Merge branch 'main' of https://github.com/FalkorDB/falkordb-omnistrate …

…into 175-handle-requests-going-to-replicas-with-no-sentinel-running

chaos/cluster-load.test.js

@@ -0,0 +1,39 @@
+import redis from 'k6/experimental/redis';
+import { check } from 'k6';
+import exec from 'k6/execution';
+
+
+const client = new redis.Client({
+  socket: {
+    dialTimeout: 5000,
+    readTimeout: 5000,
+    writeTimeout: 5000,
+    poolTimeout: 5000,
+  },
+  cluster: {
+    // Cluster options
+    maxRedirects: 3,
+    readOnly: true,
+    routeByLatency: true,
+    routeRandomly: true,
+    nodes: [
+      // Nodes URLs
+    ]
+  },
+});
+
+export const options = {
+  stages: [
+    { duration: '120s', target: 100 },
+  ]
+};
+
+async function callServer() {
+  const vuId = exec.vu.idInTest;
+  const ok = await client.set(`a-${vuId}`, `${vuId}`).then(() => true).catch(() => false);
+  check(ok, { 'set command succeeded': (ok) => ok });
+}
+
+export default function () {
+  callServer();
+}

falkordb-cluster/node.conf

@@ -2,7 +2,45 @@
 loadmodule /FalkorDB/bin/src/falkordb.so CACHE_SIZE $FALKORDB_CACHE_SIZE NODE_CREATION_BUFFER $FALKORDB_NODE_CREATION_BUFFER MAX_QUEUED_QUERIES $FALKORDB_MAX_QUEUED_QUERIES TIMEOUT_MAX $FALKORDB_TIMEOUT_MAX TIMEOUT_DEFAULT $FALKORDB_TIMEOUT_DEFAULT RESULTSET_SIZE $FALKORDB_RESULT_SET_SIZE QUERY_MEM_CAPACITY $FALKORDB_QUERY_MEM_CAPACITY
 loglevel $LOG_LEVEL
 
+#Enable tls for Redis Cluster Bus
+tls-cluster no
 
+# For maximum availability, it is possible to set the cluster-replica-validity-factor
+# to a value of 0, which means, that replicas will always try to failover the
+# master regardless of the last time they interacted with the master.
+# (However they'll always try to apply a delay proportional to their
+# offset rank).
+#
+# Zero is the only value able to guarantee that when all the partitions heal
+# the cluster will always be able to continue.
+#
+cluster-replica-validity-factor 0
+#Allows replicas to migrate to orphaned masters (masters with no replicas left)
+# only if their masters remain with at least one replica
+cluster-allow-replica-migration yes
+cluster-migration-barrier 1
+# If a hash slot is uncovered (no node serving it) the whole cluster
+# becomes unhealthy and stops accepting queries.
+cluster-require-full-coverage yes
+# This prevents replicas from failing their masters
+# can be forced by manual failover. (Replica should never be promoted to master)
+cluster-replica-no-failover no
+# Allows replicas to serve read queries in a cluster down state. 
+cluster-allow-reads-when-down no
+# This feature should be kept as yes.
+cluster-allow-pubsubshard-when-down yes
+# Cluster link send buffer limit is the limit on the memory usage of an individual
+# cluster bus link's send buffer in bytes. Cluster links would be freed if they exceed
+# this limit. This is to primarily prevent send buffers from growing unbounded on links
+# toward slow peers (E.g. PubSub messages being piled up).
+# This limit is disabled by default. Enable this limit when 'mem_cluster_links' INFO field
+# and/or 'send-buffer-allocated' entries in the 'CLUSTER LINKS` command output continuously increase.
+# Minimum limit of 1gb is recommended so that cluster link buffer can fit in at least a single
+# PubSub message by default. (client-query-buffer-limit default value is 1gb)
+cluster-link-sendbuf-limit 0
+#  optional nodename to be used in addition to the node ID for
+# debugging and admin information
+cluster-announce-human-nodename ""
 cluster-preferred-endpoint-type hostname
 cluster-port 16379
 cluster-enabled yes

falkordb-node/node-entrypoint.sh

@@ -48,6 +48,7 @@ FALKORDB_RESULT_SET_SIZE=${FALKORDB_RESULT_SET_SIZE:-10000}
 FALKORDB_QUERY_MEM_CAPACITY=${FALKORDB_QUERY_MEM_CAPACITY:-0}
 FALKORDB_TIMEOUT_MAX=${FALKORDB_TIMEOUT_MAX:-0}
 FALKORDB_TIMEOUT_DEFAULT=${FALKORDB_TIMEOUT_DEFAULT:-0}
+FALKORDB_VKEY_MAX_ENTITY_COUNT=${FALKORDB_VKEY_MAX_ENTITY_COUNT:-4611686000000000000}
 MEMORY_LIMIT=${MEMORY_LIMIT:-''}
 # If vars are <nil>, set it to 0
 if [[ "$FALKORDB_QUERY_MEM_CAPACITY" == "<nil>" ]]; then
@@ -354,12 +355,19 @@ create_user() {
   config_rewrite
 }
 
+
 config_rewrite() {
   # Config rewrite
   echo "Rewriting config"
   redis-cli -p $NODE_PORT -a $ADMIN_PASSWORD --no-auth-warning $TLS_CONNECTION_STRING CONFIG REWRITE
 }
 
+set_configs() {
+  echo "Setting configs"
+  redis-cli -p $NODE_PORT -a $ADMIN_PASSWORD --no-auth-warning $TLS_CONNECTION_STRING GRAPH.CONFIG set VKEY_MAX_ENTITY_COUNT $FALKORDB_VKEY_MAX_ENTITY_COUNT
+  redis-cli -p $NODE_PORT -a $ADMIN_PASSWORD --no-auth-warning $TLS_CONNECTION_STRING GRAPH.CONFIG get VKEY_MAX_ENTITY_COUNT
+}
+
 if [ -f $NODE_CONF_FILE ]; then
   # Get current admin password
   CURRENT_ADMIN_PASSWORD=$(cat $NODE_CONF_FILE | grep -oP '(?<=requirepass ).*' | sed 's/\"//g')
@@ -443,6 +451,7 @@ if [ "$RUN_NODE" -eq "1" ]; then
   sleep 10
 
   create_user
+  set_configs
 
   # If node should be master, add it to sentinel
   if [[ $IS_REPLICA -eq 0 && $RUN_SENTINEL -eq 1 ]]; then

omnistrate.enterprise.yaml

@@ -1127,6 +1127,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     environment:
       - RUN_NODE=0
       - RUN_SENTINEL=1
@@ -1624,6 +1626,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     environment:
       - RUN_NODE=0
       - RUN_SENTINEL=1
@@ -1946,6 +1950,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     <<: *rebalanceparam
     environment:
       - IS_MULTI_ZONE=0
@@ -2251,6 +2257,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     <<: *rebalanceparam
     environment:
       - IS_MULTI_ZONE=1

omnistrate.pro.yaml

@@ -1404,6 +1404,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     environment:
       - RUN_NODE=0
       - RUN_SENTINEL=1
@@ -2218,6 +2220,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     environment:
       - RUN_NODE=0
       - RUN_SENTINEL=1
@@ -2566,6 +2570,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     <<: *rebalanceparam
     environment:
       - NODE_HOST=$sys.network.node.externalEndpoint
@@ -2877,6 +2883,8 @@ services:
       instanceTypes:
         - cloudProvider: gcp
           name: e2-small
+        - cloudProvider: aws
+          name: t3a.small
     <<: *rebalanceparam
     environment:
       - IS_MULTI_ZONE=1