/*
* rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
- * to a set of osds)
+ * to a set of osds) and primary_temp (explicit primary setting)
*/
static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
{
rb_erase(&pg->node, &map->pg_temp);
kfree(pg);
}
+ while (!RB_EMPTY_ROOT(&map->primary_temp)) {
+ struct ceph_pg_mapping *pg =
+ rb_entry(rb_first(&map->primary_temp),
+ struct ceph_pg_mapping, node);
+ rb_erase(&pg->node, &map->primary_temp);
+ kfree(pg);
+ }
while (!RB_EMPTY_ROOT(&map->pg_pools)) {
struct ceph_pg_pool_info *pi =
rb_entry(rb_first(&map->pg_pools),
kfree(map->osd_state);
kfree(map->osd_weight);
kfree(map->osd_addr);
+ kfree(map->osd_primary_affinity);
kfree(map);
}
map->osd_weight = weight;
map->osd_addr = addr;
+ if (map->osd_primary_affinity) {
+ u32 *affinity;
+
+ affinity = krealloc(map->osd_primary_affinity,
+ max*sizeof(*affinity), GFP_NOFS);
+ if (!affinity)
+ return -ENOMEM;
+
+ for (i = map->max_osd; i < max; i++)
+ affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+ map->osd_primary_affinity = affinity;
+ }
+
map->max_osd = max;
return 0;
}
+#define OSDMAP_WRAPPER_COMPAT_VER 7
+#define OSDMAP_CLIENT_DATA_COMPAT_VER 1
+
+/*
+ * Return 0 or error. On success, *v is set to 0 for old (v6) osdmaps,
+ * to struct_v of the client_data section for new (v7 and above)
+ * osdmaps.
+ */
+static int get_osdmap_client_data_v(void **p, void *end,
+ const char *prefix, u8 *v)
+{
+ u8 struct_v;
+
+ ceph_decode_8_safe(p, end, struct_v, e_inval);
+ if (struct_v >= 7) {
+ u8 struct_compat;
+
+ ceph_decode_8_safe(p, end, struct_compat, e_inval);
+ if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) {
+ pr_warning("got v %d cv %d > %d of %s ceph_osdmap\n",
+ struct_v, struct_compat,
+ OSDMAP_WRAPPER_COMPAT_VER, prefix);
+ return -EINVAL;
+ }
+ *p += 4; /* ignore wrapper struct_len */
+
+ ceph_decode_8_safe(p, end, struct_v, e_inval);
+ ceph_decode_8_safe(p, end, struct_compat, e_inval);
+ if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) {
+ pr_warning("got v %d cv %d > %d of %s ceph_osdmap client data\n",
+ struct_v, struct_compat,
+ OSDMAP_CLIENT_DATA_COMPAT_VER, prefix);
+ return -EINVAL;
+ }
+ *p += 4; /* ignore client data struct_len */
+ } else {
+ u16 version;
+
+ *p -= 1;
+ ceph_decode_16_safe(p, end, version, e_inval);
+ if (version < 6) {
+ pr_warning("got v %d < 6 of %s ceph_osdmap\n", version,
+ prefix);
+ return -EINVAL;
+ }
+
+ /* old osdmap enconding */
+ struct_v = 0;
+ }
+
+ *v = struct_v;
+ return 0;
+
+e_inval:
+ return -EINVAL;
+}
+
static int __decode_pools(void **p, void *end, struct ceph_osdmap *map,
bool incremental)
{
return -ENOMEM;
pg->pgid = pgid;
- pg->len = len;
+ pg->pg_temp.len = len;
for (i = 0; i < len; i++)
- pg->osds[i] = ceph_decode_32(p);
+ pg->pg_temp.osds[i] = ceph_decode_32(p);
ret = __insert_pg_mapping(pg, &map->pg_temp);
if (ret) {
return __decode_pg_temp(p, end, map, true);
}
+static int __decode_primary_temp(void **p, void *end, struct ceph_osdmap *map,
+ bool incremental)
+{
+ u32 n;
+
+ ceph_decode_32_safe(p, end, n, e_inval);
+ while (n--) {
+ struct ceph_pg pgid;
+ u32 osd;
+ int ret;
+
+ ret = ceph_decode_pgid(p, end, &pgid);
+ if (ret)
+ return ret;
+
+ ceph_decode_32_safe(p, end, osd, e_inval);
+
+ ret = __remove_pg_mapping(&map->primary_temp, pgid);
+ BUG_ON(!incremental && ret != -ENOENT);
+
+ if (!incremental || osd != (u32)-1) {
+ struct ceph_pg_mapping *pg;
+
+ pg = kzalloc(sizeof(*pg), GFP_NOFS);
+ if (!pg)
+ return -ENOMEM;
+
+ pg->pgid = pgid;
+ pg->primary_temp.osd = osd;
+
+ ret = __insert_pg_mapping(pg, &map->primary_temp);
+ if (ret) {
+ kfree(pg);
+ return ret;
+ }
+ }
+ }
+
+ return 0;
+
+e_inval:
+ return -EINVAL;
+}
+
+static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+ return __decode_primary_temp(p, end, map, false);
+}
+
+static int decode_new_primary_temp(void **p, void *end,
+ struct ceph_osdmap *map)
+{
+ return __decode_primary_temp(p, end, map, true);
+}
+
+u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
+{
+ BUG_ON(osd >= map->max_osd);
+
+ if (!map->osd_primary_affinity)
+ return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+ return map->osd_primary_affinity[osd];
+}
+
+static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff)
+{
+ BUG_ON(osd >= map->max_osd);
+
+ if (!map->osd_primary_affinity) {
+ int i;
+
+ map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32),
+ GFP_NOFS);
+ if (!map->osd_primary_affinity)
+ return -ENOMEM;
+
+ for (i = 0; i < map->max_osd; i++)
+ map->osd_primary_affinity[i] =
+ CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+ }
+
+ map->osd_primary_affinity[osd] = aff;
+
+ return 0;
+}
+
+static int decode_primary_affinity(void **p, void *end,
+ struct ceph_osdmap *map)
+{
+ u32 len, i;
+
+ ceph_decode_32_safe(p, end, len, e_inval);
+ if (len == 0) {
+ kfree(map->osd_primary_affinity);
+ map->osd_primary_affinity = NULL;
+ return 0;
+ }
+ if (len != map->max_osd)
+ goto e_inval;
+
+ ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval);
+
+ for (i = 0; i < map->max_osd; i++) {
+ int ret;
+
+ ret = set_primary_affinity(map, i, ceph_decode_32(p));
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+
+e_inval:
+ return -EINVAL;
+}
+
+static int decode_new_primary_affinity(void **p, void *end,
+ struct ceph_osdmap *map)
+{
+ u32 n;
+
+ ceph_decode_32_safe(p, end, n, e_inval);
+ while (n--) {
+ u32 osd, aff;
+ int ret;
+
+ ceph_decode_32_safe(p, end, osd, e_inval);
+ ceph_decode_32_safe(p, end, aff, e_inval);
+
+ ret = set_primary_affinity(map, osd, aff);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+
+e_inval:
+ return -EINVAL;
+}
+
/*
* decode a full map.
*/
static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
{
- u16 version;
+ u8 struct_v;
u32 epoch = 0;
void *start = *p;
u32 max;
dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
- ceph_decode_16_safe(p, end, version, e_inval);
- if (version > 6) {
- pr_warning("got unknown v %d > 6 of osdmap\n", version);
- goto e_inval;
- }
- if (version < 6) {
- pr_warning("got old v %d < 6 of osdmap\n", version);
- goto e_inval;
- }
+ err = get_osdmap_client_data_v(p, end, "full", &struct_v);
+ if (err)
+ goto bad;
/* fsid, epoch, created, modified */
ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) +
if (err)
goto bad;
+ /* primary_temp */
+ if (struct_v >= 1) {
+ err = decode_primary_temp(p, end, map);
+ if (err)
+ goto bad;
+ }
+
+ /* primary_affinity */
+ if (struct_v >= 2) {
+ err = decode_primary_affinity(p, end, map);
+ if (err)
+ goto bad;
+ } else {
+ /* XXX can this happen? */
+ kfree(map->osd_primary_affinity);
+ map->osd_primary_affinity = NULL;
+ }
+
/* crush */
ceph_decode_32_safe(p, end, len, e_inval);
map->crush = crush_decode(*p, min(*p + len, end));
return ERR_PTR(-ENOMEM);
map->pg_temp = RB_ROOT;
+ map->primary_temp = RB_ROOT;
mutex_init(&map->crush_scratch_mutex);
ret = osdmap_decode(p, end, map);
__s32 new_flags, max;
void *start = *p;
int err;
- u16 version;
+ u8 struct_v;
dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
- ceph_decode_16_safe(p, end, version, e_inval);
- if (version != 6) {
- pr_warning("got unknown v %d != 6 of inc osdmap\n", version);
- goto e_inval;
- }
+ err = get_osdmap_client_data_v(p, end, "inc", &struct_v);
+ if (err)
+ goto bad;
/* fsid, epoch, modified, new_pool_max, new_flags */
ceph_decode_need(p, end, sizeof(fsid) + sizeof(u32) + sizeof(modified) +
if (err)
goto bad;
+ /* new_primary_temp */
+ if (struct_v >= 1) {
+ err = decode_new_primary_temp(p, end, map);
+ if (err)
+ goto bad;
+ }
+
+ /* new_primary_affinity */
+ if (struct_v >= 2) {
+ err = decode_new_primary_affinity(p, end, map);
+ if (err)
+ goto bad;
+ }
+
/* ignore the rest */
*p = end;
pool->pg_num_mask);
pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
if (pg) {
- *num = pg->len;
- return pg->osds;
+ *num = pg->pg_temp.len;
+ return pg->pg_temp.osds;
}
/* crush */
}
/*
- * Return acting set for given pgid.
+ * Calculate raw (crush) set for given pgid.
+ *
+ * Return raw set length, or error.
+ */
+static int pg_to_raw_osds(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pool,
+ struct ceph_pg pgid, u32 pps, int *osds)
+{
+ int ruleno;
+ int len;
+
+ /* crush */
+ ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
+ pool->type, pool->size);
+ if (ruleno < 0) {
+ pr_err("no crush rule: pool %lld ruleset %d type %d size %d\n",
+ pgid.pool, pool->crush_ruleset, pool->type,
+ pool->size);
+ return -ENOENT;
+ }
+
+ len = do_crush(osdmap, ruleno, pps, osds,
+ min_t(int, pool->size, CEPH_PG_MAX_SIZE),
+ osdmap->osd_weight, osdmap->max_osd);
+ if (len < 0) {
+ pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n",
+ len, ruleno, pgid.pool, pool->crush_ruleset,
+ pool->type, pool->size);
+ return len;
+ }
+
+ return len;
+}
+
+/*
+ * Given raw set, calculate up set and up primary.
+ *
+ * Return up set length. *primary is set to up primary osd id, or -1
+ * if up set is empty.
+ */
+static int raw_to_up_osds(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pool,
+ int *osds, int len, int *primary)
+{
+ int up_primary = -1;
+ int i;
+
+ if (ceph_can_shift_osds(pool)) {
+ int removed = 0;
+
+ for (i = 0; i < len; i++) {
+ if (ceph_osd_is_down(osdmap, osds[i])) {
+ removed++;
+ continue;
+ }
+ if (removed)
+ osds[i - removed] = osds[i];
+ }
+
+ len -= removed;
+ if (len > 0)
+ up_primary = osds[0];
+ } else {
+ for (i = len - 1; i >= 0; i--) {
+ if (ceph_osd_is_down(osdmap, osds[i]))
+ osds[i] = CRUSH_ITEM_NONE;
+ else
+ up_primary = osds[i];
+ }
+ }
+
+ *primary = up_primary;
+ return len;
+}
+
+/*
+ * Given up set, apply pg_temp and primary_temp mappings.
+ *
+ * Return acting set length. *primary is set to acting primary osd id,
+ * or -1 if acting set is empty.
+ */
+static int apply_temps(struct ceph_osdmap *osdmap,
+ struct ceph_pg_pool_info *pool, struct ceph_pg pgid,
+ int *osds, int len, int *primary)
+{
+ struct ceph_pg_mapping *pg;
+ int temp_len;
+ int temp_primary;
+ int i;
+
+ /* raw_pg -> pg */
+ pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
+ pool->pg_num_mask);
+
+ /* pg_temp? */
+ pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
+ if (pg) {
+ temp_len = 0;
+ temp_primary = -1;
+
+ for (i = 0; i < pg->pg_temp.len; i++) {
+ if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) {
+ if (ceph_can_shift_osds(pool))
+ continue;
+ else
+ osds[temp_len++] = CRUSH_ITEM_NONE;
+ } else {
+ osds[temp_len++] = pg->pg_temp.osds[i];
+ }
+ }
+
+ /* apply pg_temp's primary */
+ for (i = 0; i < temp_len; i++) {
+ if (osds[i] != CRUSH_ITEM_NONE) {
+ temp_primary = osds[i];
+ break;
+ }
+ }
+ } else {
+ temp_len = len;
+ temp_primary = *primary;
+ }
+
+ /* primary_temp? */
+ pg = __lookup_pg_mapping(&osdmap->primary_temp, pgid);
+ if (pg)
+ temp_primary = pg->primary_temp.osd;
+
+ *primary = temp_primary;
+ return temp_len;
+}
+
+/*
+ * Calculate acting set for given pgid.
+ *
+ * Return acting set length, or error. *primary is set to acting
+ * primary osd id, or -1 if acting set is empty or on error.
*/
int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
- int *acting)
+ int *osds, int *primary)
{
- int rawosds[CEPH_PG_MAX_SIZE], *osds;
- int i, o, num = CEPH_PG_MAX_SIZE;
+ struct ceph_pg_pool_info *pool;
+ u32 pps;
+ int len;
- osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
- if (!osds)
- return -1;
+ pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
+ if (!pool) {
+ *primary = -1;
+ return -ENOENT;
+ }
- /* primary is first up osd */
- o = 0;
- for (i = 0; i < num; i++)
- if (ceph_osd_is_up(osdmap, osds[i]))
- acting[o++] = osds[i];
- return o;
+ if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
+ /* hash pool id and seed so that pool PGs do not overlap */
+ pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
+ ceph_stable_mod(pgid.seed, pool->pgp_num,
+ pool->pgp_num_mask),
+ pgid.pool);
+ } else {
+ /*
+ * legacy behavior: add ps and pool together. this is
+ * not a great approach because the PGs from each pool
+ * will overlap on top of each other: 0.5 == 1.4 ==
+ * 2.3 == ...
+ */
+ pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
+ pool->pgp_num_mask) +
+ (unsigned)pgid.pool;
+ }
+
+ len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
+ if (len < 0) {
+ *primary = -1;
+ return len;
+ }
+
+ len = raw_to_up_osds(osdmap, pool, osds, len, primary);
+
+ len = apply_temps(osdmap, pool, pgid, osds, len, primary);
+
+ return len;
}
/*
projects / firefly-linux-kernel-4.4.55.git / blobdiff