On Wed, 2011-07-27 at 14:40 -0400, Jim Rees wrote:
> From: Fred Isaman <iisaman@xxxxxxxxxxxxxx>
>
> 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@xxxxxxxxxxxxxx>
> [pnfsblock: handle errors when read or write pagelist.]
> Signed-off-by: Zhang Jingwang <yyalone@xxxxxxxxx>
> [pnfs-block: use new write_pagelist api]
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxxx>
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxx>
>
> [SQUASHME: pnfsblock: mds_offset is set in the generic layer]
> Signed-off-by: Boaz Harrosh <bharrosh@xxxxxxxxxxx>
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxx>
>
> [pnfsblock: mark IO error with NFS_LAYOUT_{RW|RO}_FAILED]
> Signed-off-by: Peng Tao <peng_tao@xxxxxxx>
> [pnfsblock: SQUASHME: adjust to API change]
> Signed-off-by: Fred Isaman <iisaman@xxxxxxxxxxxxxx>
> [pnfsblock: fixup blksize alignment in bl_setup_layoutcommit]
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxxx>
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxx>
> [pnfsblock: bl_write_pagelist adjust for missing PG_USE_PNFS]
> Signed-off-by: Fred Isaman <iisaman@xxxxxxxxxxxxxx>
> [pnfsblock: handle errors when read or write pagelist.]
> Signed-off-by: Zhang Jingwang <yyalone@xxxxxxxxx>
> [pnfs-block: use new write_pagelist api]
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxxx>
> Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxx>
> ---
> fs/nfs/blocklayout/blocklayout.c | 137 +++++++++++++++++++++++++++++++++++++-
> 1 files changed, 134 insertions(+), 3 deletions(-)
>
> diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
> index 6e90371..963b3ea 100644
> --- a/fs/nfs/blocklayout/blocklayout.c
> +++ b/fs/nfs/blocklayout/blocklayout.c
> @@ -74,6 +74,19 @@ 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)
> {
> @@ -333,11 +346,129 @@ 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)
> +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;
> + }
Should never happen in the new code.
> + if (dont_like_caller(wdata->req)) {
> + dprintk("%s dont_like_caller failed\n", __func__);
> + return PNFS_NOT_ATTEMPTED;
> + }
Should never happen...
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust@xxxxxxxxxx
www.netapp.com
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
