email-rees@umich.edu> (raw)
In-Reply-To: <1311276865-29484-1-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.

[SQUASHME: pnfs: blocklayout: port block layout code]
Signed-off-by: Peng Tao <peng_tao@emc.com>
[pnfsblock: SQUASHME: adjust to API change]
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@nrchpc.ac.cn>
[pnfsblock: cleanup_layoutcommit wants a status parameter]
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
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 |    3 +
 fs/nfs/blocklayout/extents.c     |  210 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 215 insertions(+), 0 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 36fd19c..300a678 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -168,6 +168,8 @@ static void
 bl_cleanup_layoutcommit(struct pnfs_layout_hdr *lo,
 			struct nfs4_layoutcommit_data *lcdata)
 {
+	dprintk("%s enter\n", __func__);
+	clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status);
 }
 
 static void free_blk_mountid(struct block_mount_id *mid)
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index edbe6a9..197f919 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -197,6 +197,9 @@ 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);
+void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+				   const struct nfs4_layoutcommit_args *arg,
+				   int status);
 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 462a270..483c235 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -329,6 +329,73 @@ void print_clist(struct list_head *list, unsigned int count)
 	}
 }
 
+/* Note: In theory, we should do more checking that devid's match between
+ * old and new, but if they don't, the lists are too corrupt to salvage anyway.
+ */
+/* Note this is very similar to bl_add_merge_extent */
+static void add_to_commitlist(struct pnfs_block_layout *bl,
+			      struct pnfs_block_short_extent *new)
+{
+	struct list_head *clist = &bl->bl_commit;
+	struct pnfs_block_short_extent *old, *save;
+	sector_t end = new->bse_f_offset + new->bse_length;
+
+	dprintk("%s enter\n", __func__);
+	print_short_extent(new);
+	print_clist(clist, bl->bl_count);
+	bl->bl_count++;
+	/* Scan for proper place to insert, extending new to the left
+	 * as much as possible.
+	 */
+	list_for_each_entry_safe(old, save, clist, bse_node) {
+		if (new->bse_f_offset < old->bse_f_offset)
+			break;
+		if (end <= old->bse_f_offset + old->bse_length) {
+			/* Range is already in list */
+			bl->bl_count--;
+			kfree(new);
+			return;
+		} else if (new->bse_f_offset <=
+				old->bse_f_offset + old->bse_length) {
+			/* new overlaps or abuts existing be */
+			if (new->bse_mdev == old->bse_mdev) {
+				/* extend new to fully replace old */
+				new->bse_length += new->bse_f_offset -
+						old->bse_f_offset;
+				new->bse_f_offset = old->bse_f_offset;
+				list_del(&old->bse_node);
+				bl->bl_count--;
+				kfree(old);
+			}
+		}
+	}
+	/* Note that if we never hit the above break, old will not point to a
+	 * valid extent.  However, in that case &old->bse_node==list.
+	 */
+	list_add_tail(&new->bse_node, &old->bse_node);
+	/* Scan forward for overlaps.  If we find any, extend new and
+	 * remove the overlapped extent.
+	 */
+	old = list_prepare_entry(new, clist, bse_node);
+	list_for_each_entry_safe_continue(old, save, clist, bse_node) {
+		if (end < old->bse_f_offset)
+			break;
+		/* new overlaps or abuts old */
+		if (new->bse_mdev == old->bse_mdev) {
+			if (end < old->bse_f_offset + old->bse_length) {
+				/* extend new to fully cover old */
+				end = old->bse_f_offset + old->bse_length;
+				new->bse_length = end - new->bse_f_offset;
+			}
+			list_del(&old->bse_node);
+			bl->bl_count--;
+			kfree(old);
+		}
+	}
+	dprintk("%s: after merging\n", __func__);
+	print_clist(clist, bl->bl_count);
+}
+
 static void print_bl_extent(struct pnfs_block_extent *be)
 {
 	dprintk("PRINT EXTENT extent %p\n", be);
@@ -547,6 +614,34 @@ bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
 	return ret;
 }
 
+/* Similar to bl_find_get_extent, but called with lock held, and ignores cow */
+static struct pnfs_block_extent *
+bl_find_get_extent_locked(struct pnfs_block_layout *bl, sector_t isect)
+{
+	struct pnfs_block_extent *be, *ret = NULL;
+	int i;
+
+	dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
+	for (i = 0; i < EXTENT_LISTS; i++) {
+		if (ret)
+			break;
+		list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
+			if (isect >= be->be_f_offset + be->be_length)
+				break;
+			if (isect >= be->be_f_offset) {
+				/* We have found an extent */
+				dprintk("%s Get %p (%i)\n", __func__, be,
+					atomic_read(&be->be_refcnt.refcount));
+				kref_get(&be->be_refcnt);
+				ret = be;
+				break;
+			}
+		}
+	}
+	print_bl_extent(ret);
+	return ret;
+}
+
 int
 encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
 			       struct xdr_stream *xdr,
@@ -636,3 +731,118 @@ _front_merge(struct pnfs_block_extent *be, struct list_head *head,
 	kfree(storage);
 	return be;
 }
+
+static u64
+set_to_rw(struct pnfs_block_layout *bl, u64 offset, u64 length)
+{
+	u64 rv = offset + length;
+	struct pnfs_block_extent *be, *e1, *e2, *e3, *new, *old;
+	struct pnfs_block_extent *children[3];
+	struct pnfs_block_extent *merge1 = NULL, *merge2 = NULL;
+	int i = 0, j;
+
+	dprintk("%s(%llu, %llu)\n", __func__, offset, length);
+	/* Create storage for up to three new extents e1, e2, e3 */
+	e1 = kmalloc(sizeof(*e1), GFP_ATOMIC);
+	e2 = kmalloc(sizeof(*e2), GFP_ATOMIC);
+	e3 = kmalloc(sizeof(*e3), GFP_ATOMIC);
+	/* BUG - we are ignoring any failure */
+	if (!e1 || !e2 || !e3)
+		goto out_nosplit;
+
+	spin_lock(&bl->bl_ext_lock);
+	be = bl_find_get_extent_locked(bl, offset);
+	rv = be->be_f_offset + be->be_length;
+	if (be->be_state != PNFS_BLOCK_INVALID_DATA) {
+		spin_unlock(&bl->bl_ext_lock);
+		goto out_nosplit;
+	}
+	/* Add e* to children, bumping e*'s krefs */
+	if (be->be_f_offset != offset) {
+		_prep_new_extent(e1, be, be->be_f_offset,
+				 offset - be->be_f_offset,
+				 PNFS_BLOCK_INVALID_DATA);
+		children[i++] = e1;
+		print_bl_extent(e1);
+	} else
+		merge1 = e1;
+	_prep_new_extent(e2, be, offset,
+			 min(length, be->be_f_offset + be->be_length - offset),
+			 PNFS_BLOCK_READWRITE_DATA);
+	children[i++] = e2;
+	print_bl_extent(e2);
+	if (offset + length < be->be_f_offset + be->be_length) {
+		_prep_new_extent(e3, be, e2->be_f_offset + e2->be_length,
+				 be->be_f_offset + be->be_length -
+				 offset - length,
+				 PNFS_BLOCK_INVALID_DATA);
+		children[i++] = e3;
+		print_bl_extent(e3);
+	} else
+		merge2 = e3;
+
+	/* Remove be from list, and insert the e* */
+	/* We don't get refs on e*, since this list is the base reference
+	 * set when init'ed.
+	 */
+	if (i < 3)
+		children[i] = NULL;
+	new = children[0];
+	list_replace(&be->be_node, &new->be_node);
+	bl_put_extent(be);
+	new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge1);
+	for (j = 1; j < i; j++) {
+		old = new;
+		new = children[j];
+		list_add(&new->be_node, &old->be_node);
+	}
+	if (merge2) {
+		/* This is a HACK, should just create a _back_merge function */
+		new = list_entry(new->be_node.next,
+				 struct pnfs_block_extent, be_node);
+		new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge2);
+	}
+	spin_unlock(&bl->bl_ext_lock);
+
+	/* Since we removed the base reference above, be is now scheduled for
+	 * destruction.
+	 */
+	bl_put_extent(be);
+	dprintk("%s returns %llu after split\n", __func__, rv);
+	return rv;
+
+ out_nosplit:
+	kfree(e1);
+	kfree(e2);
+	kfree(e3);
+	dprintk("%s returns %llu without splitting\n", __func__, rv);
+	return rv;
+}
+
+void
+clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+			      const struct nfs4_layoutcommit_args *arg,
+			      int status)
+{
+	struct pnfs_block_short_extent *lce, *save;
+
+	dprintk("%s status %d\n", __func__, status);
+	list_for_each_entry_safe(lce, save, &bl->bl_committing, bse_node) {
+		if (likely(!status)) {
+			u64 offset = lce->bse_f_offset;
+			u64 end = offset + lce->bse_length;
+
+			do {
+				offset = set_to_rw(bl, offset, end - offset);
+			} while (offset < end);
+			list_del(&lce->bse_node);
+
+			kfree(lce);
+		} else {
+			list_del(&lce->bse_node);
+			spin_lock(&bl->bl_ext_lock);
+			add_to_commitlist(bl, lce);
+			spin_unlock(&bl->bl_ext_lock);
+		}
+	}
+}
-- 
1.7.4.1


  parent reply index

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-21 19:34 [PATCH v2 00/25] add block layout driver to pnfs client Jim Rees
2011-07-21 19:34 ` [PATCH v2 01/25] pnfs: GETDEVICELIST Jim Rees
2011-07-21 19:34 ` [PATCH v2 02/25] pnfs: add set-clear layoutdriver interface Jim Rees
2011-07-21 19:34 ` [PATCH v2 03/25] NFS41: Let layoutcommit handle multiple segments Jim Rees
2011-07-21 19:34 ` [PATCH v2 04/25] NFS41: save layoutcommit cred after first successful layoutget Jim Rees
2011-07-21 19:34 ` [PATCH v2 05/25] pnfs: ask for layout_blksize and save it in nfs_server Jim Rees
2011-07-25 14:24   ` Benny Halevy
2011-07-21 19:34 ` [PATCH v2 06/25] pnfs: cleanup_layoutcommit Jim Rees
2011-07-25 14:26   ` Benny Halevy
2011-07-21 19:34 ` [PATCH v2 07/25] pnfsblock: add blocklayout Kconfig option, Makefile, and stubs Jim Rees
2011-07-25 14:30   ` Benny Halevy
2011-07-25 14:38     ` Myklebust, Trond
2011-07-25 14:50       ` Benny Halevy
2011-07-25 17:25         ` Myklebust, Trond
2011-07-25 18:26           ` Benny Halevy
2011-07-26 17:18             ` Peng Tao
2011-07-21 19:34 ` [PATCH v2 08/25] pnfsblock: basic extent code Jim Rees
2011-07-21 19:34 ` [PATCH v2 09/25] pnfsblock: add device operations Jim Rees
2011-07-21 19:34 ` [PATCH v2 10/25] pnfsblock: remove " Jim Rees
2011-07-21 19:34 ` [PATCH v2 11/25] pnfsblock: lseg alloc and free Jim Rees
2011-07-25 14:43   ` Benny Halevy
2011-07-21 19:34 ` [PATCH v2 12/25] pnfsblock: merge extents Jim Rees
2011-07-21 19:34 ` [PATCH v2 13/25] pnfsblock: call and parse getdevicelist Jim Rees
2011-07-21 19:34 ` [PATCH v2 14/25] pnfsblock: xdr decode pnfs_block_layout4 Jim Rees
2011-07-21 19:34 ` [PATCH v2 15/25] pnfsblock: bl_find_get_extent Jim Rees
2011-07-21 19:34 ` [PATCH v2 16/25] pnfsblock: add extent manipulation functions Jim Rees
2011-07-21 19:34 ` [PATCH v2 17/25] pnfsblock: merge rw extents Jim Rees
2011-07-21 19:34 ` [PATCH v2 18/25] pnfsblock: encode_layoutcommit Jim Rees
2011-07-21 19:34 ` Jim Rees [this message]
2011-07-21 19:34 ` [PATCH v2 20/25] pnfsblock: bl_read_pagelist Jim Rees
2011-07-21 19:34 ` [PATCH v2 21/25] pnfsblock: bl_write_pagelist Jim Rees
2011-07-21 19:34 ` [PATCH v2 22/25] pnfsblock: note written INVAL areas for layoutcommit Jim Rees
2011-07-21 19:34 ` [PATCH v2 23/25] pnfsblock: use pageio_ops api Jim Rees
2011-07-21 19:34 ` [PATCH v2 24/25] pnfsblock: write_pagelist handle zero invalid extents Jim Rees
2011-07-21 19:34 ` [PATCH v2 25/25] NFS41: Drop lseg ref before fallthru to MDS 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=1311276865-29484-20-git-send-email-rees@umich.edu \
    --to=rees@umich.edu \
    --cc=Trond.Myklebust@netapp.com \
    --cc=honey@citi.umich.edu \
    --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