From 14962ce3e69e452a2447c12cde3369759365fda9 Mon Sep 17 00:00:00 2001
From: Raghavendra G <raghavendra@gluster.com>
Date: Wed, 28 Oct 2009 04:46:25 +0000
Subject: performance/io-cache: change the hash function used for rbtree based
 hash table.

- the earlier hash function does not distribute pages uniformly for offsets that
    fit into 32 bits. The reason is that the hash function just xors the contents of
    the key 4 bytes at a time with the current value of hash. Hence for keys that
    fit into 32 bits, the hash will be the key itself. Since we are using the
    rounded_offset (which is a multiple of 128KB) as the key, the key will
    be exactly divisible by the number of buckets configured (4096) resolving all
    the pages into the first bucket.

Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 335 (Io-cache optimization)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=335
---
 libglusterfs/src/common-utils.c              | 15 +++++++++++++++
 libglusterfs/src/common-utils.h              |  1 +
 xlators/performance/io-cache/src/io-cache.c  | 16 +++++++++++-----
 xlators/performance/io-cache/src/ioc-inode.c | 12 +++++-------
 4 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/libglusterfs/src/common-utils.c b/libglusterfs/src/common-utils.c
index de0cb774b..3f52a90a0 100644
--- a/libglusterfs/src/common-utils.c
+++ b/libglusterfs/src/common-utils.c
@@ -56,6 +56,21 @@ struct dnscache6 {
 	struct addrinfo *next;
 };
 
+
+int
+gf_log2 (unsigned long x)
+{
+        int val = 0;
+
+        while (x != 1) {
+                x /= 2;
+                val++;
+        }
+
+        return val;
+}
+
+
 int32_t
 gf_resolve_ip6 (const char *hostname, 
 		uint16_t port, 
diff --git a/libglusterfs/src/common-utils.h b/libglusterfs/src/common-utils.h
index c5869f4a4..48788d295 100644
--- a/libglusterfs/src/common-utils.h
+++ b/libglusterfs/src/common-utils.h
@@ -330,6 +330,7 @@ int gf_lockfd (int fd);
 int gf_unlockfd (int fd);
 
 int get_checksum_for_file (int fd, uint32_t *checksum);
+int gf_log2 (unsigned long x);
 
 #endif /* _COMMON_UTILS_H */
 
diff --git a/xlators/performance/io-cache/src/io-cache.c b/xlators/performance/io-cache/src/io-cache.c
index 5c1f74db1..da3f4f15d 100644
--- a/xlators/performance/io-cache/src/io-cache.c
+++ b/xlators/performance/io-cache/src/io-cache.c
@@ -30,6 +30,8 @@
 #include <assert.h>
 #include <sys/time.h>
 
+extern int ioc_log2_page_size;
+
 uint32_t
 ioc_get_priority (ioc_table_t *table, const char *path);
 
@@ -1234,11 +1236,12 @@ out:
 int32_t 
 init (xlator_t *this)
 {
-	ioc_table_t *table = NULL;
-	dict_t      *options = this->options;
-	uint32_t    index = 0;
-	char        *cache_size_string = NULL;
-        int32_t     ret = -1;
+	ioc_table_t     *table = NULL;
+	dict_t          *options = this->options;
+	uint32_t         index = 0;
+	char            *cache_size_string = NULL;
+        int32_t          ret = -1;
+        glusterfs_ctx_t *ctx = NULL;
 
 	if (!this->children || this->children->next) {
 		gf_log (this->name, GF_LOG_ERROR,
@@ -1320,6 +1323,9 @@ init (xlator_t *this)
 	this->private = table;
         ret = 0;
 
+        ctx = this->ctx;
+        ioc_log2_page_size = gf_log2 (ctx->page_size);
+
 out:
         if (ret == -1) {
                 if (table != NULL) {
diff --git a/xlators/performance/io-cache/src/ioc-inode.c b/xlators/performance/io-cache/src/ioc-inode.c
index e647b3183..11da86312 100644
--- a/xlators/performance/io-cache/src/ioc-inode.c
+++ b/xlators/performance/io-cache/src/ioc-inode.c
@@ -24,18 +24,16 @@
 
 #include "io-cache.h"
 
+int ioc_log2_page_size;
 
 inline uint32_t
 ioc_hashfn (void *data, int len)
 {
-        uint32_t        hash = 0;
-        while (len > 0) {
-                hash ^= *(uint32_t *)data;
-                data += sizeof (uint32_t);
-                len -= sizeof (uint32_t);
-        }
+        off_t offset;
+
+        offset = *(off_t *) data;
 
-        return hash;
+        return (offset >> ioc_log2_page_size);
 }
 
 /*
-- 
cgit