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:
parent
7ffd10640d
commit
a69aef1496
|
@ -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,
|
||||
|
|
|
@ -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;
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
|
@ -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);
|
||||
|
|
|
@ -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;
|
||||
|
|
|
@ -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];
|
||||
};
|
||||
|
||||
|
|
Loading…
Reference in New Issue