glusterfs: Use gcc builtin ATOMIC operator to increase/decreate refcount.

Problem: In glusterfs code base we call mutex_lock/unlock to take
         reference/dereference for a object.Sometime it could be
         reason for lock contention also.

Solution: There is no need to use mutex to increase/decrease ref
          counter, instead of using mutex use gcc builtin ATOMIC
          operation.

Test:   I have not observed yet how much performance gain after apply
        this patch specific to glusterfs but i have tested same
        with below small program(mutex and atomic both) and
        get good difference.

static int numOuterLoops;
static void *
threadFunc(void *arg)
{
    int j;

    for (j = 0; j < numOuterLoops; j++) {
            __atomic_add_fetch (&glob, 1,__ATOMIC_ACQ_REL);
    }
    return NULL;
}

int
main(int argc, char *argv[])
{
    int opt, s, j;
    int numThreads;
    pthread_t *thread;
    int verbose;
    int64_t n = 0;

    if (argc < 2 ) {
     printf(" Please provide 2 args Num of threads && Outer Loop\n");
     exit (-1);
    }
    numThreads = atoi(argv[1]);
    numOuterLoops = atoi (argv[2]);

    if (1) {
        printf("\tthreads: %d; outer loops: %d;\n",
                numThreads, numOuterLoops);
    }

    thread = calloc(numThreads, sizeof(pthread_t));
    if (thread == NULL) {
        printf ("calloc error so exit\n");
        exit (-1);
    }

    __atomic_store (&glob, &n, __ATOMIC_RELEASE);
    for (j = 0; j < numThreads; j++) {
        s = pthread_create(&thread[j], NULL, threadFunc, NULL);
        if (s != 0) {
            printf ("pthread_create failed so exit\n");
            exit (-1);
        }
    }

    for (j = 0; j < numThreads; j++) {
        s = pthread_join(thread[j], NULL);
        if (s != 0) {
            printf ("pthread_join failed so exit\n");
            exit (-1);
        }
    }
    printf("glob value is %ld\n",__atomic_load_n (&glob,__ATOMIC_RELAXED));

    exit(0);
}

   time ./thr_count 800 800000
   threads: 800; outer loops: 800000;
   glob value is 640000000

real	1m10.288s
user	0m57.269s
sys	3m31.565s

time ./thr_count_atomic 800 800000
     threads: 800; outer loops: 800000;
glob value is 640000000

real	0m20.313s
user	1m20.558s
sys	0m0.028

Change-Id: Ie5030a52ea264875e002e108dd4b207b15ab7cc7
Signed-off-by: Mohit Agrawal <moagrawa@redhat.com>

2 files changed, 5 insertions, 13 deletions

diff --git a/xlators/protocol/client/src/client-handshake.c b/xlators/protocol/client/src/client-handshake.c
index ca3d140d08e..6429dc2e8ae 100644
--- a/xlators/protocol/client/src/client-handshake.c
+++ b/xlators/protocol/client/src/client-handshake.c
@@ -32,7 +32,7 @@ int client_set_lk_version_cbk (struct rpc_req *req, struct iovec *iov,
 int client_set_lk_version (xlator_t *this);
 
 typedef struct client_fd_lk_local {
-        int             ref;
+        gf_atomic_t     ref;
         gf_boolean_t    error;
         gf_lock_t       lock;
         clnt_fd_ctx_t *fdctx;
@@ -285,11 +285,7 @@ clnt_fd_lk_local_ref (xlator_t *this, clnt_fd_lk_local_t *local)
 {
         GF_VALIDATE_OR_GOTO (this->name, local, out);
 
-        LOCK (&local->lock);
-        {
-                local->ref++;
-        }
-        UNLOCK (&local->lock);
+        GF_ATOMIC_INC (local->ref);
 out:
         return local;
 }
@@ -301,11 +297,7 @@ clnt_fd_lk_local_unref (xlator_t *this, clnt_fd_lk_local_t *local)
 
         GF_VALIDATE_OR_GOTO (this->name, local, out);
 
-        LOCK (&local->lock);
-        {
-                ref = --local->ref;
-        }
-        UNLOCK (&local->lock);
+        ref = GF_ATOMIC_DEC (local->ref);
 
         if (ref == 0) {
                 LOCK_DESTROY (&local->lock);
@@ -325,7 +317,7 @@ clnt_fd_lk_local_create (clnt_fd_ctx_t *fdctx)
         if (!local)
                 goto out;
 
-        local->ref    = 1;
+        GF_ATOMIC_INIT (local->ref, 1);
         local->error  = _gf_false;
         local->fdctx = fdctx;
 
diff --git a/xlators/protocol/client/src/client.c b/xlators/protocol/client/src/client.c
index 8df697ed883..8ec9eaeb8a9 100644
--- a/xlators/protocol/client/src/client.c
+++ b/xlators/protocol/client/src/client.c
@@ -2844,7 +2844,7 @@ client_fd_lk_ctx_dump (xlator_t *this, fd_lk_ctx_t *lk_ctx, int nth_fd)
         fd_lk_ctx_node_t        *plock                   = NULL;
         char                    key[GF_DUMP_MAX_BUF_LEN] = {0,};
 
-        lk_ctx_ref = fd_lk_ctx_try_ref (lk_ctx);
+        lk_ctx_ref = fd_lk_ctx_ref (lk_ctx);
         if (!lk_ctx_ref)
                 return;