Improved timeout handling and other fixes

configure.in

@@ -1,5 +1,5 @@
-AC_INIT(qperf, 0.4.3, general@lists.openfabrics.org)
-AM_INIT_AUTOMAKE(qperf, 0.4.3)
+AC_INIT(qperf, 0.4.4, general@lists.openfabrics.org)
+AM_INIT_AUTOMAKE(qperf, 0.4.4)
 AC_PROG_CC
 AC_CHECK_LIB(ibverbs, ibv_open_device, RDMA=1)
 AC_CHECK_LIB(rdmacm, rdma_create_id)

qperf.spec

@@ -1,6 +1,6 @@
 Name:           qperf
 Summary:        Measure socket and RDMA performance
-Version:        0.4.3
+Version:        0.4.4
 Release:        1
 License:        BSD 3-Clause, GPL v2
 Group:          Networking/Diagnostic

src/help.txt

@@ -351,7 +351,7 @@ Options
           The current version of qperf is printed.
     --wait_server Time (-ws)
           If the server is not ready, continue to try connecting for Time
-          seconds before giving up.
+          seconds before giving up.  The default is 5 seconds.
 Tests -RDMA
     Miscellaneous
         conf                    Show configuration
@@ -902,14 +902,15 @@ ver_rc_compare_swap +RDMA
         --cq_poll OnOff         Set polling mode on/off
         --time (-t)             Set test duration
     Other Options
-        --cpu_affinity, --listen_port, --mtu_size, --rd_atomic, --static_rate,
-        --timeout
+        --cpu_affinity, --listen_port, --msg_size, --mtu_size, --rd_atomic,
+        --static_rate, --timeout
     Display Options
         --precision, --unify_nodes, --unify_units, --verbose
     Description
         Test the RC Compare and Swap Atomic operation.  The server's memory
-        location starts with zero and the client successively exchanges, 0 for
-        1, 1 for 2, etc.  The results are checked for correctness.
+        location starts with zero and the client successively makes exchanges
+        with a variety of different values.  The results are checked for
+        correctness.
 ver_rc_fetch_add +RDMA
     Purpose
         Verify RC fetch and add
@@ -918,8 +919,8 @@ ver_rc_fetch_add +RDMA
         --cq_poll OnOff         Set polling mode on/off
         --time (-t)             Set test duration
     Other Options
-        --cpu_affinity, --listen_port, --mtu_size, --rd_atomic, --static_rate,
-        --timeout
+        --cpu_affinity, --listen_port, --msg_size, --mtu_size, --rd_atomic,
+        --static_rate, --timeout
     Display Options
         --precision, --unify_nodes, --unify_units, --use_bits_per_sec,
         --verbose

src/qperf.c

@@ -62,7 +62,7 @@
  */
 #define VER_MAJ 0                       /* Major version */
 #define VER_MIN 4                       /* Minor version */
-#define VER_INC 3                       /* Incremental version */
+#define VER_INC 4                       /* Incremental version */
 #define LISTENQ 5                       /* Size of listen queue */
 #define BUFSIZE 1024                    /* Size of buffers */
 
@@ -246,6 +246,7 @@ static void      view_time(int type, char *pref, char *name, double value);
  */
 static int  ListenPort      = DEF_LISTEN_PORT;
 static int  Precision       = DEF_PRECISION;
+static int  ServerWait      = DEF_TIMEOUT;
 static int  UseBitsPerSec   = 0;
 
 
@@ -266,7 +267,6 @@ static int      VerboseConf;
 static int      VerboseStat;
 static int      VerboseTime;
 static int      VerboseUsed;
-static int      Wait;
 
 
 /*
@@ -957,7 +957,7 @@ do_option(OPTION *option, char ***argvp)
         VerboseUsed = 2;
         *argvp += 1;
     } else if (streq(t, "wait")) {
-        Wait = arg_time(argvp);
+        ServerWait = arg_time(argvp);
     } else
         error(BUG, "do_option: unknown type: %s", t);
 }
@@ -1370,10 +1370,8 @@ server(void)
         TestName = test->name;
         debug("received request: %s", TestName);
         init_lstat();
-        Finished = 0;
         set_affinity();
         (test->server)();
-        stop_test_timer();
         exit(0);
     }
     close(ListenFD);
@@ -1490,7 +1488,6 @@ client(TEST *test)
     debug("sending request: %s", TestName);
     init_lstat();
     printf("%s:\n", TestName);
-    Finished = 0;
     (*test->client)();
     remotefd_close();
     place_show();
@@ -1512,31 +1509,34 @@ client_send_request(void)
     AI *ailist = getaddrinfo_port(ServerName, ListenPort, &hints);
 
     RemoteFD = -1;
-    if (Wait)
-        start_test_timer(Wait);
+    if (ServerWait)
+        start_test_timer(ServerWait);
     for (;;) {
         for (a = ailist; a; a = a->ai_next) {
+            if (Finished)
+                break;
             RemoteFD = socket(a->ai_family, a->ai_socktype, a->ai_protocol);
-            if (RemoteFD >= 0) {
-                if (connect(RemoteFD, a->ai_addr, a->ai_addrlen) == SUCCESS0) {
-                    ServerAddrLen = a->ai_addrlen;
-                    memcpy(&ServerAddr, a->ai_addr, ServerAddrLen);
-                    break;
-                }
+            if (RemoteFD < 0)
+                continue;
+            if (connect(RemoteFD, a->ai_addr, a->ai_addrlen) != SUCCESS0) {
                 remotefd_close();
+                continue;
             }
+            ServerAddrLen = a->ai_addrlen;
+            memcpy(&ServerAddr, a->ai_addr, ServerAddrLen);
+            break;
         }
-        if (RemoteFD >= 0 || !Wait || Finished)
+        if (RemoteFD >= 0 || !ServerWait || Finished)
             break;
         sleep(1);
     }
 
-    if (Wait)
+    if (ServerWait)
         stop_test_timer();
     freeaddrinfo(ailist);
 
     if (RemoteFD < 0)
-        error(0, "failed to connect");
+        error(0, "%s: failed to connect", ServerName);
     remotefd_setup();
     enc_init(&req);
     enc_req(&RReq);
@@ -1804,6 +1804,7 @@ start_test_timer(int seconds)
 {
     struct itimerval itimerval = {{0}};
 
+    Finished = 0;
     get_times(LStat.time_s);
     setitimer(ITIMER_REAL, &itimerval, 0);
     if (!seconds)
@@ -1824,7 +1825,8 @@ start_test_timer(int seconds)
  * executed and it will take the second SIGALRM call generated by the interval
  * timer to wake it up.  Hence, we save the end times in sig_alrm.  Note that
  * if Finished is set, we reject any packets that are sent or arrive in order
- * not to cheat.
+ * not to cheat.  We clear Finished since code assumes that it is the default
+ * state.
  */
 void
 stop_test_timer(void)
@@ -1833,6 +1835,7 @@ stop_test_timer(void)
 
     set_finished();
     setitimer(ITIMER_REAL, &itimerval, 0);
+    Finished = 0;
     debug("stopping timer");
 }
 

src/rdma.c

@@ -1682,7 +1682,10 @@ rd_create_qp(DEVICE *dev, struct ibv_context *context, struct rdma_cm_id *id)
 
 
 /*
- * Allocate a memory region and register it.
+ * Allocate a memory region and register it.  I thought this routine should
+ * never be called with a size of 0 as prior code checks for that and sets it
+ * to some default value.  I appear to be wrong.  In that case, size is set to
+ * 1 so other code does not break.
  */
 static void
 rd_mralloc(DEVICE *dev, int size)
@@ -1693,7 +1696,7 @@ rd_mralloc(DEVICE *dev, int size)
     if (dev->buffer)
         error(BUG, "rd_mralloc: memory region already allocated");
     if (size == 0)
-        return;
+        size = 1;
 
     pagesize = sysconf(_SC_PAGESIZE);
     if (posix_memalign((void **)&dev->buffer, pagesize, size) != 0)
@@ -1720,11 +1723,11 @@ rd_mrfree(DEVICE *dev)
 {
     if (dev->mr)
         ibv_dereg_mr(dev->mr);
-    dev->mr = 0;
+    dev->mr = NULL;
 
     if (dev->buffer)
         free(dev->buffer);
-    dev->buffer = 0;
+    dev->buffer = NULL;
     dev->buf_size = 0;
 
     dev->lnode.rkey = 0;

src/rds.c

@@ -296,7 +296,7 @@ server_get_hosts(char *lhost, char *rhost)
     laddr.sin_addr.s_addr = INADDR_ANY;
     laddr.sin_port = htons(0);
     if (bind(lfd, (SA *)&laddr, sizeof(laddr)) < 0)
-        error(SYS, "bind failed");
+        error(SYS, "bind INET failed");
 
     port = get_socket_port(lfd);
     encode_uint32(&port, port);
@@ -358,7 +358,7 @@ rds_socket(char *host, int port)
     setsockopt_one(sockfd, SO_REUSEADDR);
     rds_makeaddr(&sockaddr, &socklen, host, port);
     if (bind(sockfd, (SA *)&sockaddr, socklen) != SUCCESS0)
-        error(SYS, "bind failed");
+        error(SYS, "bind RDS failed");
     set_socket_buffer_size(sockfd);
     return sockfd;
 }

src/socket.c

@@ -252,7 +252,7 @@ run_client_udp_lat(void)
 /*
  * Measure UDP latency (server side).
  */
-    void
+void
 run_server_udp_lat(void)
 {
     datagram_server_lat(K_UDP);