Merge branch 'testing' into 3.0

src/cluster.c

@@ -40,6 +40,7 @@
 #include <sys/socket.h>
 #include <sys/stat.h>
 #include <sys/file.h>
+#include <math.h>
 
 /* A global reference to myself is handy to make code more clear.
  * Myself always points to server.cluster->myself, that is, the clusterNode
@@ -2136,8 +2137,9 @@ void clusterSendPing(clusterLink *link, int type) {
      * Since we have non-voting slaves that lower the probability of an entry
      * to feature our node, we set the number of entires per packet as
      * 10% of the total nodes we have. */
-    wanted = freshnodes/10;
+    wanted = floor(dictSize(server.cluster->nodes)/10);
     if (wanted < 3) wanted = 3;
+    if (wanted > freshnodes) wanted = freshnodes;
 
     /* Compute the maxium totlen to allocate our buffer. We'll fix the totlen
      * later according to the number of gossip sections we really were able
@@ -2156,7 +2158,7 @@ void clusterSendPing(clusterLink *link, int type) {
     clusterBuildMessageHdr(hdr,type);
 
     /* Populate the gossip fields */
-    int maxiterations = wanted+10;
+    int maxiterations = wanted*3;
     while(freshnodes > 0 && gossipcount < wanted && maxiterations--) {
         dictEntry *de = dictGetRandomKey(server.cluster->nodes);
         clusterNode *this = dictGetVal(de);
@@ -2167,6 +2169,11 @@ void clusterSendPing(clusterLink *link, int type) {
          * already, so we just gossip about other nodes. */
         if (this == myself) continue;
 
+        /* Give a bias to FAIL/PFAIL nodes. */
+        if (maxiterations > wanted*2 &&
+            !(this->flags & (REDIS_NODE_PFAIL|REDIS_NODE_FAIL)))
+            continue;
+
         /* In the gossip section don't include:
          * 1) Nodes in HANDSHAKE state.
          * 3) Nodes with the NOADDR flag set.

utils/cluster_fail_time.tcl

@@ -0,0 +1,50 @@
+# This simple script is used in order to estimate the average PFAIL->FAIL
+# state switch after a failure.
+
+set ::sleep_time 10     ; # How much to sleep to trigger PFAIL.
+set ::fail_port 30016   ; # Node to put in sleep.
+set ::other_port 30001  ; # Node to use to monitor the flag switch.
+
+proc avg vector {
+    set sum 0.0
+    foreach x $vector {
+        set sum [expr {$sum+$x}]
+    }
+    expr {$sum/[llength $vector]}
+}
+
+set samples {}
+while 1 {
+    exec redis-cli -p $::fail_port debug sleep $::sleep_time > /dev/null &
+
+    # Wait for fail? to appear.
+    while 1 {
+        set output [exec redis-cli -p $::other_port cluster nodes]
+        if {[string match {*fail\?*} $output]} break
+        after 100
+    }
+
+    puts "FAIL?"
+    set start [clock milliseconds]
+
+    # Wait for fail? to disappear.
+    while 1 {
+        set output [exec redis-cli -p $::other_port cluster nodes]
+        if {![string match {*fail\?*} $output]} break
+        after 100
+    }
+
+    puts "FAIL"
+    set now [clock milliseconds]
+    set elapsed [expr {$now-$start}]
+    puts $elapsed
+    lappend samples $elapsed
+
+    puts "AVG([llength $samples]): [avg $samples]"
+
+    # Wait for the instance to be available again.
+    exec redis-cli -p $::fail_port ping
+
+    # Wait for the fail flag to be cleared.
+    after 2000
+}

utils/create-cluster/README

@@ -24,4 +24,4 @@ In order to stop a cluster:
 1. Use "./craete-cluster stop" to stop all the instances. After you stopped the instances you can use "./create-cluster start" to restart them if you change ideas.
 2. Use "./create-cluster clean" to remove all the AOF / log files to restat with a clean environment.
 
-It is currently hardcoded that you start a cluster where each master has one slave, since the script is pretty basic.
+Use the command "./create-cluster help" to get the full list of features.

utils/create-cluster/create-cluster

@@ -1,8 +1,21 @@
 #!/bin/bash
 
+# Settings
 PORT=30000
-ENDPORT=30006
-TIMEOUT=15000
+TIMEOUT=2000
+NODES=6
+REPLICAS=1
+
+# You may want to put the above config parameters into config.sh in order to
+# override the defaults without modifying this script.
+
+if [ -a config.sh ]
+then
+    source "config.sh"
+fi
+
+# Computed vars
+ENDPORT=$((PORT+NODES))
 
 if [ "$1" == "start" ]
 then
@@ -21,7 +34,7 @@ then
         PORT=$((PORT+1))
         HOSTS="$HOSTS 127.0.0.1:$PORT"
     done
-    ../../src/redis-trib.rb create --replicas 1 $HOSTS
+    ../../src/redis-trib.rb create --replicas $REPLICAS $HOSTS
     exit 0
 fi
 
@@ -35,22 +48,31 @@ then
     exit 0
 fi
 
-if [ "$1" == "join" ]
+if [ "$1" == "watch" ]
+then
+    PORT=$((PORT+1))
+    while [ 1 ]; do
+        clear
+        date
+        redis-cli -p $PORT cluster nodes | head -30
+        sleep 1
+    done
+    exit 0
+fi
+
+if [ "$1" == "tail" ]
+then
+    INSTANCE=$2
+    PORT=$((PORT+INSTANCE))
+    tail -f ${PORT}.log
+    exit 0
+fi
+
+if [ "$1" == "call" ]
 then
     while [ $((PORT < ENDPORT)) != "0" ]; do
         PORT=$((PORT+1))
-        echo "Joining $PORT"
-        redis-cli -p $PORT CLUSTER MEET 127.0.0.1 10002
-    done
-
-    echo "Waiting 5 seconds"
-    sleep 5
-
-    PORT=30000
-    while [ $((PORT < ENDPORT)) != "0" ]; do
-        PORT=$((PORT+1))
-        echo "Replicate $PORT"
-        redis-cli -p $PORT CLUSTER REPLICATE $2 
+        ../../src/redis-cli -p $PORT $2 $3 $4 $5 $6 $7 $8 $9
     done
     exit 0
 fi
@@ -64,4 +86,10 @@ then
     exit 0
 fi
 
-echo "Usage: $0 [start|create|stop|join|clean]"
+echo "Usage: $0 [start|create|stop|watch|tail|clean]"
+echo "start       -- Launch Redis Cluster instances."
+echo "create      -- Create a cluster using redis-trib create."
+echo "stop        -- Stop Redis Cluster instances."
+echo "watch       -- Show CLUSTER NODES output (first 30 lines) of first node."
+echo "tail <id>   -- Run tail -f of instance at base port + ID."
+echo "clean       -- Remove all instances data, logs, configs."