NFSv4.1: pnfs filelayout driver write

Allows the pnfs filelayout driver to write to the data servers.

Note that COMMIT to data servers will be implemented in a future
patch.  To avoid improper behavior, for the moment any WRITE to a data
server that would also require a COMMIT to the data server is sent
NFS_FILE_SYNC.

Signed-off-by: Andy Adamson <andros@citi.umich.edu>
Signed-off-by: Dean Hildebrand <dhildeb@us.ibm.com>
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
Signed-off-by: Mingyang Guo <guomingyang@nrchpc.ac.cn>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com>
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Fred Isaman <iisaman@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This commit is contained in:
Fred Isaman 2011-03-03 15:13:47 +00:00 committed by Trond Myklebust
parent 7ffd10640d
commit a69aef1496
5 changed files with 128 additions and 2 deletions

View File

@ -276,6 +276,10 @@ extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
/* write.c */
extern int nfs_initiate_write(struct nfs_write_data *data,
struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops,
int how);
extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
#ifdef CONFIG_MIGRATION
extern int nfs_migrate_page(struct address_space *,
@ -291,6 +295,7 @@ extern int nfs4_init_client(struct nfs_client *clp,
const char *ip_addr,
rpc_authflavor_t authflavour,
int noresvport);
extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data);
extern int _nfs4_call_sync(struct nfs_server *server,
struct rpc_message *msg,
struct nfs4_sequence_args *args,

View File

@ -189,12 +189,69 @@ static void filelayout_read_release(void *data)
rdata->mds_ops->rpc_release(data);
}
static int filelayout_write_done_cb(struct rpc_task *task,
struct nfs_write_data *data)
{
int reset = 0;
if (filelayout_async_handle_error(task, data->args.context->state,
data->ds_clp, &reset) == -EAGAIN) {
struct nfs_client *clp;
dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
__func__, data->ds_clp, data->ds_clp->cl_session);
if (reset) {
filelayout_set_lo_fail(data->lseg);
nfs4_reset_write(task, data);
clp = NFS_SERVER(data->inode)->nfs_client;
} else
clp = data->ds_clp;
nfs_restart_rpc(task, clp);
return -EAGAIN;
}
return 0;
}
static void filelayout_write_prepare(struct rpc_task *task, void *data)
{
struct nfs_write_data *wdata = (struct nfs_write_data *)data;
if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
&wdata->args.seq_args, &wdata->res.seq_res,
0, task))
return;
rpc_call_start(task);
}
static void filelayout_write_call_done(struct rpc_task *task, void *data)
{
struct nfs_write_data *wdata = (struct nfs_write_data *)data;
/* Note this may cause RPC to be resent */
wdata->mds_ops->rpc_call_done(task, data);
}
static void filelayout_write_release(void *data)
{
struct nfs_write_data *wdata = (struct nfs_write_data *)data;
wdata->mds_ops->rpc_release(data);
}
struct rpc_call_ops filelayout_read_call_ops = {
.rpc_call_prepare = filelayout_read_prepare,
.rpc_call_done = filelayout_read_call_done,
.rpc_release = filelayout_read_release,
};
struct rpc_call_ops filelayout_write_call_ops = {
.rpc_call_prepare = filelayout_write_prepare,
.rpc_call_done = filelayout_write_call_done,
.rpc_release = filelayout_write_release,
};
static enum pnfs_try_status
filelayout_read_pagelist(struct nfs_read_data *data)
{
@ -238,10 +295,52 @@ filelayout_read_pagelist(struct nfs_read_data *data)
return PNFS_ATTEMPTED;
}
/* Perform async writes. */
static enum pnfs_try_status
filelayout_write_pagelist(struct nfs_write_data *data, int sync)
{
return PNFS_NOT_ATTEMPTED;
struct pnfs_layout_segment *lseg = data->lseg;
struct nfs4_pnfs_ds *ds;
loff_t offset = data->args.offset;
u32 j, idx;
struct nfs_fh *fh;
int status;
/* Retrieve the correct rpc_client for the byte range */
j = nfs4_fl_calc_j_index(lseg, offset);
idx = nfs4_fl_calc_ds_index(lseg, j);
ds = nfs4_fl_prepare_ds(lseg, idx);
if (!ds) {
printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
return PNFS_NOT_ATTEMPTED;
}
dprintk("%s ino %lu sync %d req %Zu@%llu DS:%x:%hu\n", __func__,
data->inode->i_ino, sync, (size_t) data->args.count, offset,
ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
/* We can't handle commit to ds yet */
if (!FILELAYOUT_LSEG(lseg)->commit_through_mds)
data->args.stable = NFS_FILE_SYNC;
data->write_done_cb = filelayout_write_done_cb;
data->ds_clp = ds->ds_clp;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
data->args.fh = 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(lseg, offset);
data->mds_offset = offset;
/* Perform an asynchronous write */
status = nfs_initiate_write(data, ds->ds_clp->cl_rpcclient,
&filelayout_write_call_ops, sync);
BUG_ON(status != 0);
return PNFS_ATTEMPTED;
}
/*

View File

@ -3145,6 +3145,23 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
return data->write_done_cb(task, data);
}
/* Reset the the nfs_write_data to send the write to the MDS. */
void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data)
{
dprintk("%s Reset task for i/o through\n", __func__);
put_lseg(data->lseg);
data->lseg = NULL;
data->ds_clp = NULL;
data->write_done_cb = nfs4_write_done_cb;
data->args.fh = NFS_FH(data->inode);
data->args.bitmask = data->res.server->cache_consistency_bitmask;
data->args.offset = data->mds_offset;
data->res.fattr = &data->fattr;
task->tk_ops = data->mds_ops;
rpc_task_reset_client(task, NFS_CLIENT(data->inode));
}
EXPORT_SYMBOL_GPL(nfs4_reset_write);
static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
{
struct nfs_server *server = NFS_SERVER(data->inode);

View File

@ -783,7 +783,7 @@ static int flush_task_priority(int how)
return RPC_PRIORITY_NORMAL;
}
static int nfs_initiate_write(struct nfs_write_data *data,
int nfs_initiate_write(struct nfs_write_data *data,
struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops,
int how)
@ -833,6 +833,7 @@ static int nfs_initiate_write(struct nfs_write_data *data,
out:
return ret;
}
EXPORT_SYMBOL_GPL(nfs_initiate_write);
/*
* Set up the argument/result storage required for the RPC call.
@ -1194,6 +1195,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
*/
static unsigned long complain;
/* Note this will print the MDS for a DS write */
if (time_before(complain, jiffies)) {
dprintk("NFS: faulty NFS server %s:"
" (committed = %d) != (stable = %d)\n",
@ -1214,6 +1216,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
/* Was this an NFSv2 write or an NFSv3 stable write? */
if (resp->verf->committed != NFS_UNSTABLE) {
/* Resend from where the server left off */
data->mds_offset += resp->count;
argp->offset += resp->count;
argp->pgbase += resp->count;
argp->count -= resp->count;

View File

@ -1039,11 +1039,13 @@ struct nfs_write_data {
struct nfs_writeargs args; /* argument struct */
struct nfs_writeres res; /* result struct */
struct pnfs_layout_segment *lseg;
struct nfs_client *ds_clp; /* pNFS data server */
const struct rpc_call_ops *mds_ops;
int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
#ifdef CONFIG_NFS_V4
unsigned long timestamp; /* For lease renewal */
#endif
__u64 mds_offset; /* Filelayout dense stripe */
struct page *page_array[NFS_PAGEVEC_SIZE];
};