libceph: support crush tunables

The server side recently added support for tuning some magic
crush variables. Decode these variables if they are present, or use the
default values if they are not present.

Corresponds to ceph.git commit 89af369c25f274fe62ef730e5e8aad0c54f1e5a5.

Signed-off-by: caleb miles <caleb.miles@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 342f93dbe16219fbd0ded415dfae4615fe6f11c2..dad579b0c0e65981ea42c7a820f71e0480154b17 100644 (file)
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -12,12 +12,15 @@
 #define CEPH_FEATURE_MONNAMES       (1<<5)
 #define CEPH_FEATURE_RECONNECT_SEQ  (1<<6)
 #define CEPH_FEATURE_DIRLAYOUTHASH  (1<<7)
+/* bits 8-17 defined by user-space; not supported yet here */
+#define CEPH_FEATURE_CRUSH_TUNABLES (1<<18)
 
 /*
  * Features supported.
  */
 #define CEPH_FEATURES_SUPPORTED_DEFAULT  \
-       (CEPH_FEATURE_NOSRCADDR)
+       (CEPH_FEATURE_NOSRCADDR |        \
+        CEPH_FEATURE_CRUSH_TUNABLES)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
        (CEPH_FEATURE_NOSRCADDR)

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 7c4750811b966e7d865484c2cf7020199c628164..25baa287cff7287d8e6cc6f5b94255ef4cf86f9e 100644 (file)
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -154,6 +154,14 @@ struct crush_map {
        __s32 max_buckets;
        __u32 max_rules;
        __s32 max_devices;
+
+       /* choose local retries before re-descent */
+       __u32 choose_local_tries;
+       /* choose local attempts using a fallback permutation before
+        * re-descent */
+       __u32 choose_local_fallback_tries;
+       /* choose attempts before giving up */ 
+       __u32 choose_total_tries;
 };
 
 

diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index d7edc24333b84d5aab17da2d983878ff5044b2bb..35fce755ce103528071d422ca6e9ca2e0faf6a27 100644 (file)
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -306,7 +306,6 @@ static int crush_choose(const struct crush_map *map,
        int item = 0;
        int itemtype;
        int collide, reject;
-       const unsigned int orig_tries = 5; /* attempts before we fall back to search */
 
        dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
                bucket->id, x, outpos, numrep);
@@ -351,8 +350,9 @@ static int crush_choose(const struct crush_map *map,
                                        reject = 1;
                                        goto reject;
                                }
-                               if (flocal >= (in->size>>1) &&
-                                   flocal > orig_tries)
+                               if (map->choose_local_fallback_tries > 0 &&
+                                   flocal >= (in->size>>1) &&
+                                   flocal > map->choose_local_fallback_tries)
                                        item = bucket_perm_choose(in, x, r);
                                else
                                        item = crush_bucket_choose(in, x, r);
@@ -422,13 +422,14 @@ reject:
                                        ftotal++;
                                        flocal++;
 
-                                       if (collide && flocal < 3)
+                                       if (collide && flocal <= map->choose_local_tries)
                                                /* retry locally a few times */
                                                retry_bucket = 1;
-                                       else if (flocal <= in->size + orig_tries)
+                                       else if (map->choose_local_fallback_tries > 0 &&
+                                                flocal <= in->size + map->choose_local_fallback_tries)
                                                /* exhaustive bucket search */
                                                retry_bucket = 1;
-                                       else if (ftotal < 20)
+                                       else if (ftotal <= map->choose_total_tries)
                                                /* then retry descent */
                                                retry_descent = 1;
                                        else

diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 9600674c2c3978fc79912235d7cdb708a572501c..3124b71a888362910f96efec9bca0104f84dba5d 100644 (file)
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -135,6 +135,21 @@ bad:
        return -EINVAL;
 }
 
+static int skip_name_map(void **p, void *end)
+{
+        int len;
+        ceph_decode_32_safe(p, end, len ,bad);
+        while (len--) {
+                int strlen;
+                *p += sizeof(u32);
+                ceph_decode_32_safe(p, end, strlen, bad);
+                *p += strlen;
+}
+        return 0;
+bad:
+        return -EINVAL;
+}
+
 static struct crush_map *crush_decode(void *pbyval, void *end)
 {
        struct crush_map *c;
@@ -143,6 +158,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
        void **p = &pbyval;
        void *start = pbyval;
        u32 magic;
+       u32 num_name_maps;
 
        dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p));
 
@@ -150,6 +166,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
        if (c == NULL)
                return ERR_PTR(-ENOMEM);
 
+        /* set tunables to default values */
+        c->choose_local_tries = 2;
+        c->choose_local_fallback_tries = 5;
+        c->choose_total_tries = 19;
+
        ceph_decode_need(p, end, 4*sizeof(u32), bad);
        magic = ceph_decode_32(p);
        if (magic != CRUSH_MAGIC) {
@@ -297,7 +318,25 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
        }
 
        /* ignore trailing name maps. */
+        for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) {
+                err = skip_name_map(p, end);
+                if (err < 0)
+                        goto done;
+        }
+
+        /* tunables */
+        ceph_decode_need(p, end, 3*sizeof(u32), done);
+        c->choose_local_tries = ceph_decode_32(p);
+        c->choose_local_fallback_tries =  ceph_decode_32(p);
+        c->choose_total_tries = ceph_decode_32(p);
+        dout("crush decode tunable choose_local_tries = %d",
+             c->choose_local_tries);
+        dout("crush decode tunable choose_local_fallback_tries = %d",
+             c->choose_local_fallback_tries);
+        dout("crush decode tunable choose_total_tries = %d",
+             c->choose_total_tries);
 
+done:
        dout("crush_decode success\n");
        return c;