summaryrefslogtreecommitdiffstats
path: root/net/ceph/osd_client.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-04-07 11:09:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-04-07 11:09:13 -0700
commit240cd6a817bd855e3f1e615ed9ae16407f8cfce6 (patch)
treeda7d6267d549cd0fbdff3f30032720b416d1ff3d /net/ceph/osd_client.c
parent3021112598d2b722eee54d8a662fea2089abbdbc (diff)
parenta30be7cb2ccb995ad5e67fd4b548f11fe37fc8b1 (diff)
downloadlinux-240cd6a817bd855e3f1e615ed9ae16407f8cfce6.tar.bz2
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
Pull Ceph updates from Sage Weil: "The biggest chunk is a series of patches from Ilya that add support for new Ceph osd and crush map features, including some new tunables, primary affinity, and the new encoding that is needed for erasure coding support. This brings things into parity with the server side and the looming firefly release. There is also support for allocation hints in RBD that help limit fragmentation on the server side. There is also a series of patches from Zheng fixing NFS reexport, directory fragmentation support, flock vs fnctl behavior, and some issues with clustered MDS. Finally, there are some miscellaneous fixes from Yunchuan Wen for fscache, Fabian Frederick for ACLs, and from me for fsync(dirfd) behavior" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (79 commits) ceph: skip invalid dentry during dcache readdir libceph: dump pool {read,write}_tier to debugfs libceph: output primary affinity values on osdmap updates ceph: flush cap release queue when trimming session caps ceph: don't grabs open file reference for aborted request ceph: drop extra open file reference in ceph_atomic_open() ceph: preallocate buffer for readdir reply libceph: enable PRIMARY_AFFINITY feature bit libceph: redo ceph_calc_pg_primary() in terms of ceph_calc_pg_acting() libceph: add support for osd primary affinity libceph: add support for primary_temp mappings libceph: return primary from ceph_calc_pg_acting() libceph: switch ceph_calc_pg_acting() to new helpers libceph: introduce apply_temps() helper libceph: introduce pg_to_raw_osds() and raw_to_up_osds() helpers libceph: ceph_can_shift_osds(pool) and pool type defines libceph: ceph_osd_{exists,is_up,is_down}(osd) definitions libceph: enable OSDMAP_ENC feature bit libceph: primary_affinity decode bits libceph: primary_affinity infrastructure ...
Diffstat (limited to 'net/ceph/osd_client.c')
-rw-r--r--net/ceph/osd_client.c41
1 files changed, 34 insertions, 7 deletions
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 82750f915865..b0dfce77656a 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -436,6 +436,7 @@ static bool osd_req_opcode_valid(u16 opcode)
case CEPH_OSD_OP_OMAPCLEAR:
case CEPH_OSD_OP_OMAPRMKEYS:
case CEPH_OSD_OP_OMAP_CMP:
+ case CEPH_OSD_OP_SETALLOCHINT:
case CEPH_OSD_OP_CLONERANGE:
case CEPH_OSD_OP_ASSERT_SRC_VERSION:
case CEPH_OSD_OP_SRC_CMPXATTR:
@@ -591,6 +592,26 @@ void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
}
EXPORT_SYMBOL(osd_req_op_watch_init);
+void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+ unsigned int which,
+ u64 expected_object_size,
+ u64 expected_write_size)
+{
+ struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+ CEPH_OSD_OP_SETALLOCHINT);
+
+ op->alloc_hint.expected_object_size = expected_object_size;
+ op->alloc_hint.expected_write_size = expected_write_size;
+
+ /*
+ * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed
+ * not worth a feature bit. Set FAILOK per-op flag to make
+ * sure older osds don't trip over an unsupported opcode.
+ */
+ op->flags |= CEPH_OSD_OP_FLAG_FAILOK;
+}
+EXPORT_SYMBOL(osd_req_op_alloc_hint_init);
+
static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
struct ceph_osd_data *osd_data)
{
@@ -681,6 +702,12 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
dst->watch.ver = cpu_to_le64(src->watch.ver);
dst->watch.flag = src->watch.flag;
break;
+ case CEPH_OSD_OP_SETALLOCHINT:
+ dst->alloc_hint.expected_object_size =
+ cpu_to_le64(src->alloc_hint.expected_object_size);
+ dst->alloc_hint.expected_write_size =
+ cpu_to_le64(src->alloc_hint.expected_write_size);
+ break;
default:
pr_err("unsupported osd opcode %s\n",
ceph_osd_op_name(src->op));
@@ -688,7 +715,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
return 0;
}
+
dst->op = cpu_to_le16(src->op);
+ dst->flags = cpu_to_le32(src->flags);
dst->payload_len = cpu_to_le32(src->payload_len);
return request_data_len;
@@ -1304,7 +1333,7 @@ static int __map_request(struct ceph_osd_client *osdc,
{
struct ceph_pg pgid;
int acting[CEPH_PG_MAX_SIZE];
- int o = -1, num = 0;
+ int num, o;
int err;
bool was_paused;
@@ -1317,11 +1346,9 @@ static int __map_request(struct ceph_osd_client *osdc,
}
req->r_pgid = pgid;
- err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting);
- if (err > 0) {
- o = acting[0];
- num = err;
- }
+ num = ceph_calc_pg_acting(osdc->osdmap, pgid, acting, &o);
+ if (num < 0)
+ num = 0;
was_paused = req->r_paused;
req->r_paused = __req_should_be_paused(osdc, req);
@@ -2033,7 +2060,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
int skipped_map = 0;
dout("taking full map %u len %d\n", epoch, maplen);
- newmap = osdmap_decode(&p, p+maplen);
+ newmap = ceph_osdmap_decode(&p, p+maplen);
if (IS_ERR(newmap)) {
err = PTR_ERR(newmap);
goto bad;