Merge git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
Pull ceph updates from Sage Weil:
"There are some updates and cleanups to the CRUSH placement code, a bug
fix with incremental maps, several cleanups and fixes from Josh Durgin
in the RBD block device code, a series of cleanups and bug fixes from
Alex Elder in the messenger code, and some miscellaneous bounds
checking and gfp cleanups/fixes."
Fix up trivial conflicts in net/ceph/{messenger.c,osdmap.c} due to the
networking people preferring "unsigned int" over just "unsigned".
* git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (45 commits)
libceph: fix pg_temp updates
libceph: avoid unregistering osd request when not registered
ceph: add auth buf in prepare_write_connect()
ceph: rename prepare_connect_authorizer()
ceph: return pointer from prepare_connect_authorizer()
ceph: use info returned by get_authorizer
ceph: have get_authorizer methods return pointers
ceph: ensure auth ops are defined before use
ceph: messenger: reduce args to create_authorizer
ceph: define ceph_auth_handshake type
ceph: messenger: check return from get_authorizer
ceph: messenger: rework prepare_connect_authorizer()
ceph: messenger: check prepare_write_connect() result
ceph: don't set WRITE_PENDING too early
ceph: drop msgr argument from prepare_write_connect()
ceph: messenger: send banner in process_connect()
ceph: messenger: reset connection kvec caller
libceph: don't reset kvec in prepare_write_banner()
ceph: ignore preferred_osd field
ceph: fully initialize new layout
...
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 56e561a..81e3b84 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -161,13 +161,6 @@
c->max_rules = ceph_decode_32(p);
c->max_devices = ceph_decode_32(p);
- c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS);
- if (c->device_parents == NULL)
- goto badmem;
- c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS);
- if (c->bucket_parents == NULL)
- goto badmem;
-
c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS);
if (c->buckets == NULL)
goto badmem;
@@ -890,8 +883,12 @@
pglen = ceph_decode_32(p);
if (pglen) {
- /* insert */
ceph_decode_need(p, end, pglen*sizeof(u32), bad);
+
+ /* removing existing (if any) */
+ (void) __remove_pg_mapping(&map->pg_temp, pgid);
+
+ /* insert */
pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
if (!pg) {
err = -ENOMEM;
@@ -1000,7 +997,6 @@
{
unsigned int num, num_mask;
struct ceph_pg pgid;
- s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred);
int poolid = le32_to_cpu(fl->fl_pg_pool);
struct ceph_pg_pool_info *pool;
unsigned int ps;
@@ -1011,23 +1007,13 @@
if (!pool)
return -EIO;
ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid));
- if (preferred >= 0) {
- ps += preferred;
- num = le32_to_cpu(pool->v.lpg_num);
- num_mask = pool->lpg_num_mask;
- } else {
- num = le32_to_cpu(pool->v.pg_num);
- num_mask = pool->pg_num_mask;
- }
+ num = le32_to_cpu(pool->v.pg_num);
+ num_mask = pool->pg_num_mask;
pgid.ps = cpu_to_le16(ps);
- pgid.preferred = cpu_to_le16(preferred);
+ pgid.preferred = cpu_to_le16(-1);
pgid.pool = fl->fl_pg_pool;
- if (preferred >= 0)
- dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps,
- (int)preferred);
- else
- dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps);
+ dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps);
ol->ol_pgid = pgid;
ol->ol_stripe_unit = fl->fl_object_stripe_unit;
@@ -1045,24 +1031,18 @@
struct ceph_pg_mapping *pg;
struct ceph_pg_pool_info *pool;
int ruleno;
- unsigned int poolid, ps, pps, t;
- int preferred;
+ unsigned int poolid, ps, pps, t, r;
poolid = le32_to_cpu(pgid.pool);
ps = le16_to_cpu(pgid.ps);
- preferred = (s16)le16_to_cpu(pgid.preferred);
pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
if (!pool)
return NULL;
/* pg_temp? */
- if (preferred >= 0)
- t = ceph_stable_mod(ps, le32_to_cpu(pool->v.lpg_num),
- pool->lpgp_num_mask);
- else
- t = ceph_stable_mod(ps, le32_to_cpu(pool->v.pg_num),
- pool->pgp_num_mask);
+ t = ceph_stable_mod(ps, le32_to_cpu(pool->v.pg_num),
+ pool->pgp_num_mask);
pgid.ps = cpu_to_le16(t);
pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
if (pg) {
@@ -1080,23 +1060,20 @@
return NULL;
}
- /* don't forcefeed bad device ids to crush */
- if (preferred >= osdmap->max_osd ||
- preferred >= osdmap->crush->max_devices)
- preferred = -1;
-
- if (preferred >= 0)
- pps = ceph_stable_mod(ps,
- le32_to_cpu(pool->v.lpgp_num),
- pool->lpgp_num_mask);
- else
- pps = ceph_stable_mod(ps,
- le32_to_cpu(pool->v.pgp_num),
- pool->pgp_num_mask);
+ pps = ceph_stable_mod(ps,
+ le32_to_cpu(pool->v.pgp_num),
+ pool->pgp_num_mask);
pps += poolid;
- *num = crush_do_rule(osdmap->crush, ruleno, pps, osds,
- min_t(int, pool->v.size, *num),
- preferred, osdmap->osd_weight);
+ r = crush_do_rule(osdmap->crush, ruleno, pps, osds,
+ min_t(int, pool->v.size, *num),
+ osdmap->osd_weight);
+ if (r < 0) {
+ pr_err("error %d from crush rule: pool %d ruleset %d type %d"
+ " size %d\n", r, poolid, pool->v.crush_ruleset,
+ pool->v.type, pool->v.size);
+ return NULL;
+ }
+ *num = r;
return osds;
}