distribute: add hash-name-regex option

This is to support the common "write to temp file then rename" idiom. In our
case this causes us to create a linkfile during the rename in (N-1)/N cases,
with a significant impact on performance e.g. for UFO which uses this idiom.
This patch allows the user to specify up to two regular expressions that
separate the permanent and transient parts of a temp-file name:

    rsync-hash-regex reimplements the existing RSYNC_FRIENDLY_NAME
    pattern where the temporary name for EXAMPLE is .EXAMPLE.suffix

    extra-hash-regex can be used for a second pattern, active concurrently,
    and can include alternatives via the POSIX extended-regex syntax

Change-Id: Ic1a6ed19324bc31fefe91ee34b8478877a9c5d2c
BUG: 912564
Signed-off-by: Jeff Darcy <jdarcy@redhat.com>
Reviewed-on: http://review.gluster.org/4116
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

1 files changed, 57 insertions, 19 deletions

diff --git a/xlators/cluster/dht/src/dht-hashfn.c b/xlators/cluster/dht/src/dht-hashfn.c
index 97eb1f05fa8..2276ca116be 100644
--- a/xlators/cluster/dht/src/dht-hashfn.c
+++ b/xlators/cluster/dht/src/dht-hashfn.c
@@ -44,30 +44,68 @@ dht_hash_compute_internal (int type, const char *name, uint32_t *hash_p)
 }
 
 
-#define MAKE_RSYNC_FRIENDLY_NAME(rsync_frndly_name, name) do {          \
-                rsync_frndly_name = (char *) name;                      \
-                if (name[0] == '.') {                                   \
-                        char *dot   = 0;                                \
-                        int namelen = 0;                                \
-                                                                        \
-                        dot = strrchr (name, '.');                      \
-                        if (dot && dot > (name + 1) && *(dot + 1)) {    \
-                                namelen = (dot - name);                 \
-                                rsync_frndly_name = alloca (namelen);   \
-                                strncpy (rsync_frndly_name, name + 1,   \
-                                         namelen);                      \
-                                rsync_frndly_name[namelen - 1] = 0;     \
-                        }                                               \
-                }                                                       \
-        } while (0);
+static inline
+gf_boolean_t
+dht_munge_name (const char *original, char *modified, size_t len, regex_t *re)
+{
+        regmatch_t      matches[2];
+        size_t          new_len;
 
+        if (regexec(re,original,2,matches,0) != REG_NOMATCH) {
+                if (matches[1].rm_so != -1) {
+                        new_len = matches[1].rm_eo - matches[1].rm_so;
+                        /* Equal would fail due to the NUL at the end. */
+                        if (new_len < len) {
+                                memcpy (modified,original+matches[1].rm_so,
+                                        new_len);
+                                modified[new_len] = '\0';
+                                return _gf_true;
+                        }
+                }
+        }
+
+        /* This is guaranteed safe because of how the dest was allocated. */
+        strcpy(modified,original);
+        return _gf_false;
+}
 
 int
-dht_hash_compute (int type, const char *name, uint32_t *hash_p)
+dht_hash_compute (xlator_t *this, int type, const char *name, uint32_t *hash_p)
 {
-        char     *rsync_friendly_name = NULL;
+        char            *rsync_friendly_name    = NULL;
+        dht_conf_t      *priv                   = this->private;
+        size_t           len                    = 0;
+        gf_boolean_t     munged                 = _gf_false;
+
+        /*
+         * It wouldn't be safe to use alloca in an inline function that doesn't
+         * actually get inlined, and it wouldn't be efficient to do a real
+         * allocation, so we use alloca here (if needed) and pass that to the
+         * inline.
+         */
 
-        MAKE_RSYNC_FRIENDLY_NAME (rsync_friendly_name, name);
+        if (priv->extra_regex_valid) {
+                len = strlen(name) + 1;
+                rsync_friendly_name = alloca(len);
+                munged = dht_munge_name (name, rsync_friendly_name, len,
+                                         &priv->extra_regex);
+        }
+
+        if (!munged && priv->rsync_regex_valid) {
+                len = strlen(name) + 1;
+                rsync_friendly_name = alloca(len);
+                gf_log (this->name, GF_LOG_INFO, "trying regex for %s", name);
+                munged = dht_munge_name (name, rsync_friendly_name, len,
+                                         &priv->rsync_regex);
+                if (munged) {
+                        gf_log (this->name, GF_LOG_INFO,
+                                "munged down to %s", rsync_friendly_name);
+                }
+        }
+
+        if (!munged) {
+                rsync_friendly_name = (char *)name;
+        }
 
         return dht_hash_compute_internal (type, rsync_friendly_name, hash_p);
 }