libceph: rados pool namespace support
Add pool namesapce pointer to struct ceph_file_layout and struct
ceph_object_locator. Pool namespace is used by when mapping object
to PG, it's also used when composing OSD request.
The namespace pointer in struct ceph_file_layout is RCU protected.
So libceph can read namespace without taking lock.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
[idryomov@gmail.com: ceph_oloc_destroy(), misc minor changes]
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 23efcac..b68cc15 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -387,7 +387,9 @@
static void target_destroy(struct ceph_osd_request_target *t)
{
ceph_oid_destroy(&t->base_oid);
+ ceph_oloc_destroy(&t->base_oloc);
ceph_oid_destroy(&t->target_oid);
+ ceph_oloc_destroy(&t->target_oloc);
}
/*
@@ -533,6 +535,11 @@
}
EXPORT_SYMBOL(ceph_osdc_alloc_request);
+static int ceph_oloc_encoding_size(struct ceph_object_locator *oloc)
+{
+ return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
+}
+
int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
{
struct ceph_osd_client *osdc = req->r_osdc;
@@ -540,11 +547,13 @@
int msg_size;
WARN_ON(ceph_oid_empty(&req->r_base_oid));
+ WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
/* create request message */
msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
- msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */
+ msg_size += CEPH_ENCODING_START_BLK_LEN +
+ ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */
msg_size += 1 + 8 + 4 + 4; /* pgid */
msg_size += 4 + req->r_base_oid.name_len; /* oid */
msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
@@ -949,6 +958,7 @@
req->r_flags = flags;
req->r_base_oloc.pool = layout->pool_id;
+ req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
req->r_snapid = vino.snap;
@@ -1489,12 +1499,16 @@
p += sizeof(req->r_replay_version);
/* oloc */
- ceph_encode_8(&p, 4);
- ceph_encode_8(&p, 4);
- ceph_encode_32(&p, 8 + 4 + 4);
+ ceph_start_encoding(&p, 5, 4,
+ ceph_oloc_encoding_size(&req->r_t.target_oloc));
ceph_encode_64(&p, req->r_t.target_oloc.pool);
ceph_encode_32(&p, -1); /* preferred */
ceph_encode_32(&p, 0); /* key len */
+ if (req->r_t.target_oloc.pool_ns)
+ ceph_encode_string(&p, end, req->r_t.target_oloc.pool_ns->str,
+ req->r_t.target_oloc.pool_ns->len);
+ else
+ ceph_encode_32(&p, 0);
/* pgid */
ceph_encode_8(&p, 1);
@@ -2596,8 +2610,8 @@
if (struct_v >= 5) {
len = ceph_decode_32(p);
if (len > 0) {
- pr_warn("ceph_object_locator::nspace is set\n");
- goto e_inval;
+ ceph_decode_need(p, end, len, e_inval);
+ *p += len;
}
}
@@ -2835,7 +2849,11 @@
unlink_request(osd, req);
mutex_unlock(&osd->lock);
- ceph_oloc_copy(&req->r_t.target_oloc, &m.redirect.oloc);
+ /*
+ * Not ceph_oloc_copy() - changing pool_ns is not
+ * supported.
+ */
+ req->r_t.target_oloc.pool = m.redirect.oloc.pool;
req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
req->r_tid = 0;
__submit_request(req, false);
