diff options
author | Jeff Layton <jlayton@kernel.org> | 2022-02-11 11:38:02 -0500 |
---|---|---|
committer | Ilya Dryomov <idryomov@gmail.com> | 2023-08-22 09:01:47 +0200 |
commit | f628d799972799023d32c2542bb2639eb8c4f84e (patch) | |
tree | f6ae659115e694ff6d5f7b5c4701c5df22e4fc6b /include/linux/ceph | |
parent | d396f89db39a2f259e2125ca43b4c31bb65afcad (diff) |
libceph: add sparse read support to OSD client
Have get_reply check for the presence of sparse read ops in the
request and set the sparse_read boolean in the msg. That will queue the
messenger layer to use the sparse read codepath instead of the normal
data receive.
Add a new sparse_read operation for the OSD client, driven by its own
state machine. The messenger will repeatedly call the sparse_read
operation, and it will pass back the necessary info to set up to read
the next extent of data, while zero-filling the sparse regions.
The state machine will stop at the end of the last extent, and will
attach the extent map buffer to the ceph_osd_req_op so that the caller
can use it.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'include/linux/ceph')
-rw-r--r-- | include/linux/ceph/osd_client.h | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 05da1e755b7b..bfa4813590da 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -40,6 +40,36 @@ struct ceph_sparse_extent { u64 len; } __packed; +/* Sparse read state machine state values */ +enum ceph_sparse_read_state { + CEPH_SPARSE_READ_HDR = 0, + CEPH_SPARSE_READ_EXTENTS, + CEPH_SPARSE_READ_DATA_LEN, + CEPH_SPARSE_READ_DATA, +}; + +/* + * A SPARSE_READ reply is a 32-bit count of extents, followed by an array of + * 64-bit offset/length pairs, and then all of the actual file data + * concatenated after it (sans holes). + * + * Unfortunately, we don't know how long the extent array is until we've + * started reading the data section of the reply. The caller should send down + * a destination buffer for the array, but we'll alloc one if it's too small + * or if the caller doesn't. + */ +struct ceph_sparse_read { + enum ceph_sparse_read_state sr_state; /* state machine state */ + u64 sr_req_off; /* orig request offset */ + u64 sr_req_len; /* orig request length */ + u64 sr_pos; /* current pos in buffer */ + int sr_index; /* current extent index */ + __le32 sr_datalen; /* length of actual data */ + u32 sr_count; /* extent count in reply */ + int sr_ext_len; /* length of extent array */ + struct ceph_sparse_extent *sr_extent; /* extent array */ +}; + /* * A given osd we're communicating with. * @@ -48,6 +78,7 @@ struct ceph_sparse_extent { */ struct ceph_osd { refcount_t o_ref; + int o_sparse_op_idx; struct ceph_osd_client *o_osdc; int o_osd; int o_incarnation; @@ -63,6 +94,7 @@ struct ceph_osd { unsigned long lru_ttl; struct list_head o_keepalive_item; struct mutex lock; + struct ceph_sparse_read o_sparse_read; }; #define CEPH_OSD_SLAB_OPS 2 |