All of lore.kernel.org
 help / color / mirror / 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 22/25] pnfsblock: note written INVAL areas for layoutcommit
Date: Thu, 21 Jul 2011 15:34:22 -0400	[thread overview]
Message-ID: <1311276865-29484-23-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>

[SQUASHME: pnfs: blocklayout: port block layout code]
Signed-off-by: Peng Tao <peng_tao@emc.com>
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 |   32 +++++++++++++
 fs/nfs/blocklayout/blocklayout.h |    2 +
 fs/nfs/blocklayout/extents.c     |   95 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 129 insertions(+), 0 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 6d6ac0e..16214df 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -346,6 +346,30 @@ out:
 	return PNFS_NOT_ATTEMPTED;
 }
 
+static void mark_extents_written(struct pnfs_block_layout *bl,
+				 __u64 offset, __u32 count)
+{
+	sector_t isect, end;
+	struct pnfs_block_extent *be;
+
+	dprintk("%s(%llu, %u)\n", __func__, offset, count);
+	if (count == 0)
+		return;
+	isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT;
+	end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK);
+	end >>= SECTOR_SHIFT;
+	while (isect < end) {
+		sector_t len;
+		be = bl_find_get_extent(bl, isect, NULL);
+		BUG_ON(!be); /* FIXME */
+		len = min(end, be->be_f_offset + be->be_length) - isect;
+		if (be->be_state == PNFS_BLOCK_INVALID_DATA)
+			mark_for_commit(be, isect, len); /* What if fails? */
+		isect += len;
+		bl_put_extent(be);
+	}
+}
+
 /* This is basically copied from mpage_end_io_read */
 static void bl_end_io_write(struct bio *bio, int err)
 {
@@ -372,6 +396,14 @@ static void bl_write_cleanup(struct work_struct *work)
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
 	wdata = container_of(task, struct nfs_write_data, task);
+	if (!wdata->task.tk_status) {
+		/* Marks for LAYOUTCOMMIT */
+		/* BUG - this should be called after each bio, not after
+		 * all finish, unless have some way of storing success/failure
+		 */
+		mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+				     wdata->args.offset, wdata->args.count);
+	}
 	pnfs_ld_write_done(wdata);
 }
 
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 197f919..52986cc 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -202,5 +202,7 @@ void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
 				   int status);
 int bl_add_merge_extent(struct pnfs_block_layout *bl,
 			 struct pnfs_block_extent *new);
+int mark_for_commit(struct pnfs_block_extent *be,
+		    sector_t offset, sector_t length);
 
 #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 483c235..a5c2851 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -217,6 +217,48 @@ int is_sector_initialized(struct pnfs_inval_markings *marks, sector_t isect)
 	return rv;
 }
 
+/* Assume start, end already sector aligned */
+static int
+_range_has_tag(struct my_tree *tree, u64 start, u64 end, int32_t tag)
+{
+	struct pnfs_inval_tracking *pos;
+	u64 expect = 0;
+
+	dprintk("%s(%llu, %llu, %i) enter\n", __func__, start, end, tag);
+	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
+		if (pos->it_sector >= end)
+			continue;
+		if (!expect) {
+			if ((pos->it_sector == end - tree->mtt_step_size) &&
+			    (pos->it_tags & (1 << tag))) {
+				expect = pos->it_sector - tree->mtt_step_size;
+				if (pos->it_sector < tree->mtt_step_size || expect < start)
+					return 1;
+				continue;
+			} else {
+				return 0;
+			}
+		}
+		if (pos->it_sector != expect || !(pos->it_tags & (1 << tag)))
+			return 0;
+		expect -= tree->mtt_step_size;
+		if (expect < start)
+			return 1;
+	}
+	return 0;
+}
+
+static int is_range_written(struct pnfs_inval_markings *marks,
+			    sector_t start, sector_t end)
+{
+	int rv;
+
+	spin_lock(&marks->im_lock);
+	rv = _range_has_tag(&marks->im_tree, start, end, EXTENT_WRITTEN);
+	spin_unlock(&marks->im_lock);
+	return rv;
+}
+
 /* Marks sectors in [offest, offset_length) as having been initialized.
  * All lengths are step-aligned, where step is min(pagesize, blocksize).
  * Notes where partial block is initialized, and helps prepare it for
@@ -396,6 +438,59 @@ static void add_to_commitlist(struct pnfs_block_layout *bl,
 	print_clist(clist, bl->bl_count);
 }
 
+/* Note the range described by offset, length is guaranteed to be contained
+ * within be.
+ */
+int mark_for_commit(struct pnfs_block_extent *be,
+		    sector_t offset, sector_t length)
+{
+	sector_t new_end, end = offset + length;
+	struct pnfs_block_short_extent *new;
+	struct pnfs_block_layout *bl = container_of(be->be_inval,
+						    struct pnfs_block_layout,
+						    bl_inval);
+
+	new = kmalloc(sizeof(*new), GFP_NOFS);
+	if (!new)
+		return -ENOMEM;
+
+	mark_written_sectors(be->be_inval, offset, length);
+	/* We want to add the range to commit list, but it must be
+	 * block-normalized, and verified that the normalized range has
+	 * been entirely written to disk.
+	 */
+	new->bse_f_offset = offset;
+	offset = normalize(offset, bl->bl_blocksize);
+	if (offset < new->bse_f_offset) {
+		if (is_range_written(be->be_inval, offset, new->bse_f_offset))
+			new->bse_f_offset = offset;
+		else
+			new->bse_f_offset = offset + bl->bl_blocksize;
+	}
+	new_end = normalize_up(end, bl->bl_blocksize);
+	if (end < new_end) {
+		if (is_range_written(be->be_inval, end, new_end))
+			end = new_end;
+		else
+			end = new_end - bl->bl_blocksize;
+	}
+	if (end <= new->bse_f_offset) {
+		kfree(new);
+		return 0;
+	}
+	new->bse_length = end - new->bse_f_offset;
+	new->bse_devid = be->be_devid;
+	new->bse_mdev = be->be_mdev;
+
+	spin_lock(&bl->bl_ext_lock);
+	/* new will be freed, either by add_to_commitlist if it decides not
+	 * to use it, or after LAYOUTCOMMIT uses it in the commitlist.
+	 */
+	add_to_commitlist(bl, new);
+	spin_unlock(&bl->bl_ext_lock);
+	return 0;
+}
+
 static void print_bl_extent(struct pnfs_block_extent *be)
 {
 	dprintk("PRINT EXTENT extent %p\n", be);
-- 
1.7.4.1


  parent reply	other threads:[~2011-07-21 19:34 UTC|newest]

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 ` [PATCH v2 19/25] pnfsblock: cleanup_layoutcommit Jim Rees
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 ` Jim Rees [this message]
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=1311276865-29484-23-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
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.