Commit 58baac0a authored by Trond Myklebust's avatar Trond Myklebust
Browse files

Merge branch 'flexfiles' 

* flexfiles:
  pNFS/flexfiles: Ensure we record layoutstats even if RPC is terminated early
  pNFS: Add flag to track if we've called nfs4_ff_layout_stat_io_start_read/write
  pNFS/flexfiles: Fix a statistics gathering imbalance
  pNFS/flexfiles: Don't mark the entire layout as failed, when returning it
  pNFS/flexfiles: Don't prevent flexfiles client from retrying LAYOUTGET
  pnfs/flexfiles: count io stat in rpc_count_stats callback
  pnfs/flexfiles: do not mark delay-like status as DS failure
  NFS41: map NFS4ERR_LAYOUTUNAVAILABLE to ENODATA
  nfs: only remove page from mapping if launder_page fails
  nfs: handle request add failure properly
  nfs: centralize pgio error cleanup
  nfs: clean up rest of reqs when failing to add one
  NFS41: pop some layoutget errors to application
  pNFS/flexfiles: Support server-supplied layoutstats sampling period
parents 8d0ed0ca 4d0ac221

fs/nfs/direct.c

+14 −1
Original line number Diff line number Diff line
@@ -670,6 +670,10 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) 


	req = nfs_list_entry(reqs.next);

	nfs_direct_setup_mirroring(dreq, &desc, req);

	if (desc.pg_error < 0) {

		list_splice_init(&reqs, &failed);

		goto out_failed;

	}



	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {

		if (!nfs_pageio_add_request(&desc, req)) {
@@ -677,6 +681,9 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) 
			nfs_list_add_request(req, &failed);

			spin_lock(cinfo.lock);

			dreq->flags = 0;

			if (desc.pg_error < 0)

				dreq->error = desc.pg_error;

			else

				dreq->error = -EIO;

			spin_unlock(cinfo.lock);

		}
@@ -684,6 +691,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) 
	}

	nfs_pageio_complete(&desc);



out_failed:

	while (!list_empty(&failed)) {

		req = nfs_list_entry(failed.next);

		nfs_list_remove_request(req);
@@ -900,6 +908,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, 
			}



			nfs_direct_setup_mirroring(dreq, &desc, req);

			if (desc.pg_error < 0) {

				nfs_free_request(req);

				result = desc.pg_error;

				break;

			}



			nfs_lock_request(req);

			req->wb_index = pos >> PAGE_SHIFT;

fs/nfs/file.c

+1 −1
Original line number Diff line number Diff line
@@ -545,7 +545,7 @@ static int nfs_launder_page(struct page *page) 
		inode->i_ino, (long long)page_offset(page));



	nfs_fscache_wait_on_page_write(nfsi, page);

	return nfs_wb_page(inode, page);

	return nfs_wb_launder_page(inode, page);

}



static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,

fs/nfs/filelayout/filelayout.c

+16 −2
Original line number Diff line number Diff line
@@ -202,6 +202,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, 
			task->tk_status);

		nfs4_mark_deviceid_unavailable(devid);

		pnfs_error_mark_layout_for_return(inode, lseg);

		pnfs_set_lo_fail(lseg);

		rpc_wake_up(&tbl->slot_tbl_waitq);

		/* fall through */

	default:
@@ -883,13 +884,19 @@ static void 
filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,

			struct nfs_page *req)

{

	if (!pgio->pg_lseg)

	if (!pgio->pg_lseg) {

		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,

					   req->wb_context,

					   0,

					   NFS4_MAX_UINT64,

					   IOMODE_READ,

					   GFP_KERNEL);

		if (IS_ERR(pgio->pg_lseg)) {

			pgio->pg_error = PTR_ERR(pgio->pg_lseg);

			pgio->pg_lseg = NULL;

			return;

		}

	}

	/* If no lseg, fall back to read through mds */

	if (pgio->pg_lseg == NULL)

		nfs_pageio_reset_read_mds(pgio);
@@ -902,13 +909,20 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, 
	struct nfs_commit_info cinfo;

	int status;



	if (!pgio->pg_lseg)

	if (!pgio->pg_lseg) {

		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,

					   req->wb_context,

					   0,

					   NFS4_MAX_UINT64,

					   IOMODE_RW,

					   GFP_NOFS);

		if (IS_ERR(pgio->pg_lseg)) {

			pgio->pg_error = PTR_ERR(pgio->pg_lseg);

			pgio->pg_lseg = NULL;

			return;

		}

	}



	/* If no lseg, fall back to write through mds */

	if (pgio->pg_lseg == NULL)

		goto out_mds;

fs/nfs/flexfilelayout/flexfilelayout.c

+145 −45
Original line number Diff line number Diff line
@@ -505,9 +505,17 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, 
	}



	p = xdr_inline_decode(&stream, 4);

	if (p)

	if (!p)

		goto out_sort_mirrors;

	fls->flags = be32_to_cpup(p);



	p = xdr_inline_decode(&stream, 4);

	if (!p)

		goto out_sort_mirrors;

	for (i=0; i < fls->mirror_array_cnt; i++)

		fls->mirror_array[i]->report_interval = be32_to_cpup(p);



out_sort_mirrors:

	ff_layout_sort_mirrors(fls);

	rc = ff_layout_check_layout(lgr);

	if (rc)
@@ -603,7 +611,9 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror, 
		mirror->start_time = now;

	if (ktime_equal(mirror->last_report_time, notime))

		mirror->last_report_time = now;

	if (layoutstats_timer != 0)

	if (mirror->report_interval != 0)

		report_interval = (s64)mirror->report_interval * 1000LL;

	else if (layoutstats_timer != 0)

		report_interval = (s64)layoutstats_timer * 1000LL;

	if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >=

			report_interval) {
@@ -785,13 +795,19 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, 
	int ds_idx;



	/* Use full layout for now */

	if (!pgio->pg_lseg)

	if (!pgio->pg_lseg) {

		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,

						   req->wb_context,

						   0,

						   NFS4_MAX_UINT64,

						   IOMODE_READ,

						   GFP_KERNEL);

		if (IS_ERR(pgio->pg_lseg)) {

			pgio->pg_error = PTR_ERR(pgio->pg_lseg);

			pgio->pg_lseg = NULL;

			return;

		}

	}

	/* If no lseg, fall back to read through mds */

	if (pgio->pg_lseg == NULL)

		goto out_mds;
@@ -825,13 +841,19 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, 
	int i;

	int status;



	if (!pgio->pg_lseg)

	if (!pgio->pg_lseg) {

		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,

						   req->wb_context,

						   0,

						   NFS4_MAX_UINT64,

						   IOMODE_RW,

						   GFP_NOFS);

		if (IS_ERR(pgio->pg_lseg)) {

			pgio->pg_error = PTR_ERR(pgio->pg_lseg);

			pgio->pg_lseg = NULL;

			return;

		}

	}

	/* If no lseg, fall back to write through mds */

	if (pgio->pg_lseg == NULL)

		goto out_mds;
@@ -867,18 +889,25 @@ static unsigned int 
ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,

				    struct nfs_page *req)

{

	if (!pgio->pg_lseg)

	if (!pgio->pg_lseg) {

		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,

						   req->wb_context,

						   0,

						   NFS4_MAX_UINT64,

						   IOMODE_RW,

						   GFP_NOFS);

		if (IS_ERR(pgio->pg_lseg)) {

			pgio->pg_error = PTR_ERR(pgio->pg_lseg);

			pgio->pg_lseg = NULL;

			goto out;

		}

	}

	if (pgio->pg_lseg)

		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);



	/* no lseg means that pnfs is not in use, so no mirroring here */

	nfs_pageio_reset_write_mds(pgio);

out:

	return 1;

}
@@ -1101,7 +1130,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task, 
	return -NFS4ERR_RESET_TO_PNFS;

out_retry:

	task->tk_status = 0;

	rpc_restart_call(task);

	rpc_restart_call_prepare(task);

	rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);

	return -EAGAIN;

}
@@ -1159,6 +1188,14 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, 
		}

	}



	switch (status) {

	case NFS4ERR_DELAY:

	case NFS4ERR_GRACE:

		return;

	default:

		break;

	}



	mirror = FF_LAYOUT_COMP(lseg, idx);

	err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),

				       mirror, offset, length, status, opnum,
@@ -1242,14 +1279,31 @@ ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) 
	return ff_layout_test_devid_unavailable(node);

}



static int ff_layout_read_prepare_common(struct rpc_task *task,

static void ff_layout_read_record_layoutstats_start(struct rpc_task *task,

		struct nfs_pgio_header *hdr)

{

	if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags))

		return;

	nfs4_ff_layout_stat_io_start_read(hdr->inode,

			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),

			hdr->args.count,

			task->tk_start);

}



static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,

		struct nfs_pgio_header *hdr)

{

	if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags))

		return;

	nfs4_ff_layout_stat_io_end_read(task,

			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),

			hdr->args.count,

			hdr->res.count);

}



static int ff_layout_read_prepare_common(struct rpc_task *task,

					 struct nfs_pgio_header *hdr)

{

	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {

		rpc_exit(task, -EIO);

		return -EIO;
@@ -1265,6 +1319,7 @@ static int ff_layout_read_prepare_common(struct rpc_task *task, 
	}

	hdr->pgio_done_cb = ff_layout_read_done_cb;



	ff_layout_read_record_layoutstats_start(task, hdr);

	return 0;

}
@@ -1323,10 +1378,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data) 


	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);



	nfs4_ff_layout_stat_io_end_read(task,

			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),

			hdr->args.count, hdr->res.count);



	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&

	    task->tk_status == 0) {

		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1341,10 +1392,20 @@ static void ff_layout_read_count_stats(struct rpc_task *task, void *data) 
{

	struct nfs_pgio_header *hdr = data;



	ff_layout_read_record_layoutstats_done(task, hdr);

	rpc_count_iostats_metrics(task,

	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]);

}



static void ff_layout_read_release(void *data)

{

	struct nfs_pgio_header *hdr = data;



	ff_layout_read_record_layoutstats_done(&hdr->task, hdr);

	pnfs_generic_rw_release(data);

}





static int ff_layout_write_done_cb(struct rpc_task *task,

				struct nfs_pgio_header *hdr)

{
@@ -1362,15 +1423,12 @@ static int ff_layout_write_done_cb(struct rpc_task *task, 


	switch (err) {

	case -NFS4ERR_RESET_TO_PNFS:

		pnfs_set_retry_layoutget(hdr->lseg->pls_layout);

		ff_layout_reset_write(hdr, true);

		return task->tk_status;

	case -NFS4ERR_RESET_TO_MDS:

		pnfs_clear_retry_layoutget(hdr->lseg->pls_layout);

		ff_layout_reset_write(hdr, false);

		return task->tk_status;

	case -EAGAIN:

		rpc_restart_call_prepare(task);

		return -EAGAIN;

	}
@@ -1402,11 +1460,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, 


	switch (err) {

	case -NFS4ERR_RESET_TO_PNFS:

		pnfs_set_retry_layoutget(data->lseg->pls_layout);

		pnfs_generic_prepare_to_resend_writes(data);

		return -EAGAIN;

	case -NFS4ERR_RESET_TO_MDS:

		pnfs_clear_retry_layoutget(data->lseg->pls_layout);

		pnfs_generic_prepare_to_resend_writes(data);

		return -EAGAIN;

	case -EAGAIN:
@@ -1421,14 +1477,31 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, 
	return 0;

}



static int ff_layout_write_prepare_common(struct rpc_task *task,

static void ff_layout_write_record_layoutstats_start(struct rpc_task *task,

		struct nfs_pgio_header *hdr)

{

	if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags))

		return;

	nfs4_ff_layout_stat_io_start_write(hdr->inode,

			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),

			hdr->args.count,

			task->tk_start);

}



static void ff_layout_write_record_layoutstats_done(struct rpc_task *task,

		struct nfs_pgio_header *hdr)

{

	if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags))

		return;

	nfs4_ff_layout_stat_io_end_write(task,

			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),

			hdr->args.count, hdr->res.count,

			hdr->res.verf->committed);

}



static int ff_layout_write_prepare_common(struct rpc_task *task,

					  struct nfs_pgio_header *hdr)

{

	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {

		rpc_exit(task, -EIO);

		return -EIO;
@@ -1445,6 +1518,7 @@ static int ff_layout_write_prepare_common(struct rpc_task *task, 
		return -EAGAIN;

	}



	ff_layout_write_record_layoutstats_start(task, hdr);

	return 0;

}
@@ -1480,11 +1554,6 @@ static void ff_layout_write_call_done(struct rpc_task *task, void *data) 
{

	struct nfs_pgio_header *hdr = data;



	nfs4_ff_layout_stat_io_end_write(task,

			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),

			hdr->args.count, hdr->res.count,

			hdr->res.verf->committed);



	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&

	    task->tk_status == 0) {

		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1499,18 +1568,53 @@ static void ff_layout_write_count_stats(struct rpc_task *task, void *data) 
{

	struct nfs_pgio_header *hdr = data;



	ff_layout_write_record_layoutstats_done(task, hdr);

	rpc_count_iostats_metrics(task,

	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]);

}



static void ff_layout_commit_prepare_common(struct rpc_task *task,

static void ff_layout_write_release(void *data)

{

	struct nfs_pgio_header *hdr = data;



	ff_layout_write_record_layoutstats_done(&hdr->task, hdr);

	pnfs_generic_rw_release(data);

}



static void ff_layout_commit_record_layoutstats_start(struct rpc_task *task,

		struct nfs_commit_data *cdata)

{

	if (test_and_set_bit(NFS_IOHDR_STAT, &cdata->flags))

		return;

	nfs4_ff_layout_stat_io_start_write(cdata->inode,

			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),

			0, task->tk_start);

}



static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task,

		struct nfs_commit_data *cdata)

{

	struct nfs_page *req;

	__u64 count = 0;



	if (!test_and_clear_bit(NFS_IOHDR_STAT, &cdata->flags))

		return;



	if (task->tk_status == 0) {

		list_for_each_entry(req, &cdata->pages, wb_list)

			count += req->wb_bytes;

	}

	nfs4_ff_layout_stat_io_end_write(task,

			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),

			count, count, NFS_FILE_SYNC);

}



static void ff_layout_commit_prepare_common(struct rpc_task *task,

		struct nfs_commit_data *cdata)

{

	ff_layout_commit_record_layoutstats_start(task, cdata);

}



static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data)

{

	ff_layout_commit_prepare_common(task, data);
@@ -1531,19 +1635,6 @@ static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data) 


static void ff_layout_commit_done(struct rpc_task *task, void *data)

{

	struct nfs_commit_data *cdata = data;

	struct nfs_page *req;

	__u64 count = 0;



	if (task->tk_status == 0) {

		list_for_each_entry(req, &cdata->pages, wb_list)

			count += req->wb_bytes;

	}



	nfs4_ff_layout_stat_io_end_write(task,

			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),

			count, count, NFS_FILE_SYNC);



	pnfs_generic_write_commit_done(task, data);

}
@@ -1551,50 +1642,59 @@ static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) 
{

	struct nfs_commit_data *cdata = data;



	ff_layout_commit_record_layoutstats_done(task, cdata);

	rpc_count_iostats_metrics(task,

	    &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]);

}



static void ff_layout_commit_release(void *data)

{

	struct nfs_commit_data *cdata = data;



	ff_layout_commit_record_layoutstats_done(&cdata->task, cdata);

	pnfs_generic_commit_release(data);

}



static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {

	.rpc_call_prepare = ff_layout_read_prepare_v3,

	.rpc_call_done = ff_layout_read_call_done,

	.rpc_count_stats = ff_layout_read_count_stats,

	.rpc_release = pnfs_generic_rw_release,

	.rpc_release = ff_layout_read_release,

};



static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {

	.rpc_call_prepare = ff_layout_read_prepare_v4,

	.rpc_call_done = ff_layout_read_call_done,

	.rpc_count_stats = ff_layout_read_count_stats,

	.rpc_release = pnfs_generic_rw_release,

	.rpc_release = ff_layout_read_release,

};



static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {

	.rpc_call_prepare = ff_layout_write_prepare_v3,

	.rpc_call_done = ff_layout_write_call_done,

	.rpc_count_stats = ff_layout_write_count_stats,

	.rpc_release = pnfs_generic_rw_release,

	.rpc_release = ff_layout_write_release,

};



static const struct rpc_call_ops ff_layout_write_call_ops_v4 = {

	.rpc_call_prepare = ff_layout_write_prepare_v4,

	.rpc_call_done = ff_layout_write_call_done,

	.rpc_count_stats = ff_layout_write_count_stats,

	.rpc_release = pnfs_generic_rw_release,

	.rpc_release = ff_layout_write_release,

};



static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = {

	.rpc_call_prepare = ff_layout_commit_prepare_v3,

	.rpc_call_done = ff_layout_commit_done,

	.rpc_count_stats = ff_layout_commit_count_stats,

	.rpc_release = pnfs_generic_commit_release,

	.rpc_release = ff_layout_commit_release,

};



static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = {

	.rpc_call_prepare = ff_layout_commit_prepare_v4,

	.rpc_call_done = ff_layout_commit_done,

	.rpc_count_stats = ff_layout_commit_count_stats,

	.rpc_release = pnfs_generic_commit_release,

	.rpc_release = ff_layout_commit_release,

};



static enum pnfs_try_status

fs/nfs/flexfilelayout/flexfilelayout.h

+1 −0
Original line number Diff line number Diff line
@@ -85,6 +85,7 @@ struct nfs4_ff_layout_mirror { 
	struct nfs4_ff_layoutstat	write_stat;

	ktime_t				start_time;

	ktime_t				last_report_time;

	u32				report_interval;

};



struct nfs4_ff_layout_segment {

CRA Git | Maintained and supported by SUSTech CRA and CCSE