From 66a0e2d579dbec5c676cfe446234ffebb267c564 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 31 Jan 2017 15:55:06 +0100 Subject: crush: remove mutable part of CRUSH map Then add it to the working state. It would be very nice if we didn't have to take a lock to calculate a crush placement. By moving the permutation array into the working data, we can treat the CRUSH map as immutable. Reflects ceph.git commit cbcd039651c0569551cb90d26ce27e1432671f2a. Signed-off-by: Ilya Dryomov --- net/ceph/osdmap.c | 47 ++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 42 insertions(+), 5 deletions(-) (limited to 'net/ceph/osdmap.c') diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 47df075b31e5..3892e7fa7747 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -153,6 +153,32 @@ bad: return -EINVAL; } +static void crush_finalize(struct crush_map *c) +{ + __s32 b; + + /* Space for the array of pointers to per-bucket workspace */ + c->working_size = sizeof(struct crush_work) + + c->max_buckets * sizeof(struct crush_work_bucket *); + + for (b = 0; b < c->max_buckets; b++) { + if (!c->buckets[b]) + continue; + + switch (c->buckets[b]->alg) { + default: + /* + * The base case, permutation variables and + * the pointer to the permutation array. + */ + c->working_size += sizeof(struct crush_work_bucket); + break; + } + /* Every bucket has a permutation array. */ + c->working_size += c->buckets[b]->size * sizeof(__u32); + } +} + static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; @@ -246,10 +272,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS); if (b->items == NULL) goto badmem; - b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS); - if (b->perm == NULL) - goto badmem; - b->perm_n = 0; ceph_decode_need(p, end, b->size*sizeof(u32), bad); for (j = 0; j < b->size; j++) @@ -368,6 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable chooseleaf_stable = %d\n", c->chooseleaf_stable); + crush_finalize(c); + done: dout("crush_decode success\n"); return c; @@ -753,6 +777,7 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) kfree(map->osd_weight); kfree(map->osd_addr); kfree(map->osd_primary_affinity); + kfree(map->crush_workspace); kfree(map); } @@ -810,12 +835,23 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush) { + void *workspace; + if (IS_ERR(crush)) return PTR_ERR(crush); + workspace = kmalloc(crush->working_size, GFP_NOIO); + if (!workspace) { + crush_destroy(crush); + return -ENOMEM; + } + crush_init_workspace(crush, workspace); + if (map->crush) crush_destroy(map->crush); + kfree(map->crush_workspace); map->crush = crush; + map->crush_workspace = workspace; return 0; } @@ -1940,7 +1976,8 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x, mutex_lock(&map->crush_scratch_mutex); r = crush_do_rule(map->crush, ruleno, x, result, result_max, - weight, weight_max, map->crush_scratch_ary); + weight, weight_max, map->crush_workspace, + map->crush_scratch_ary); mutex_unlock(&map->crush_scratch_mutex); return r; -- cgit v1.2.3