@@ -219,8 +219,10 @@ static void finish_netfs_read(struct ceph_osd_request *req)
struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
struct netfs_io_subrequest *subreq = req->r_priv;
+ struct ceph_osd_req_op *op = &req->r_ops[0];
int num_pages;
int err = req->r_result;
+ bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, osd_data->length, err);
@@ -229,7 +231,9 @@ static void finish_netfs_read(struct ceph_osd_request *req)
subreq->len, i_size_read(req->r_inode));
/* no object means success but no data */
- if (err == -ENOENT)
+ if (sparse && err >= 0)
+ err = ceph_sparse_ext_map_end(op);
+ else if (err == -ENOENT)
err = 0;
else if (err == -EBLOCKLISTED)
fsc->blocklisted = true;
@@ -312,6 +316,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
size_t page_off;
int err = 0;
u64 len = subreq->len;
+ bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
if (ceph_inode_is_shutdown(inode)) {
err = -EIO;
@@ -322,7 +327,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
return;
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
- 0, 1, CEPH_OSD_OP_READ,
+ 0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
if (IS_ERR(req)) {
@@ -331,6 +336,12 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
goto out;
}
+ if (sparse) {
+ err = ceph_alloc_sparse_ext_map(&req->r_ops[0]);
+ if (err)
+ goto out;
+ }
+
dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
@@ -939,6 +939,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
u64 off = iocb->ki_pos;
u64 len = iov_iter_count(to);
u64 i_size = i_size_read(inode);
+ bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
@@ -965,10 +966,12 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
bool more;
int idx;
size_t left;
+ struct ceph_osd_req_op *op;
req = ceph_osdc_new_request(osdc, &ci->i_layout,
ci->i_vino, off, &len, 0, 1,
- CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
+ sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
+ CEPH_OSD_FLAG_READ,
NULL, ci->i_truncate_seq,
ci->i_truncate_size, false);
if (IS_ERR(req)) {
@@ -989,6 +992,16 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
false, false);
+
+ op = &req->r_ops[0];
+ if (sparse) {
+ ret = ceph_alloc_sparse_ext_map(op);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ break;
+ }
+ }
+
ceph_osdc_start_request(osdc, req);
ret = ceph_osdc_wait_request(osdc, req);
@@ -997,19 +1010,24 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
req->r_end_latency,
len, ret);
- ceph_osdc_put_request(req);
-
i_size = i_size_read(inode);
dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
off, len, ret, i_size, (more ? " MORE" : ""));
- if (ret == -ENOENT)
+ /* Fix it to go to end of extent map */
+ if (sparse && ret >= 0)
+ ret = ceph_sparse_ext_map_end(op);
+ else if (ret == -ENOENT)
ret = 0;
+
+ ceph_osdc_put_request(req);
+
if (ret >= 0 && ret < len && (off + ret < i_size)) {
int zlen = min(len - ret, i_size - off - ret);
int zoff = page_off + ret;
+
dout("sync_read zero gap %llu~%llu\n",
- off + ret, off + ret + zlen);
+ off + ret, off + ret + zlen);
ceph_zero_page_vector_range(zoff, zlen, pages);
ret += zlen;
}
@@ -1128,8 +1146,10 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
struct inode *inode = req->r_inode;
struct ceph_aio_request *aio_req = req->r_priv;
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
+ struct ceph_osd_req_op *op = &req->r_ops[0];
struct ceph_client_metric *metric = &ceph_sb_to_mdsc(inode->i_sb)->metric;
unsigned int len = osd_data->bvec_pos.iter.bi_size;
+ bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
BUG_ON(!osd_data->num_bvecs);
@@ -1150,6 +1170,8 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
}
rc = -ENOMEM;
} else if (!aio_req->write) {
+ if (sparse && rc >= 0)
+ rc = ceph_sparse_ext_map_end(op);
if (rc == -ENOENT)
rc = 0;
if (rc >= 0 && len > rc) {
@@ -1286,6 +1308,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
loff_t pos = iocb->ki_pos;
bool write = iov_iter_rw(iter) == WRITE;
bool should_dirty = !write && user_backed_iter(iter);
+ bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
@@ -1313,6 +1336,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
while (iov_iter_count(iter) > 0) {
u64 size = iov_iter_count(iter);
ssize_t len;
+ struct ceph_osd_req_op *op;
+ int readop = sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ;
if (write)
size = min_t(u64, size, fsc->mount_options->wsize);
@@ -1323,8 +1348,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
vino, pos, &size, 0,
1,
- write ? CEPH_OSD_OP_WRITE :
- CEPH_OSD_OP_READ,
+ write ? CEPH_OSD_OP_WRITE : readop,
flags, snapc,
ci->i_truncate_seq,
ci->i_truncate_size,
@@ -1375,6 +1399,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
}
osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
+ op = &req->r_ops[0];
+ if (sparse) {
+ ret = ceph_alloc_sparse_ext_map(op);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ break;
+ }
+ }
if (aio_req) {
aio_req->total_len += len;
@@ -1402,8 +1434,11 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
size = i_size_read(inode);
if (!write) {
- if (ret == -ENOENT)
+ if (sparse && ret >= 0)
+ ret = ceph_sparse_ext_map_end(op);
+ else if (ret == -ENOENT)
ret = 0;
+
if (ret >= 0 && ret < len && pos + ret < size) {
struct iov_iter i;
int zlen = min_t(size_t, len - ret,
@@ -165,6 +165,7 @@ enum {
Opt_copyfrom,
Opt_wsync,
Opt_pagecache,
+ Opt_sparseread,
};
enum ceph_recover_session_mode {
@@ -207,6 +208,7 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
fsparam_u32 ("wsize", Opt_wsize),
fsparam_flag_no ("wsync", Opt_wsync),
fsparam_flag_no ("pagecache", Opt_pagecache),
+ fsparam_flag_no ("sparseread", Opt_sparseread),
{}
};
@@ -576,6 +578,12 @@ static int ceph_parse_mount_param(struct fs_context *fc,
else
fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE;
break;
+ case Opt_sparseread:
+ if (result.negated)
+ fsopt->flags &= ~CEPH_MOUNT_OPT_SPARSEREAD;
+ else
+ fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD;
+ break;
default:
BUG();
}
@@ -710,9 +718,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS))
seq_puts(m, ",wsync");
-
if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE)
seq_puts(m, ",nopagecache");
+ if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
+ seq_puts(m, ",sparseread");
if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
seq_printf(m, ",wsize=%u", fsopt->wsize);
@@ -1296,6 +1305,11 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
else
ceph_clear_mount_opt(fsc, ASYNC_DIROPS);
+ if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
+ ceph_set_mount_opt(fsc, SPARSEREAD);
+ else
+ ceph_clear_mount_opt(fsc, SPARSEREAD);
+
if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) {
kfree(fsc->mount_options->mon_addr);
fsc->mount_options->mon_addr = fsopt->mon_addr;
@@ -42,6 +42,7 @@
#define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */
#define CEPH_MOUNT_OPT_ASYNC_DIROPS (1<<15) /* allow async directory ops */
#define CEPH_MOUNT_OPT_NOPAGECACHE (1<<16) /* bypass pagecache altogether */
+#define CEPH_MOUNT_OPT_SPARSEREAD (1<<17) /* always do sparse reads */
#define CEPH_MOUNT_OPT_DEFAULT \
(CEPH_MOUNT_OPT_DCACHE | \