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 21/25] pnfsblock: bl_write_pagelist
Date: Sun, 17 Jul 2011 19:59:08 -0400
Message-ID: <1310947152-12255-22-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>

Note: When upper layer's read/write request cannot be fulfilled, the block
layout driver shouldn't silently mark the page as error. It should do
what can be done and  leave the rest to the upper layer. To do so, we
should set rdata/wdata->res.count properly.

When upper layer re-send the read/write request to finish the rest
part of the request, pgbase is the position where we should start at.

[pnfsblock: bl_write_pagelist support functions]
[pnfsblock: bl_write_pagelist adjust for missing PG_USE_PNFS]
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
[pnfsblock: handle errors when read or write pagelist.]
Signed-off-by: Zhang Jingwang <yyalone@gmail.com>
[pnfs-block: use new write_pagelist api]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <benny@tonian.com>

[SQUASHME: pnfsblock: mds_offset is set in the generic layer]
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
Signed-off-by: Benny Halevy <benny@tonian.com>

[pnfsblock: mark IO error with NFS_LAYOUT_{RW|RO}_FAILED]
Signed-off-by: Peng Tao <peng_tao@emc.com>
[pnfsblock: SQUASHME: adjust to API change]
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
[pnfsblock: fixup blksize alignment in bl_setup_layoutcommit]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <benny@tonian.com>
[pnfsblock: bl_write_pagelist adjust for missing PG_USE_PNFS]
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
[pnfsblock: handle errors when read or write pagelist.]
Signed-off-by: Zhang Jingwang <yyalone@gmail.com>
[pnfs-block: use new write_pagelist api]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <benny@tonian.com>
---
 fs/nfs/blocklayout/blocklayout.c |  134 +++++++++++++++++++++++++++++++++++++-
 1 files changed, 133 insertions(+), 1 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 282ef50..5db756f 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -75,6 +75,19 @@ static int is_hole(struct pnfs_block_extent *be, sector_t isect)
 		return !is_sector_initialized(be->be_inval, isect);
 }
 
+/* Given the be associated with isect, determine if page data can be
+ * written to disk.
+ */
+static int is_writable(struct pnfs_block_extent *be, sector_t isect)
+{
+	if (be->be_state == PNFS_BLOCK_READWRITE_DATA)
+		return 1;
+	else if (be->be_state != PNFS_BLOCK_INVALID_DATA)
+		return 0;
+	else
+		return is_sector_initialized(be->be_inval, isect);
+}
+
 static int
 dont_like_caller(struct nfs_page *req)
 {
@@ -334,11 +347,130 @@ out:
 	return PNFS_NOT_ATTEMPTED;
 }
 
+/* This is basically copied from mpage_end_io_read */
+static void bl_end_io_write(struct bio *bio, int err)
+{
+	struct parallel_io *par = bio->bi_private;
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+
+	if (!uptodate) {
+		if (!wdata->pnfs_error)
+			wdata->pnfs_error = -EIO;
+		bl_set_lo_fail(wdata->lseg);
+	}
+	bio_put(bio);
+	put_parallel(par);
+}
+
+/* Function scheduled for call during bl_end_par_io_write,
+ * it marks sectors as written and extends the commitlist.
+ */
+static void bl_write_cleanup(struct work_struct *work)
+{
+	struct rpc_task *task;
+	struct nfs_write_data *wdata;
+	dprintk("%s enter\n", __func__);
+	task = container_of(work, struct rpc_task, u.tk_work);
+	wdata = container_of(task, struct nfs_write_data, task);
+	pnfs_ld_write_done(wdata);
+}
+
+/* Called when last of bios associated with a bl_write_pagelist call finishes */
+static void
+bl_end_par_io_write(void *data)
+{
+	struct nfs_write_data *wdata = data;
+
+	/* STUB - ignoring error handling */
+	wdata->task.tk_status = 0;
+	wdata->verf.committed = NFS_FILE_SYNC;
+	INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
+	schedule_work(&wdata->task.u.tk_work);
+}
+
 static enum pnfs_try_status
 bl_write_pagelist(struct nfs_write_data *wdata,
 		  int sync)
 {
-	return PNFS_NOT_ATTEMPTED;
+	int i;
+	struct bio *bio = NULL;
+	struct pnfs_block_extent *be = NULL;
+	sector_t isect, extent_length = 0;
+	struct parallel_io *par;
+	loff_t offset = wdata->args.offset;
+	size_t count = wdata->args.count;
+	struct page **pages = wdata->args.pages;
+	int pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
+
+	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+	if (!wdata->lseg) {
+		dprintk("%s no lseg, falling back to MDS\n", __func__);
+		return PNFS_NOT_ATTEMPTED;
+	}
+	if (dont_like_caller(wdata->req)) {
+		dprintk("%s dont_like_caller failed\n", __func__);
+		return PNFS_NOT_ATTEMPTED;
+	}
+	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
+	 * We want to write each, and if there is an error remove it from
+	 * list and call
+	 * nfs_retry_request(req) to have it redone using nfs.
+	 * QUEST? Do as block or per req?  Think have to do per block
+	 * as part of end_bio
+	 */
+	par = alloc_parallel(wdata);
+	if (!par)
+		return PNFS_NOT_ATTEMPTED;
+	par->call_ops = *wdata->mds_ops;
+	par->call_ops.rpc_call_done = bl_rpc_do_nothing;
+	par->pnfs_callback = bl_end_par_io_write;
+	/* At this point, have to be more careful with error handling */
+
+	isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
+	for (i = pg_index; i < wdata->npages ; i++) {
+		if (!extent_length) {
+			/* We've used up the previous extent */
+			bl_put_extent(be);
+			bio = bl_submit_bio(WRITE, bio);
+			/* Get the next one */
+			be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg),
+					     isect, NULL);
+			if (!be || !is_writable(be, isect)) {
+				wdata->pnfs_error = -ENOMEM;
+				goto out;
+			}
+			extent_length = be->be_length -
+				(isect - be->be_f_offset);
+		}
+		for (;;) {
+			if (!bio) {
+				bio = bio_alloc(GFP_NOIO, wdata->npages - i);
+				if (!bio) {
+					wdata->pnfs_error = -ENOMEM;
+					goto out;
+				}
+				bio->bi_sector = isect - be->be_f_offset +
+					be->be_v_offset;
+				bio->bi_bdev = be->be_mdev;
+				bio->bi_end_io = bl_end_io_write;
+				bio->bi_private = par;
+			}
+			if (bio_add_page(bio, pages[i], PAGE_SIZE, 0))
+				break;
+			bio = bl_submit_bio(WRITE, bio);
+		}
+		isect += PAGE_CACHE_SECTORS;
+		extent_length -= PAGE_CACHE_SECTORS;
+	}
+	wdata->res.count = (isect << SECTOR_SHIFT) - (offset);
+	if (count < wdata->res.count)
+		wdata->res.count = count;
+out:
+	bl_put_extent(be);
+	bl_submit_bio(WRITE, bio);
+	put_parallel(par);
+	return PNFS_ATTEMPTED;
 }
 
 /* FIXME - range ignored */
-- 
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 ` [PATCH v1 18/25] pnfsblock: encode_layoutcommit Jim Rees
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 ` Jim Rees [this message]
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=1310947152-12255-22-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