BUG();
}
+static void filelayout_reset_write(struct nfs_write_data *data)
+{
+ struct nfs_pgio_header *hdr = data->header;
+ struct rpc_task *task = &data->task;
+
+ if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ dprintk("%s Reset task %5u for i/o through MDS "
+ "(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+ data->task.tk_pid,
+ hdr->inode->i_sb->s_id,
+ (long long)NFS_FILEID(hdr->inode),
+ data->args.count,
+ (unsigned long long)data->args.offset);
+
+ task->tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
+ &hdr->pages,
+ hdr->completion_ops);
+ }
+}
+
+static void filelayout_reset_read(struct nfs_read_data *data)
+{
+ struct nfs_pgio_header *hdr = data->header;
+ struct rpc_task *task = &data->task;
+
+ if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ dprintk("%s Reset task %5u for i/o through MDS "
+ "(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+ data->task.tk_pid,
+ hdr->inode->i_sb->s_id,
+ (long long)NFS_FILEID(hdr->inode),
+ data->args.count,
+ (unsigned long long)data->args.offset);
+
+ task->tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
+ &hdr->pages,
+ hdr->completion_ops);
+ }
+}
+
static int filelayout_async_handle_error(struct rpc_task *task,
struct nfs4_state *state,
struct nfs_client *clp,
- int *reset)
+ struct pnfs_layout_segment *lseg)
{
- struct nfs_server *mds_server = NFS_SERVER(state->inode);
+ struct inode *inode = lseg->pls_layout->plh_inode;
+ struct nfs_server *mds_server = NFS_SERVER(inode);
+ struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
struct nfs_client *mds_client = mds_server->nfs_client;
+ struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
if (task->tk_status >= 0)
return 0;
- *reset = 0;
switch (task->tk_status) {
/* MDS state errors */
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
+ if (state == NULL)
+ break;
nfs_remove_bad_delegation(state->inode);
case -NFS4ERR_OPENMODE:
+ if (state == NULL)
+ break;
nfs4_schedule_stateid_recovery(mds_server, state);
goto wait_on_recovery;
case -NFS4ERR_EXPIRED:
- nfs4_schedule_stateid_recovery(mds_server, state);
+ if (state != NULL)
+ nfs4_schedule_stateid_recovery(mds_server, state);
nfs4_schedule_lease_recovery(mds_client);
goto wait_on_recovery;
/* DS session errors */
dprintk("%s ERROR %d, Reset session. Exchangeid "
"flags 0x%x\n", __func__, task->tk_status,
clp->cl_exchange_flags);
- nfs4_schedule_session_recovery(clp->cl_session);
+ nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
break;
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
break;
case -NFS4ERR_RETRY_UNCACHED_REP:
break;
+ /* Invalidate Layout errors */
+ case -NFS4ERR_PNFS_NO_LAYOUT:
+ case -ESTALE: /* mapped NFS4ERR_STALE */
+ case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */
+ case -EISDIR: /* mapped NFS4ERR_ISDIR */
+ case -NFS4ERR_FHEXPIRED:
+ case -NFS4ERR_WRONG_TYPE:
+ dprintk("%s Invalid layout error %d\n", __func__,
+ task->tk_status);
+ /*
+ * Destroy layout so new i/o will get a new layout.
+ * Layout will not be destroyed until all current lseg
+ * references are put. Mark layout as invalid to resend failed
+ * i/o and all i/o waiting on the slot table to the MDS until
+ * layout is destroyed and a new valid layout is obtained.
+ */
+ set_bit(NFS_LAYOUT_INVALID,
+ &NFS_I(inode)->layout->plh_flags);
+ pnfs_destroy_layout(NFS_I(inode));
+ rpc_wake_up(&tbl->slot_tbl_waitq);
+ goto reset;
+ /* RPC connection errors */
+ case -ECONNREFUSED:
+ case -EHOSTDOWN:
+ case -EHOSTUNREACH:
+ case -ENETUNREACH:
+ case -EIO:
+ case -ETIMEDOUT:
+ case -EPIPE:
+ dprintk("%s DS connection error %d\n", __func__,
+ task->tk_status);
+ if (!filelayout_test_devid_invalid(devid))
+ _pnfs_return_layout(inode);
+ filelayout_mark_devid_invalid(devid);
+ rpc_wake_up(&tbl->slot_tbl_waitq);
+ nfs4_ds_disconnect(clp);
+ /* fall through */
default:
- dprintk("%s DS error. Retry through MDS %d\n", __func__,
+reset:
+ dprintk("%s Retry through MDS. Error %d\n", __func__,
task->tk_status);
- *reset = 1;
- break;
+ return -NFS4ERR_RESET_TO_MDS;
}
out:
task->tk_status = 0;
struct nfs_read_data *data)
{
struct nfs_pgio_header *hdr = data->header;
- int reset = 0;
+ int err;
- dprintk("%s DS read\n", __func__);
+ err = filelayout_async_handle_error(task, data->args.context->state,
+ data->ds_clp, hdr->lseg);
- if (filelayout_async_handle_error(task, data->args.context->state,
- data->ds_clp, &reset) == -EAGAIN) {
- dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
- __func__, data->ds_clp, data->ds_clp->cl_session);
- if (reset) {
- pnfs_set_lo_fail(hdr->lseg);
- nfs4_reset_read(task, data);
- }
+ switch (err) {
+ case -NFS4ERR_RESET_TO_MDS:
+ filelayout_reset_read(data);
+ return task->tk_status;
+ case -EAGAIN:
rpc_restart_call_prepare(task);
return -EAGAIN;
}
{
struct nfs_read_data *rdata = data;
+ if (filelayout_reset_to_mds(rdata->header->lseg)) {
+ dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+ filelayout_reset_read(rdata);
+ rpc_exit(task, 0);
+ return;
+ }
rdata->read_done_cb = filelayout_read_done_cb;
if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
+ if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) &&
+ task->tk_status == 0)
+ return;
+
/* Note this may cause RPC to be resent */
rdata->header->mds_ops->rpc_call_done(task, data);
}
{
struct nfs_read_data *rdata = data;
+ nfs_put_client(rdata->ds_clp);
rdata->header->mds_ops->rpc_release(data);
}
struct nfs_write_data *data)
{
struct nfs_pgio_header *hdr = data->header;
- int reset = 0;
-
- if (filelayout_async_handle_error(task, data->args.context->state,
- data->ds_clp, &reset) == -EAGAIN) {
- dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
- __func__, data->ds_clp, data->ds_clp->cl_session);
- if (reset) {
- pnfs_set_lo_fail(hdr->lseg);
- nfs4_reset_write(task, data);
- }
+ int err;
+
+ err = filelayout_async_handle_error(task, data->args.context->state,
+ data->ds_clp, hdr->lseg);
+
+ switch (err) {
+ case -NFS4ERR_RESET_TO_MDS:
+ filelayout_reset_write(data);
+ return task->tk_status;
+ case -EAGAIN:
rpc_restart_call_prepare(task);
return -EAGAIN;
}
static int filelayout_commit_done_cb(struct rpc_task *task,
struct nfs_commit_data *data)
{
- int reset = 0;
-
- if (filelayout_async_handle_error(task, data->context->state,
- data->ds_clp, &reset) == -EAGAIN) {
- dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
- __func__, data->ds_clp, data->ds_clp->cl_session);
- if (reset) {
- prepare_to_resend_writes(data);
- pnfs_set_lo_fail(data->lseg);
- } else
- rpc_restart_call_prepare(task);
+ int err;
+
+ err = filelayout_async_handle_error(task, NULL, data->ds_clp,
+ data->lseg);
+
+ switch (err) {
+ case -NFS4ERR_RESET_TO_MDS:
+ prepare_to_resend_writes(data);
+ return -EAGAIN;
+ case -EAGAIN:
+ rpc_restart_call_prepare(task);
return -EAGAIN;
}
{
struct nfs_write_data *wdata = data;
+ if (filelayout_reset_to_mds(wdata->header->lseg)) {
+ dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+ filelayout_reset_write(wdata);
+ rpc_exit(task, 0);
+ return;
+ }
if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
&wdata->args.seq_args, &wdata->res.seq_res,
task))
{
struct nfs_write_data *wdata = data;
+ if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
+ task->tk_status == 0)
+ return;
+
/* Note this may cause RPC to be resent */
wdata->header->mds_ops->rpc_call_done(task, data);
}
{
struct nfs_write_data *wdata = data;
+ nfs_put_client(wdata->ds_clp);
wdata->header->mds_ops->rpc_release(data);
}
static void filelayout_commit_release(void *calldata)
{
struct nfs_commit_data *data = calldata;
- struct nfs_commit_info cinfo;
- nfs_commit_release_pages(data);
- nfs_init_cinfo(&cinfo, data->inode, data->dreq);
- if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
- nfs_commit_clear_lock(NFS_I(data->inode));
+ data->completion_ops->completion(data);
put_lseg(data->lseg);
+ nfs_put_client(data->ds_clp);
nfs_commitdata_release(data);
}
__func__, hdr->inode->i_ino,
data->args.pgbase, (size_t)data->args.count, offset);
- if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
- return PNFS_NOT_ATTEMPTED;
-
/* 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) {
- /* Either layout fh index faulty, or ds connect failed */
- set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
- set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+ if (!ds)
return PNFS_NOT_ATTEMPTED;
- }
- dprintk("%s USE DS: %s\n", __func__, ds->ds_remotestr);
+ dprintk("%s USE DS: %s cl_count %d\n", __func__,
+ ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
/* No multipath support. Use first DS */
+ atomic_inc(&ds->ds_clp->cl_count);
data->ds_clp = ds->ds_clp;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
/* Perform an asynchronous read to ds */
status = nfs_initiate_read(ds->ds_clp->cl_rpcclient, data,
- &filelayout_read_call_ops);
+ &filelayout_read_call_ops, RPC_TASK_SOFTCONN);
BUG_ON(status != 0);
return PNFS_ATTEMPTED;
}
struct nfs_fh *fh;
int status;
- if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
- return PNFS_NOT_ATTEMPTED;
-
/* 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 "NFS: %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);
+ if (!ds)
return PNFS_NOT_ATTEMPTED;
- }
- dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__,
- hdr->inode->i_ino, sync, (size_t) data->args.count, offset,
- ds->ds_remotestr);
+ dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n",
+ __func__, hdr->inode->i_ino, sync, (size_t) data->args.count,
+ offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
data->write_done_cb = filelayout_write_done_cb;
+ atomic_inc(&ds->ds_clp->cl_count);
data->ds_clp = ds->ds_clp;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
/* Perform an asynchronous write */
status = nfs_initiate_write(ds->ds_clp->cl_rpcclient, data,
- &filelayout_write_call_ops, sync);
+ &filelayout_write_call_ops, sync,
+ RPC_TASK_SOFTCONN);
BUG_ON(status != 0);
return PNFS_ATTEMPTED;
}
idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
ds = nfs4_fl_prepare_ds(lseg, idx);
if (!ds) {
- printk(KERN_ERR "NFS: %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);
prepare_to_resend_writes(data);
filelayout_commit_release(data);
return -EAGAIN;
}
- dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how);
+ dprintk("%s ino %lu, how %d cl_count %d\n", __func__,
+ data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count));
data->commit_done_cb = filelayout_commit_done_cb;
+ atomic_inc(&ds->ds_clp->cl_count);
data->ds_clp = ds->ds_clp;
fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
if (fh)
data->args.fh = fh;
return nfs_initiate_commit(ds->ds_clp->cl_rpcclient, data,
- &filelayout_commit_call_ops, how);
+ &filelayout_commit_call_ops, how,
+ RPC_TASK_SOFTCONN);
}
static int
-filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
- struct nfs_commit_info *cinfo,
- int max)
+transfer_commit_list(struct list_head *src, struct list_head *dst,
+ struct nfs_commit_info *cinfo, int max)
{
- struct list_head *src = &bucket->written;
- struct list_head *dst = &bucket->committing;
struct nfs_page *req, *tmp;
int ret = 0;
list_for_each_entry_safe(req, tmp, src, wb_list) {
if (!nfs_lock_request(req))
continue;
+ kref_get(&req->wb_kref);
if (cond_resched_lock(cinfo->lock))
list_safe_reset_next(req, tmp, wb_list);
nfs_request_remove_commit_list(req, cinfo);
clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
nfs_list_add_request(req, dst);
ret++;
- if (ret == max)
+ if ((ret == max) && !cinfo->dreq)
break;
}
+ return ret;
+}
+
+static int
+filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
+ struct nfs_commit_info *cinfo,
+ int max)
+{
+ struct list_head *src = &bucket->written;
+ struct list_head *dst = &bucket->committing;
+ int ret;
+
+ ret = transfer_commit_list(src, dst, cinfo, max);
if (ret) {
cinfo->ds->nwritten -= ret;
cinfo->ds->ncommitting += ret;
return rv;
}
+/* Pull everything off the committing lists and dump into @dst */
+static void filelayout_recover_commit_reqs(struct list_head *dst,
+ struct nfs_commit_info *cinfo)
+{
+ struct pnfs_commit_bucket *b;
+ int i;
+
+ /* NOTE cinfo->lock is NOT held, relying on fact that this is
+ * only called on single thread per dreq.
+ * Can't take the lock because need to do put_lseg
+ */
+ for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
+ if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
+ BUG_ON(!list_empty(&b->written));
+ put_lseg(b->wlseg);
+ b->wlseg = NULL;
+ }
+ }
+ cinfo->ds->nwritten = 0;
+}
+
static unsigned int
alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
{
nreq += alloc_ds_commits(cinfo, &list);
if (nreq == 0) {
- nfs_commit_clear_lock(NFS_I(inode));
+ cinfo->completion_ops->error_cleanup(NFS_I(inode));
goto out;
}
list_for_each_entry_safe(data, tmp, &list, pages) {
list_del_init(&data->pages);
if (!data->lseg) {
- nfs_init_commit(data, mds_pages, NULL);
+ nfs_init_commit(data, mds_pages, NULL, cinfo);
nfs_initiate_commit(NFS_CLIENT(inode), data,
- data->mds_ops, how);
+ data->mds_ops, how, 0);
} else {
struct pnfs_commit_bucket *buckets;
buckets = cinfo->ds->buckets;
- nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg);
+ nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo);
filelayout_initiate_commit(data, how);
}
}
static struct pnfs_ds_commit_info *
filelayout_get_ds_info(struct inode *inode)
{
- return &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info;
+ struct pnfs_layout_hdr *layout = NFS_I(inode)->layout;
+
+ if (layout == NULL)
+ return NULL;
+ else
+ return &FILELAYOUT_FROM_HDR(layout)->commit_info;
}
static struct pnfs_layoutdriver_type filelayout_type = {
.mark_request_commit = filelayout_mark_request_commit,
.clear_request_commit = filelayout_clear_request_commit,
.scan_commit_lists = filelayout_scan_commit_lists,
+ .recover_commit_reqs = filelayout_recover_commit_reqs,
.commit_pagelist = filelayout_commit_pagelist,
.read_pagelist = filelayout_read_pagelist,
.write_pagelist = filelayout_write_pagelist,
projects / cascardo / linux.git / blobdiff