[pnfs] [PATCH 4/5] pNFS: Merge filelayout_flush_one into filelayout_write_pagelist.
William A. (Andy) Adamson
andros at citi.umich.edu
Wed May 7 19:13:55 EDT 2008
On Wed, May 7, 2008 at 6:35 PM, Dean Hildebrand <seattleplus at gmail.com>
wrote:
>
>
> William A. (Andy) Adamson wrote:
>
> >
> >
> > On Wed, May 7, 2008 at 5:47 PM, Dean Hildebrand <seattleplus at gmail.com<mailto:
> > seattleplus at gmail.com>> wrote:
> >
> >
> >
> > William A. (Andy) Adamson wrote:
> >
> > Hi Dean
> >
> > Could you please split this patch up? Perhaps into the removal
> > of the flush function + replacement function, the changes to
> > filelayout_write_pagelist, the changes to filelayout_commit,
> > and the removal of free _request_data?
> >
> > But how do I keep the bisectability? Touching any one of those 3
> > elements affects the other. I don't like separating the add and
> > remove of things, I prefer the replace-style patches. Either way,
> > this patch essentially has those elements in separate chunks.
> > (there is no replacement of flush_one, just deletion of
> > flush_one/free_request_data and change of write_pagelist/commit)
> >
> >
> > ok. then 1 patch has the deletion of flush one, one patch has the
> > deletion of free_request_data, one patch has the change to write_pagelist
> > and the other the change to filelayout_commit. that way, if we don't agree
> > with the change to say write_pagelist we can change just the one patch. or,
> > if we end up not wanting to remove free_request_data, we just remove one
> > patch.
> >
>
> If you want, I could have 1 patch to move to the new system of writes,
> including the removal of file_layout_flushone and
> filelayout_free_request_data, then have 1 patch which removes the common
> part of flushone and 1 patch to remove the common parts of
> free_request_data. How about that?
ok, thanks. i guess i don't completely understand the bisectability issues.
let's talk at c-thon..
-->Andy
>
>
> Dean
>
> >
> > -->Andy
> >
> >
> > If you want, I could split it up and send it out just for interest
> > sake.
> > Dean
> >
> >
> > -->Andy
> >
> >
> > On Tue, May 6, 2008 at 7:45 PM, Dean Hildebrand
> > <seattleplus at gmail.com <mailto:seattleplus at gmail.com>
> > <mailto:seattleplus at gmail.com <mailto:seattleplus at gmail.com>>>
> > wrote:
> >
> > details: The flush_one layout driver interface function is a
> > specialized
> > function only for the file layout. It's purpose was to
> > calculate
> > the correct data server for each write request so this
> > calculation
> > can be avoided when the data is actually sent on the wire. It
> > was decided that having such a specialized function (plus its
> > associated private state) was not worth
> > the effort. In addition, O_DIRECT needs to redo this
> > calculation
> > anyways.
> >
> > Signed-off-by: Dean Hildebrand <dhildeb at us.ibm.com
> > <mailto:dhildeb at us.ibm.com>
> > <mailto:dhildeb at us.ibm.com <mailto:dhildeb at us.ibm.com>>>
> >
> >
> > ---
> > fs/nfs/nfs4filelayout.c | 356
> > +++++++++++++-------------------------------
> > fs/nfs/nfs4filelayout.h | 8 +-
> > fs/nfs/nfs4filelayoutdev.c | 26 +++-
> > fs/nfs/pagelist.c | 3 -
> > fs/nfs/pnfs.c | 45 ------
> > fs/nfs/pnfs.h | 2 -
> > fs/nfs/write.c | 4 -
> > include/linux/nfs4_pnfs.h | 3 -
> > include/linux/nfs_page.h | 4 -
> > 9 files changed, 125 insertions(+), 326 deletions(-)
> >
> > diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
> > index 4f4748b..5d9b551 100644
> > --- a/fs/nfs/nfs4filelayout.c
> > +++ b/fs/nfs/nfs4filelayout.c
> > @@ -240,14 +240,7 @@ struct rpc_call_ops
> > filelayout_write_call_ops = {
> > * allows the original read/write data structs to be passed
> > in the
> > * last argument.
> > *
> > -
> > - * This is called after the pNFS client has already
> > created, so I
> > pass it
> > - * in via the last argument (void*). I think this is the
> > only
> > way as there
> > - * are just too many NFS specific arguments in the read/write
> > data structs
> > - * to pass to the layout drivers.
> > - *
> > - * TODO:
> > - * 1. This is a lot of arguments, create special
> > non-nfs-specific
> > structure?
> > + * TODO: join with write_pagelist?
> > */
> > static int filelayout_read_pagelist(
> > struct pnfs_layout_type *layoutid,
> > @@ -259,12 +252,11 @@ static int filelayout_read_pagelist(
> > struct nfs_read_data *data)
> > {
> > struct inode *inode = PNFS_INODE(layoutid);
> > - struct nfs4_filelayout *nfslay = NULL;
> > struct nfs4_filelayout_segment *flseg;
> > struct nfs4_pnfs_dserver dserver;
> > + struct nfs4_pnfs_ds *ds;
> > int status;
> >
> > - nfslay = PNFS_LD_DATA(layoutid);
> > flseg = LSEG_LD_DATA(data->lseg);
> >
> > /* Retrieve the correct rpc_client for the byte range
> > */
> > @@ -280,7 +272,9 @@ static int filelayout_read_pagelist(
> > data->args.fh = NFS_FH(inode);
> > status = 0;
> > } else {
> > - struct nfs4_pnfs_ds *ds =
> > dserver.dev->ds_list[0];
> > + ds = dserver.dev->ds_list[0];
> > +
> > + dprintk("%s USE DS:ip %x\n", __func__,
> > htonl(ds->ds_ip_addr));
> >
> > /* just try the first data server for the
> > index..*/
> > data->pnfs_client = ds->ds_clp->cl_rpcclient;
> > @@ -316,179 +310,7 @@ print_ds(struct nfs4_pnfs_ds *ds)
> > dprintk(" ds->ds_count %d\n",
> > atomic_read(&ds->ds_count));
> > }
> >
> > -static struct nfs4_pnfs_dserver *
> > -filelayout_create_dserver(void)
> > -{
> > - struct nfs4_pnfs_dserver *local;
> > -
> > - local = kzalloc(sizeof(*local), GFP_KERNEL);
> > - if (!local)
> > - return NULL;
> > - kref_init(&local->ref);
> > - dprintk("<-- %s dserver %p\n", __func__, local);
> > - return local;
> > -}
> > -
> > -static void filelayout_free_dserver(struct kref *kref)
> > -{
> > - struct nfs4_pnfs_dserver *dserver;
> > - dserver = container_of(kref, struct
> > nfs4_pnfs_dserver, ref);
> > -
> > - dprintk("--> %s dserver %p\n", __func__, dserver);
> > - kfree(dserver);
> > -}
> > -
> > -static void filelayout_release_dserver(struct
> > nfs4_pnfs_dserver
> > *dserver)
> > -{
> > - kref_put(&dserver->ref, filelayout_free_dserver);
> > -}
> > -
> > -static void filelayout_get_dserver(struct
> > nfs4_pnfs_dserver *dserver)
> > -{
> > - kref_get(&dserver->ref);
> > -}
> > -
> > -/*
> > - * Called by nfs_release_request()
> > - */
> > -void
> > -filelayout_free_request_data(struct nfs_page *req)
> > -{
> > - struct nfs4_pnfs_dserver *dserver;
> > -
> > - dserver = (struct nfs4_pnfs_dserver *)req->wb_private;
> > - BUG_ON(!dserver);
> > - filelayout_release_dserver(dserver);
> > -}
> > -
> > -static struct nfs4_pnfs_ds *
> > -filelayout_create_init_ds(struct pnfs_layout_segment *lseg,
> > - loff_t file_offset, size_t wb_bytes,
> > - struct nfs4_pnfs_dserver **dsp)
> > -{
> > - struct nfs4_pnfs_dserver *dserver;
> > - struct nfs4_pnfs_ds *ds;
> > - int status = -ENOMEM;
> > -
> > - *dsp = dserver = filelayout_create_dserver();
> > - if (!dserver) {
> > - dprintk("%s failed to get dserver. status
> > %d\n",
> > - __func__, status);
> > - goto out_err;
> > - }
> > -
> > - /* get the data server that serves this page */
> > - status = nfs4_pnfs_dserver_get(lseg, file_offset,
> > wb_bytes, dserver);
> > -
> > - if (status != 0) {
> > - dprintk("%s failed to get dataserver.
> > status %d\n",
> > - __func__,
> > status);
> > - filelayout_release_dserver(dserver);
> > - status = -EIO;
> > - goto out_err;
> > - }
> > - /* just try the first multipath data server */
> > - ds = dserver->dev->ds_list[0];
> > -
> > - return ds;
> > -out_err:
> > - return ERR_PTR(status);
> > -}
> > -
> > -/*
> > -* feed nfs_flush_one with per data server pages.
> > -*
> > -* Assume stripesz >= PAGE_SIZE.
> > -* TODO: If stripesz < PAGE_SIZE, use i/o through MDS
> > -*
> > -*/
> > -int filelayout_flush_one(struct pnfs_layout_segment *lseg,
> > - struct list_head *head, unsigned
> > int npages,
> > - size_t count, int how)
> > -{
> > - struct nfs4_pnfs_dserver *dserver = NULL;
> > - struct nfs4_pnfs_ds *ds = NULL; /* current stripe
> > data
> > server */
> > - struct nfs_page *req;
> > - loff_t file_offset = 0, stripe_offset, temp;
> > - size_t stripesz, dstotal = 0;
> > - struct list_head dslist;
> > - int status = -ENOMEM, use_ds = 0, ndspages = 0;
> > -
> > - dprintk("--> %s npages %d, count %Zd, lseg %p\n",
> > __func__,
> > - npages, count, lseg);
> > -
> > - INIT_LIST_HEAD(&dslist);
> > - stripesz = filelayout_get_stripesize(lseg->layout);
> > - dprintk("%s stripesize %Zd\n", __func__, stripesz);
> > -
> > - /* split up the list according to DS */
> > - while (!list_empty(head)) {
> > -next_ds:
> > - req = nfs_list_entry(head->next);
> > -
> > - file_offset = req->wb_index <<
> > PAGE_CACHE_SHIFT;
> > -
> > - if (!use_ds) {
> > - ds = filelayout_create_init_ds(lseg,
> > file_offset,
> > -
> > req->wb_bytes, &dserver);
> > - if (IS_ERR(ds)) {
> > - status = PTR_ERR(ds);
> > - goto out;
> > - }
> > - /* reset for new data server */
> > - dstotal = 0;
> > - ndspages = 0;
> > - use_ds = 1;
> > - } else
> > - filelayout_get_dserver(dserver);
> > -
> > - req->wb_ops = &filelayout_io_operations;
> > - req->wb_private = dserver;
> > -
> > - /* move request to dslist */
> > - nfs_list_remove_request(req);
> > - nfs_list_add_request(req, &dslist);
> > - ndspages++;
> > - npages--;
> > -
> > - count -= req->wb_bytes;
> > - dstotal += req->wb_bytes;
> > -
> > - /* Are we done with this DS? */
> > - temp = file_offset + req->wb_bytes;
> > - stripe_offset = do_div(temp, stripesz);
> > -
> > - if (count == 0 || stripe_offset == 0) {
> > - use_ds = 0;
> > - goto send;
> > - }
> > - }
> > -send:
> > - /* XXX should recover to send through MDS */
> > - dprintk("%s Send: ndspages %d dstotal %Zd
> > list_empty %d \n",
> > - __func__, ndspages, dstotal,
> > list_empty(head));
> > - status = nfs_flush_one(PNFS_INODE(lseg->layout),
> > &dslist,
> > ndspages,
> > - dstotal, how);
> > - if (status < 0)
> > - goto out;
> > -
> > - /* Is there more data to process? */
> > - if (!list_empty(head)) {
> > - /* count and npages better not be zero! */
> > - dprintk("%s next_ds count %Zd npages %d\n",
> > - __func__, count, npages);
> > - goto next_ds;
> > - }
> > -
> > -out:
> > - dprintk("<-- %s npages %d (should be zero!)\n",
> > __func__,
> > npages);
> > - return status;
> > -}
> > -
> > -/* Perform async writes.
> > - *
> > - * TODO: See filelayout_read_pagelist.
> > - */
> > +/* Perform async writes. */
> > static int filelayout_write_pagelist(
> > struct pnfs_layout_type *layoutid,
> > struct page **pages,
> > @@ -499,48 +321,52 @@ static int filelayout_write_pagelist(
> > int sync,
> > struct nfs_write_data *data)
> > {
> > + struct inode *inode = PNFS_INODE(layoutid);
> > struct nfs4_filelayout_segment *flseg =
> > LSEG_LD_DATA(data->lseg);
> > - struct nfs4_pnfs_dserver *dserver = NULL;
> > + struct nfs4_pnfs_dserver dserver;
> > struct nfs4_pnfs_ds *ds;
> > - struct nfs_page *req = NULL;
> > - struct list_head *h;
> > + int status;
> >
> > - dprintk("--> %s nr_pages %d offset:count
> > %Lu:%Zu\n", __func__,
> > - nr_pages,
> > offset,
> > count);
> > + dprintk("--> %s ino %lu nr_pages %d pgbase %u req
> > %Zu@%Lu
> > sync %d\n",
> > + __func__, inode->i_ino, nr_pages, pgbase,
> > count,
> > offset, sync);
> >
> > /* Retrieve the correct rpc_client for the byte range
> > */
> > - list_for_each(h, &data->pages) {
> > - req = list_entry(h, struct nfs_page, wb_list);
> > - break;
> > - }
> > - BUG_ON(!req);
> > -
> > - dserver = (struct nfs4_pnfs_dserver *)req->wb_private;
> > - BUG_ON(!dserver);
> > + status = nfs4_pnfs_dserver_get(data->lseg,
> > + offset,
> > + count,
> > + &dserver);
> >
> > - /* use the first multipath data server */
> > - ds = dserver->dev->ds_list[0];
> > - dprintk("%s USE DS:\n", __func__);
> > - print_ds(ds);
> > + if (status) {
> > + printk(KERN_ERR "%s: dserver get failed
> > status %d
> > use MDS\n",
> > + __func__, status);
> > + data->pnfs_client = NFS_CLIENT(inode);
> > + data->ds_nfs_client = NULL;
> > + data->args.fh = NFS_FH(inode);
> > + status = 0;
> > + } else {
> > + /* use the first multipath data server */
> > + ds = dserver.dev->ds_list[0];
> >
> > - data->pnfs_client = ds->ds_clp->cl_rpcclient;
> > - data->ds_nfs_client = ds->ds_clp;
> > - data->args.fh = dserver->fh;
> > + dprintk("%s ino %lu %Zu@%Lu DS:%x:%hu\n",
> > + __func__, inode->i_ino, count, offset,
> > + htonl(ds->ds_ip_addr),
> > ntohs(ds->ds_port));
> >
> > - dprintk("%s using DS %x:%hu\n", __func__,
> > - htonl(ds->ds_ip_addr), ntohs(ds->ds_port));
> > + data->pnfs_client = ds->ds_clp->cl_rpcclient;
> > + data->ds_nfs_client = ds->ds_clp;
> > + data->args.fh = dserver.fh;
> >
> > - /* Get the file offset on the dserver. Set the
> > write offset to
> > - * this offset and save the original offset.
> > - */
> > - data->args.offset =
> > filelayout_get_dserver_offset(offset,
> > flseg);
> > - data->orig_offset = offset;
> > + /* Get the file offset on the dserver. Set the
> > write offset to
> > + * this offset and save the original offset.
> > + */
> > + data->args.offset =
> > filelayout_get_dserver_offset(offset, flseg);
> > + data->orig_offset = offset;
> > + }
> >
> > /* Perform an asynchronous write The offset will be
> > reset
> > in the
> > * call_ops->rpc_call_done() routine
> > */
> > nfs_initiate_write(data, data->pnfs_client,
> > - &filelayout_write_call_ops, sync);
> > + &filelayout_write_call_ops, sync);
> >
> > return 0;
> > }
> > @@ -639,24 +465,6 @@ filelayout_free_lseg(struct
> > pnfs_layout_segment *lseg)
> > }
> >
> > /*
> > - * Do two nfs_pnfs_dserver pointers point to the same
> > structure?
> > - * Just compare the first multipath servers.
> > - */
> > -static int
> > -filelayout_same_ds(struct nfs4_pnfs_dserver *one, struct
> > nfs4_pnfs_dserver *two)
> > -{
> > - struct nfs4_pnfs_dev *d_one = one->dev, *d_two =
> > two->dev;
> > - struct nfs4_pnfs_ds *ds_one, *ds_two;
> > -
> > - ds_one = d_one->ds_list[0];
> > - ds_two = d_two->ds_list[0];
> > - return (d_one->stripe_index == d_two->stripe_index &&
> > - d_one->num_ds == d_two->num_ds &&
> > - ds_one->ds_ip_addr == ds_two->ds_ip_addr &&
> > - ds_one->ds_port == ds_two->ds_port);
> > -}
> > -
> > -/*
> > * Allocate a new nfs_write_data struct and initialize
> > */
> > static struct nfs_write_data *
> > @@ -693,66 +501,102 @@ filelayout_commit(struct
> > pnfs_layout_type
> > *layoutid, int sync,
> > {
> > struct nfs4_filelayout_segment *nfslay;
> > struct nfs_write_data *dsdata = NULL;
> > - struct nfs4_pnfs_dserver *dserver = NULL;
> > + struct nfs4_pnfs_dserver dserver;
> > struct nfs4_pnfs_ds *ds;
> > - struct nfs_page *req;
> > + struct nfs_page *req, *reqt;
> > struct list_head *pos, *tmp, *head = &data->pages;
> > + loff_t file_offset, comp_offset;
> > + size_t stripesz, cbytes;
> > + int status;
> > + struct nfs4_pnfs_dev_item *di;
> > + u32 idx1, idx2;
> >
> > nfslay = LSEG_LD_DATA(data->lseg);
> >
> > - dprintk("%s data %p pnfs_client %p nfslay %p\n",
> > - __func__, data, data->pnfs_client,
> > nfslay);
> > + dprintk("%s data %p pnfs_client %p nfslay %p sync
> > %d\n",
> > + __func__, data, data->pnfs_client, nfslay,
> > sync);
> >
> > if (nfslay->commit_through_mds) {
> > dprintk("%s data %p commit through mds\n",
> > __func__, data);
> > return 1;
> > }
> >
> > + stripesz = filelayout_get_stripesize(layoutid);
> > + dprintk("%s stripesize %Zd\n", __func__, stripesz);
> > +
> > + di = nfs4_pnfs_device_item_get(FILE_MT(data->inode),
> > NFS_FH(data->inode),
> > + &nfslay->dev_id);
> > + if (di == NULL) {
> > + status = -EIO;
> > + goto out_bad;
> > + }
> > +
> > /* COMMIT to each Data Server */
> > while (!list_empty(head)) {
> > -
> > - /* dserver and dsdata must be NULL */
> > req = nfs_list_entry(head->next);
> >
> > - dserver = (struct nfs4_pnfs_dserver
> > *)req->wb_private;
> > - /* XXX BUG_ON(!dserver) ?*/
> > - if (!dserver)
> > + file_offset = req->wb_index <<
> > PAGE_CACHE_SHIFT;
> > +
> > + /* Get dserver for the current page */
> > + status = nfs4_pnfs_dserver_get(data->lseg,
> > + file_offset,
> > + req->wb_bytes,
> > + &dserver);
> > +
> > + /* Get its index */
> > + idx1 =
> > filelayout_dserver_get_index(file_offset,
> > di, nfslay);
> > +
> > + if (status) {
> > + status = -EIO;
> > goto out_bad;
> > + }
> >
> > dsdata = filelayout_clone_write_data(data);
> > - if (!dsdata)
> > + if (!dsdata) {
> > + status = -ENOMEM;
> > goto out_bad;
> > + }
> >
> > /* Just try the first multipath data server */
> > - ds = dserver->dev->ds_list[0];
> > + ds = dserver.dev->ds_list[0];
> > dsdata->pnfs_client = ds->ds_clp->cl_rpcclient;
> > dsdata->ds_nfs_client = ds->ds_clp;
> > - dsdata->args.fh = dserver->fh;
> > -
> > - /* Gather all pages going to the data server
> > */
> > + dsdata->args.fh = dserver.fh;
> > + cbytes = req->wb_bytes;
> > +
> > + /* Gather all pages going to the current data
> > server by
> > + * comparing their indices.
> > + * XXX: This recalculates the indices
> > unecessarily.
> > + * One idea would be to calc the index
> > for
> > every page
> > + * and then compare if they are the
> > same. */
> > list_for_each_safe(pos, tmp, head) {
> > - req = nfs_list_entry(pos);
> > - if (filelayout_same_ds(dserver,
> > req->wb_private)) {
> > - nfs_list_remove_request(req);
> > - nfs_list_add_request(req,
> > &dsdata->pages);
> > + reqt = nfs_list_entry(pos);
> > + comp_offset = reqt->wb_index <<
> > PAGE_CACHE_SHIFT;
> > + idx2 =
> > filelayout_dserver_get_index(comp_offset, di, nfslay);
> > + if (idx1 == idx2) {
> > + nfs_list_remove_request(reqt);
> > + nfs_list_add_request(reqt,
> > &dsdata->pages);
> > + cbytes += reqt->wb_bytes;
> > }
> > }
> >
> > + dprintk("%s: Initiating commit: %Zu@%llu
> > USE DS:\n",
> > + __func__, cbytes, file_offset);
> > + print_ds(ds);
> > +
> > /* Send COMMIT to data server */
> > nfs_initiate_commit(dsdata,
> > dsdata->pnfs_client, sync);
> > -
> > - /* reset for next data server */
> > - dsdata = NULL;
> > - dserver = NULL;
> > }
> > /* Release original commit data since it is not used */
> > nfs_commit_free(data);
> > return 0;
> >
> > out_bad:
> > + printk(KERN_ERR "%s: dserver get failed status %d\n",
> > __func__, status);
> > +
> > /* XXX should we send COMMIT to MDS e.g. not free
> > data and
> > return 1 ? */
> > nfs_commit_free(data);
> > - return -ENOMEM;
> > + return status;
> > }
> >
> > /* Return the stripesize for the specified file.
> > @@ -803,6 +647,10 @@ boundary:
> > r_stripe = req->wb_index << PAGE_CACHE_SHIFT;
> > do_div(r_stripe, pgio->pg_boundary);
> >
> > +#if 0
> > + dprintk("%s p %u r %u bnd %d bsize %Zu\n",__func__,
> > p_stripe, r_stripe, pgio->pg_boundary, pgio->pg_bsize);
> > +#endif
> > +
> > return (p_stripe == r_stripe);
> > }
> >
> > @@ -831,8 +679,6 @@ struct layoutdriver_io_operations
> > filelayout_io_operations = {
> > .commit = filelayout_commit,
> > .read_pagelist = filelayout_read_pagelist,
> > .write_pagelist = filelayout_write_pagelist,
> > - .flush_one = filelayout_flush_one,
> > - .free_request_data =
> > filelayout_free_request_data,
> > .alloc_layout = filelayout_alloc_layout,
> > .free_layout = filelayout_free_layout,
> > .alloc_lseg = filelayout_alloc_lseg,
> > diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
> > index d0aeb78..4ec98ab 100644
> > --- a/fs/nfs/nfs4filelayout.h
> > +++ b/fs/nfs/nfs4filelayout.h
> > @@ -74,7 +74,6 @@ struct nfs4_pnfs_devlist {
> > struct nfs4_pnfs_dserver {
> > struct nfs_fh *fh;
> > struct nfs4_pnfs_dev *dev;
> > - struct kref ref;
> > };
> >
> > struct nfs4_filelayout_segment {
> > @@ -105,7 +104,6 @@ extern struct pnfs_client_operations
> > *pnfs_callback_ops;
> > char *deviceid_fmt(const struct pnfs_deviceid *dev_id);
> > int nfs4_pnfs_devlist_init(struct nfs4_pnfs_dev_hlist
> > *hlist);
> > void nfs4_pnfs_devlist_destroy(struct nfs4_pnfs_dev_hlist
> > *hlist);
> > -
> > int nfs4_pnfs_dserver_get(struct pnfs_layout_segment *lseg,
> > loff_t offset,
> > size_t count,
> > @@ -114,6 +112,12 @@ int decode_and_add_devicelist(struct
> > filelayout_mount_type *mt, struct pnfs_devi
> > int process_deviceid_list(struct filelayout_mount_type *mt,
> > struct nfs_fh *fh,
> > struct pnfs_devicelist *devlist);
> > +struct nfs4_pnfs_dev_item * nfs4_pnfs_device_item_get(struct
> > filelayout_mount_type *mt,
> > + struct
> > nfs_fh *fh,
> > + struct
> > pnfs_deviceid *dev_id);
> > +u32 filelayout_dserver_get_index(loff_t offset,
> > + struct nfs4_pnfs_dev_item
> > *di,
> > + struct
> > nfs4_filelayout_segment
> > *layout);
> >
> > #define READ32(x) (x) = ntohl(*p++)
> > #define READ64(x) do { \
> > diff --git a/fs/nfs/nfs4filelayoutdev.c
> > b/fs/nfs/nfs4filelayoutdev.c
> > index dce1bd1..ead8a53 100644
> > --- a/fs/nfs/nfs4filelayoutdev.c
> > +++ b/fs/nfs/nfs4filelayoutdev.c
> > @@ -695,6 +695,22 @@ nfs4_pnfs_device_item_get(struct
> > filelayout_mount_type *mt,
> > return dev;
> > }
> >
> > +/* Want res = ((offset / layout->stripe_unit) %
> > di->stripe_count)
> > + * Then: ((res + fsi) % di->stripe_count)
> > + */
> > +u32
> > +filelayout_dserver_get_index(loff_t offset,
> > + struct nfs4_pnfs_dev_item *di,
> > + struct nfs4_filelayout_segment
> > *layout)
> > +{
> > + u64 tmp, tmp2;
> > +
> > + tmp = offset;
> > + do_div(tmp, layout->stripe_unit);
> > + tmp2 = do_div(tmp, di->stripe_count) +
> > layout->first_stripe_index;
> > + return do_div(tmp2, di->stripe_count);
> > +}
> > +
> > /* Retrieve the rpc client for a specified byte range
> > * in 'inode' by filling in the contents of 'dserver'.
> > */
> > @@ -718,15 +734,9 @@ nfs4_pnfs_dserver_get(struct
> > pnfs_layout_segment *lseg,
> > if (di == NULL)
> > return 1;
> >
> > - /* Want res = ((offset / layout->stripe_unit) %
> > di->stripe_count)
> > - * Then: ((res + fsi) % di->stripe_count)
> > - */
> > -
> > - tmp = offset;
> > - do_div(tmp, layout->stripe_unit);
> > - tmp2 = do_div(tmp, di->stripe_count) +
> > layout->first_stripe_index;
> > - stripe_idx = do_div(tmp2, di->stripe_count);
> > + stripe_idx = filelayout_dserver_get_index(offset,
> > di, layout);
> >
> > + /* For debugging, ensure entire requested range is
> > in this
> > dserver */
> > tmp = offset + count - 1;
> > do_div(tmp, layout->stripe_unit);
> > tmp2 = do_div(tmp, di->stripe_count) +
> > layout->first_stripe_index;
> > diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
> > index b99fa0a..2b4cb44 100644
> > --- a/fs/nfs/pagelist.c
> > +++ b/fs/nfs/pagelist.c
> > @@ -170,9 +170,6 @@ static void nfs_free_request(struct
> > kref *kref)
> > /* Release struct file or cached credential */
> > nfs_clear_request(req);
> > put_nfs_open_context(req->wb_context);
> > -#ifdef CONFIG_PNFS
> > - pnfs_free_request_data(req);
> > -#endif /* CONFIG_PNFS */
> > nfs_page_free(req);
> > }
> >
> > diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
> > index 27e37be..9f504df 100644
> > --- a/fs/nfs/pnfs.c
> > +++ b/fs/nfs/pnfs.c
> > @@ -1338,40 +1338,6 @@ pnfs_writeback_done(struct
> > nfs_write_data
> > *data)
> > }
> >
> > /*
> > - * return 0 for success, 1 for legacy nfs fallback,
> > negative for
> > error
> > - */
> > -int
> > -pnfs_flush_one(struct inode *inode, struct list_head *head,
> > - unsigned int npages, size_t count, int how)
> > -{
> > - struct nfs_server *nfss = NFS_SERVER(inode);
> > - struct layoutdriver_io_operations *io_ops;
> > - struct nfs_page *req;
> > - struct pnfs_layout_segment *lseg;
> > - int status;
> > -
> > - if (!pnfs_enabled_sb(nfss) ||
> > !nfss->pnfs_curr_ld->ld_io_ops->flush_one)
> > - goto fallback;
> > -
> > - req = nfs_list_entry(head->next);
> > - status = pnfs_update_layout(inode,
> > - req->wb_context,
> > - count,
> > - req->wb_offset,
> > - IOMODE_RW,
> > - &lseg);
> > - if (status)
> > - goto fallback;
> > - io_ops = nfss->pnfs_curr_ld->ld_io_ops;
> > - status = io_ops->flush_one(lseg, head, npages,
> > count, how);
> > - put_lseg(lseg);
> > -
> > - return status;
> > -fallback:
> > - return nfs_flush_one(inode, head, npages, count, how);
> > -}
> > -
> > -/*
> > * Obtain a layout for the the write range, and call
> > do_sync_write.
> > *
> > * Unlike the read path which can wait until page coalescing
> > @@ -1965,17 +1931,6 @@ void
> > _pnfs_modify_new_write_request(struct
> > nfs_page *req,
> > }
> > }
> >
> > -void pnfs_free_request_data(struct nfs_page *req)
> > -{
> > - struct layoutdriver_io_operations *lo;
> > -
> > - if (!req->wb_ops || !req->wb_private)
> > - return;
> > - lo = (struct layoutdriver_io_operations *)req->wb_ops;
> > - if (lo->free_request_data)
> > - lo->free_request_data(req);
> > -}
> > -
> > void pnfs_free_fsdata(struct pnfs_fsdata *fsdata)
> > {
> > kfree(fsdata);
> > diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
> > index acbce4b..95ffbd3 100644
> > --- a/fs/nfs/pnfs.h
> > +++ b/fs/nfs/pnfs.h
> > @@ -53,8 +53,6 @@ int _pnfs_try_to_commit(struct
> > nfs_write_data *);
> > void pnfs_pageio_init_read(struct nfs_pageio_descriptor *,
> > struct
> > inode *, struct nfs_open_context *, struct list_head *,
> > size_t *);
> > void pnfs_pageio_init_write(struct nfs_pageio_descriptor *,
> > struct inode *);
> > void pnfs_update_layout_commit(struct inode *, struct
> > list_head
> > *, pgoff_t, unsigned int);
> > -int pnfs_flush_one(struct inode *, struct list_head *,
> > unsigned
> > int, size_t, int);
> > -void pnfs_free_request_data(struct nfs_page *req);
> > void pnfs_free_fsdata(struct pnfs_fsdata *fsdata);
> > ssize_t pnfs_file_write(struct file *, const char __user *,
> > size_t, loff_t *);
> > void pnfs_get_layout_done(struct pnfs_layout_type *,
> > diff --git a/fs/nfs/write.c b/fs/nfs/write.c
> > index 0da5280..9410fad 100644
> > --- a/fs/nfs/write.c
> > +++ b/fs/nfs/write.c
> > @@ -1008,11 +1008,7 @@ static void
> > nfs_pageio_init_write(struct
> > nfs_pageio_descriptor *pgio,
> > if (wsize < PAGE_CACHE_SIZE)
> > nfs_pageio_init(pgio, inode, nfs_flush_multi,
> > wsize, ioflags);
> > else
> > -#ifdef CONFIG_PNFS
> > - nfs_pageio_init(pgio, inode, pnfs_flush_one,
> > wsize, ioflags);
> > -#else
> > nfs_pageio_init(pgio, inode, nfs_flush_one,
> > wsize,
> > ioflags);
> > -#endif /* CONFIG_PNFS */
> > }
> >
> > /*
> > diff --git a/include/linux/nfs4_pnfs.h
> > b/include/linux/nfs4_pnfs.h
> > index c83aae6..290ffd6 100644
> > --- a/include/linux/nfs4_pnfs.h
> > +++ b/include/linux/nfs4_pnfs.h
> > @@ -137,7 +137,6 @@ struct layoutdriver_io_operations {
> > struct page **pages, unsigned
> > int
> > pgbase,
> > unsigned nr_pages, loff_t
> > offset,
> > size_t count,
> > int sync, struct nfs_write_data
> > *nfs_data);
> > - int (*flush_one) (struct pnfs_layout_segment *, struct
> > list_head *head, unsigned int npages, size_t count, int how);
> > int (*write_begin) (struct pnfs_layout_segment *lseg,
> > struct page *page,
> > loff_t pos, unsigned count,
> > struct pnfs_fsdata *fsdata);
> > @@ -147,8 +146,6 @@ struct layoutdriver_io_operations {
> > void (*new_request)(struct pnfs_layout_segment *lseg,
> > struct nfs_page *req, loff_t pos,
> > unsigned count,
> > struct pnfs_fsdata *fsdata);
> > - void (*free_request_data) (struct nfs_page *);
> > -
> >
> > /* Consistency ops */
> > /* 2 problems:
> > diff --git a/include/linux/nfs_page.h
> > b/include/linux/nfs_page.h
> > index 10329fb..1d6e830 100644
> > --- a/include/linux/nfs_page.h
> > +++ b/include/linux/nfs_page.h
> > @@ -45,10 +45,6 @@ struct nfs_page {
> > struct kref wb_kref; /* reference
> > count */
> > unsigned long wb_flags;
> > struct nfs_writeverf wb_verf; /* Commit
> > cookie */
> > -#ifdef CONFIG_PNFS
> > - void *wb_ops; /* pNFS io
> > operations */
> > - void *wb_private;
> > -#endif
> > };
> >
> > struct nfs_pageio_descriptor {
> > --
> > 1.5.3.3 <http://1.5.3.3> <http://1.5.3.3>
> >
> > _______________________________________________
> > pNFS mailing list
> > pNFS at linux-nfs.org <mailto:pNFS at linux-nfs.org>
> > <mailto:pNFS at linux-nfs.org <mailto:pNFS at linux-nfs.org>>
> >
> > http://linux-nfs.org/cgi-bin/mailman/listinfo/pnfs
> >
> >
> >
> >
> >
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://linux-nfs.org/pipermail/pnfs/attachments/20080507/7bdb896e/attachment-0001.htm
More information about the pNFS
mailing list