summaryrefslogtreecommitdiffstats
path: root/net/ceph
diff options
context:
space:
mode:
authorIlya Dryomov <idryomov@gmail.com>2017-06-21 17:27:18 +0200
committerIlya Dryomov <idryomov@gmail.com>2017-07-07 17:25:18 +0200
commit1c2e7b451b889bead46cef410a737d1767cd6f0b (patch)
treefeed3db675b4019f726ebb5dd68423022abae9bc /net/ceph
parent463bb8da5042c165bf50ae2688d251c5af26f3cf (diff)
downloadlinux-1c2e7b451b889bead46cef410a737d1767cd6f0b.tar.bz2
libceph: apply_upmap()
Previously, pg_to_raw_osds() didn't filter for existent OSDs because raw_to_up_osds() would filter for "up" ("up" is predicated on "exists") and raw_to_up_osds() was called directly after pg_to_raw_osds(). Now, with apply_upmap() call in there, nonexistent OSDs in pg_to_raw_osds() output can affect apply_upmap(). Introduce remove_nonexistent_osds() to deal with that. Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'net/ceph')
-rw-r--r--net/ceph/osdmap.c97
1 files changed, 95 insertions, 2 deletions
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 245c8025ab44..93baa69407c5 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -2117,9 +2117,37 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
return r;
}
+static void remove_nonexistent_osds(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pi,
+ struct ceph_osds *set)
+{
+ int i;
+
+ if (ceph_can_shift_osds(pi)) {
+ int removed = 0;
+
+ /* shift left */
+ for (i = 0; i < set->size; i++) {
+ if (!ceph_osd_exists(osdmap, set->osds[i])) {
+ removed++;
+ continue;
+ }
+ if (removed)
+ set->osds[i - removed] = set->osds[i];
+ }
+ set->size -= removed;
+ } else {
+ /* set dne devices to NONE */
+ for (i = 0; i < set->size; i++) {
+ if (!ceph_osd_exists(osdmap, set->osds[i]))
+ set->osds[i] = CRUSH_ITEM_NONE;
+ }
+ }
+}
+
/*
- * Calculate raw set (CRUSH output) for given PG. The result may
- * contain nonexistent OSDs. ->primary is undefined for a raw set.
+ * Calculate raw set (CRUSH output) for given PG and filter out
+ * nonexistent OSDs. ->primary is undefined for a raw set.
*
* Placement seed (CRUSH input) is returned through @ppps.
*/
@@ -2162,6 +2190,70 @@ static void pg_to_raw_osds(struct ceph_osdmap *osdmap,
}
raw->size = len;
+ remove_nonexistent_osds(osdmap, pi, raw);
+}
+
+/* apply pg_upmap[_items] mappings */
+static void apply_upmap(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *pgid,
+ struct ceph_osds *raw)
+{
+ struct ceph_pg_mapping *pg;
+ int i, j;
+
+ pg = lookup_pg_mapping(&osdmap->pg_upmap, pgid);
+ if (pg) {
+ /* make sure targets aren't marked out */
+ for (i = 0; i < pg->pg_upmap.len; i++) {
+ int osd = pg->pg_upmap.osds[i];
+
+ if (osd != CRUSH_ITEM_NONE &&
+ osd < osdmap->max_osd &&
+ osdmap->osd_weight[osd] == 0) {
+ /* reject/ignore explicit mapping */
+ return;
+ }
+ }
+ for (i = 0; i < pg->pg_upmap.len; i++)
+ raw->osds[i] = pg->pg_upmap.osds[i];
+ raw->size = pg->pg_upmap.len;
+ return;
+ }
+
+ pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid);
+ if (pg) {
+ /*
+ * Note: this approach does not allow a bidirectional swap,
+ * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1].
+ */
+ for (i = 0; i < pg->pg_upmap_items.len; i++) {
+ int from = pg->pg_upmap_items.from_to[i][0];
+ int to = pg->pg_upmap_items.from_to[i][1];
+ int pos = -1;
+ bool exists = false;
+
+ /* make sure replacement doesn't already appear */
+ for (j = 0; j < raw->size; j++) {
+ int osd = raw->osds[j];
+
+ if (osd == to) {
+ exists = true;
+ break;
+ }
+ /* ignore mapping if target is marked out */
+ if (osd == from && pos < 0 &&
+ !(to != CRUSH_ITEM_NONE &&
+ to < osdmap->max_osd &&
+ osdmap->osd_weight[to] == 0)) {
+ pos = j;
+ }
+ }
+ if (!exists && pos >= 0) {
+ raw->osds[pos] = to;
+ return;
+ }
+ }
+ }
}
/*
@@ -2341,6 +2433,7 @@ void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
raw_pg_to_pg(pi, raw_pgid, &pgid);
pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps);
+ apply_upmap(osdmap, &pgid, up);
raw_to_up_osds(osdmap, pi, up);
apply_primary_affinity(osdmap, pi, pps, up);
get_temp_osds(osdmap, pi, &pgid, acting);