Merge pull request #135 from etschannen/release-5.1

Release 5.1

documentation/sphinx/source/command-line-interface.rst

@@ -59,7 +59,7 @@ The ``commit`` command commits the current transaction. Any sets or clears execu
 configure
 ---------
 
-The ``configure`` command changes the database configuration. Its syntax is ``configure [new] [single|double|triple|three_data_hall|multi_dc] [ssd|memory] [proxies=<N>] [resolvers=<N>] [logs=<N>]``.
+The ``configure`` command changes the database configuration. Its syntax is ``configure [new] [single|double|triple|three_data_hall|three_datacenter] [ssd|memory] [proxies=<N>] [resolvers=<N>] [logs=<N>]``.
 
 The ``new`` option, if present, initializes a new database with the given configuration rather than changing the configuration of an existing one. When ``new`` is used, both a redundancy mode and a storage engine must be specified.
 
@@ -72,7 +72,7 @@ Redundancy modes define storage requirements, required cluster size, and resilie
 * ``double``
 * ``triple``
 * ``three_data_hall``
-* ``multi_dc``
+* ``three_datacenter``
 
 For descriptions of redundacy modes, see :ref:`configuration-choosing-redundancy-mode`.
 

documentation/sphinx/source/fault-tolerance.rst

@@ -28,7 +28,7 @@ The number of machines in each team is based on the replication mode; the total
 Independence assumptions
 ========================
 
-As a further refinement, FoundationDB can be made aware that certain machines might tend to fail together by specifying the locality of each process. For example, every machine in a rack might share a network and power connection. If either failed, then the entire rack of machines would fail. We use this knowledge when choosing teams, taking care not to place any two machines in a team that would have a tendency to fail together. Pieces of data can then be intelligently distributed across racks or even datacenters, so that characteristic multimachine failures (for example, based on rack configuration) do not cause service interruption or data loss. Our ``three_data_hall`` and ``multi_dc`` configurations use this technique to continuously operate through a failure of a data hall or datacenter respectively.
+As a further refinement, FoundationDB can be made aware that certain machines might tend to fail together by specifying the locality of each process. For example, every machine in a rack might share a network and power connection. If either failed, then the entire rack of machines would fail. We use this knowledge when choosing teams, taking care not to place any two machines in a team that would have a tendency to fail together. Pieces of data can then be intelligently distributed across racks or even datacenters, so that characteristic multimachine failures (for example, based on rack configuration) do not cause service interruption or data loss. Our ``three_data_hall`` and ``three_datacenter`` configurations use this technique to continuously operate through a failure of a data hall or datacenter respectively.
 
 Other types of failure
 ======================

fdbcli/fdbcli.actor.cpp

@@ -438,9 +438,9 @@ void initHelp() {
 		"clear a range of keys from the database",
 		"All keys between BEGINKEY (inclusive) and ENDKEY (exclusive) are cleared from the database. This command will succeed even if the specified range is empty, but may fail because of conflicts." ESCAPINGK);
 	helpMap["configure"] = CommandHelp(
-		"configure [new] <single|double|triple|three_data_hall|three_datacenter|multi_dc|ssd|memory|proxies=<PROXIES>|logs=<LOGS>|resolvers=<RESOLVERS>>*",
+		"configure [new] <single|double|triple|three_data_hall|three_datacenter|ssd|memory|proxies=<PROXIES>|logs=<LOGS>|resolvers=<RESOLVERS>>*",
 		"change database configuration",
-		"The `new' option, if present, initializes a new database with the given configuration rather than changing the configuration of an existing one. When used, both a redundancy mode and a storage engine must be specified.\n\nRedundancy mode:\n  single - one copy of the data.  Not fault tolerant.\n  double - two copies of data (survive one failure).\n  triple - three copies of data (survive two failures).\n  three_data_hall - See the Admin Guide.\n  three_datacenter - See the Admin Guide.\n  multi_dc - See the Admin Guide.\n\nStorage engine:\n  ssd - B-Tree storage engine optimized for solid state disks.\n  memory - Durable in-memory storage engine for small datasets.\n\nproxies=<PROXIES>: Sets the desired number of proxies in the cluster. Must be at least 1, or set to -1 which restores the number of proxies to the default value.\n\nlogs=<LOGS>: Sets the desired number of log servers in the cluster. Must be at least 1, or set to -1 which restores the number of logs to the default value.\n\nresolvers=<RESOLVERS>: Sets the desired number of resolvers in the cluster. Must be at least 1, or set to -1 which restores the number of resolvers to the default value.\n\nSee the FoundationDB Administration Guide for more information.");
+		"The `new' option, if present, initializes a new database with the given configuration rather than changing the configuration of an existing one. When used, both a redundancy mode and a storage engine must be specified.\n\nRedundancy mode:\n  single - one copy of the data.  Not fault tolerant.\n  double - two copies of data (survive one failure).\n  triple - three copies of data (survive two failures).\n  three_data_hall - See the Admin Guide.\n  three_datacenter - See the Admin Guide.\n\nStorage engine:\n  ssd - B-Tree storage engine optimized for solid state disks.\n  memory - Durable in-memory storage engine for small datasets.\n\nproxies=<PROXIES>: Sets the desired number of proxies in the cluster. Must be at least 1, or set to -1 which restores the number of proxies to the default value.\n\nlogs=<LOGS>: Sets the desired number of log servers in the cluster. Must be at least 1, or set to -1 which restores the number of logs to the default value.\n\nresolvers=<RESOLVERS>: Sets the desired number of resolvers in the cluster. Must be at least 1, or set to -1 which restores the number of resolvers to the default value.\n\nSee the FoundationDB Administration Guide for more information.");
 	helpMap["coordinators"] = CommandHelp(
 		"coordinators auto|<ADDRESS>+ [description=new_cluster_description]",
 		"change cluster coordinators or description",
@@ -1984,7 +1984,7 @@ void onoff_generator(const char* text, const char *line, std::vector<std::string
 }
 
 void configure_generator(const char* text, const char *line, std::vector<std::string>& lc) {
-	const char* opts[] = {"new", "single", "double", "triple", "three_data_hall", "three_datacenter", "multi_dc", "ssd", "ssd-1", "ssd-2", "memory", "proxies=", "logs=", "resolvers=", NULL};
+	const char* opts[] = {"new", "single", "double", "triple", "three_data_hall", "three_datacenter", "ssd", "ssd-1", "ssd-2", "memory", "proxies=", "logs=", "resolvers=", NULL};
 	array_generator(text, line, opts, lc);
 }
 

fdbclient/ManagementAPI.actor.cpp

@@ -105,25 +105,7 @@ std::map<std::string, std::string> configForToken( std::string const& mode ) {
 		redundancy="3";
 		log_replicas="3";
 		storagePolicy = tLogPolicy = IRepPolicyRef(new PolicyAcross(3, "zoneid", IRepPolicyRef(new PolicyOne())));
-	} else if(mode == "two_datacenter") {
+	} else if(mode == "three_datacenter" || mode == "multi_dc") {
-		redundancy="3";
-		log_replicas="3";
-		storagePolicy = tLogPolicy = IRepPolicyRef(new PolicyAcross(3, "zoneid", IRepPolicyRef(new PolicyOne())));
-	} else if(mode == "three_datacenter") {
-		redundancy="3";
-		log_replicas="3";
-		storagePolicy = tLogPolicy = IRepPolicyRef(new PolicyAnd({
-			IRepPolicyRef(new PolicyAcross(3, "dcid", IRepPolicyRef(new PolicyOne()))),
-			IRepPolicyRef(new PolicyAcross(3, "zoneid", IRepPolicyRef(new PolicyOne())))
-		}));
-	} else if(mode == "three_data_hall") {
-		redundancy="3";
-		log_replicas="4";
-		storagePolicy = IRepPolicyRef(new PolicyAcross(3, "data_hall", IRepPolicyRef(new PolicyOne())));
-		tLogPolicy = IRepPolicyRef(new PolicyAcross(2, "data_hall",
-			IRepPolicyRef(new PolicyAcross(2, "zoneid", IRepPolicyRef(new PolicyOne())))
-		));
-	} else if(mode == "multi_dc") {
 		redundancy="6";
 		log_replicas="4";
 		storagePolicy = IRepPolicyRef(new PolicyAcross(3, "dcid",
@@ -132,6 +114,13 @@ std::map<std::string, std::string> configForToken( std::string const& mode ) {
 		tLogPolicy = IRepPolicyRef(new PolicyAcross(2, "dcid",
 			IRepPolicyRef(new PolicyAcross(2, "zoneid", IRepPolicyRef(new PolicyOne())))
 		));
+	} else if(mode == "three_data_hall") {
+		redundancy="3";
+		log_replicas="4";
+		storagePolicy = IRepPolicyRef(new PolicyAcross(3, "data_hall", IRepPolicyRef(new PolicyOne())));
+		tLogPolicy = IRepPolicyRef(new PolicyAcross(2, "data_hall",
+			IRepPolicyRef(new PolicyAcross(2, "zoneid", IRepPolicyRef(new PolicyOne())))
+		));
 	} else
 		redundancySpecified = false;
 	if (redundancySpecified) {
@@ -303,12 +292,9 @@ ConfigureAutoResult parseConfig( StatusObject const& status ) {
 	} else if( result.old_replication == "triple" || result.old_replication == "fast_recovery_triple" ) {
 		storage_replication = 3;
 		log_replication = 3;
-	} else if( result.old_replication == "two_datacenter" ) {
-		storage_replication = 3;
-		log_replication = 3;
 	} else if( result.old_replication == "three_datacenter" ) {
-		storage_replication = 3;
+		storage_replication = 6;
-		log_replication = 3;
+		log_replication = 4;
 	} else
 		return ConfigureAutoResult();
 

fdbserver/DataDistributionQueue.actor.cpp

@@ -687,7 +687,7 @@ ACTOR Future<Void> dataDistributionRelocator( DDQueueData *self, RelocateData rd
 				}
 				TEST(true); //did not find a healthy destination team on the first attempt
 				stuckCount++;
-				TraceEvent(stuckCount > 50 ? SevWarnAlways : SevWarn, "BestTeamStuck", masterId).detail("Count", stuckCount);
+				TraceEvent(stuckCount > 50 ? SevWarnAlways : SevWarn, "BestTeamStuck", masterId).detail("Count", stuckCount).suppressFor(1.0);
 				if(stuckCount > 50 && g_network->isSimulated()) { //FIXME: known bug in simulation we are supressing
 					int unseed = noUnseed ? 0 : g_random->randomInt(0, 100001);
 					TraceEvent("ElapsedTime").detail("SimTime", now()).detail("RealTime", 0)

fdbserver/DatabaseConfiguration.cpp

@@ -85,14 +85,12 @@ std::map<std::string, std::string> DatabaseConfiguration::toMap() const {
 				result["redundancy_mode"] = "single";
 			else if( tLogReplicationFactor == 2 && durableStorageQuorum == 2 )
 				result["redundancy_mode"] = "double";
-			else if( tLogReplicationFactor == 3 && durableStorageQuorum == 3 && tlogInfo == "((dcid^3 x 1) & (zoneid^3 x 1))" && storageInfo == "((dcid^3 x 1) & (zoneid^3 x 1))" )
+			else if( tLogReplicationFactor == 4 && durableStorageQuorum == 6 && tlogInfo == "dcid^2 x zoneid^2 x 1" && storageInfo == "dcid^3 x zoneid^2 x 1" )
 				result["redundancy_mode"] = "three_datacenter";
 			else if( tLogReplicationFactor == 3 && durableStorageQuorum == 3 )
 				result["redundancy_mode"] = "triple";
 			else if( tLogReplicationFactor == 4 && durableStorageQuorum == 3 && tlogInfo == "data_hall^2 x zoneid^2 x 1" && storageInfo == "data_hall^3 x 1" )
 				result["redundancy_mode"] = "three_data_hall";
-			else if( tLogReplicationFactor == 4 && durableStorageQuorum == 6 && tlogInfo == "dcid^2 x zoneid^2 x 1" && storageInfo == "dcid^3 x zoneid^2 x 1" )
-				result["redundancy_mode"] = "multi_dc";
 			else
 				result["redundancy_mode"] = "custom";
 		} else

fdbserver/MoveKeys.actor.cpp

@@ -318,11 +318,14 @@ ACTOR Future<Void> startMoveKeys( Database occ, KeyRange keys, vector<UID> serve
 					if (err.code() == error_code_move_to_removed_server)
 						throw;
 					Void _ = wait( tr.onError(e) );
-					TraceEvent(retries == 50 ? SevWarnAlways : SevWarn, "startMoveKeysRetrying", relocationIntervalId)
+
-						.detail("Keys", printable(keys))
+					if(retries%10 == 0) {
-						.detail("BeginKey", printable(begin))
+						TraceEvent(retries == 50 ? SevWarnAlways : SevWarn, "startMoveKeysRetrying", relocationIntervalId)
-						.detail("NumTries", retries)
+							.detail("Keys", printable(keys))
-						.error(err);
+							.detail("BeginKey", printable(begin))
+							.detail("NumTries", retries)
+							.error(err);
+					}
 				}
 			}
 
@@ -602,12 +605,15 @@ ACTOR Future<Void> finishMoveKeys( Database occ, KeyRange keys, vector<UID> dest
 					if (error.code() == error_code_actor_cancelled) throw;
 					state Error err = error;
 					Void _ = wait( tr.onError(error) );
-					TraceEvent(retries++ == 15 ? SevWarnAlways : SevWarn, "RelocateShard_finishMoveKeysRetrying", relocationIntervalId)
+					retries++;
-						.error(err)
+					if(retries%10 == 0) {
-						.detail("KeyBegin", printable(keys.begin))
+						TraceEvent(retries == 20 ? SevWarnAlways : SevWarn, "RelocateShard_finishMoveKeysRetrying", relocationIntervalId)
-						.detail("KeyEnd", printable(keys.end))
+							.error(err)
-						.detail("IterationBegin", printable(begin))
+							.detail("KeyBegin", printable(keys.begin))
-						.detail("IterationEnd", printable(endKey));
+							.detail("KeyEnd", printable(keys.end))
+							.detail("IterationBegin", printable(begin))
+							.detail("IterationEnd", printable(endKey));
+					}
 				}
 			}
 		}

fdbserver/SimulatedCluster.actor.cpp

@@ -735,14 +735,10 @@ void SimulationConfig::generateNormalConfig(int minimumReplication) {
 		break;
 	}
 	case 3: {
-		if( datacenters == 1 ) {
+		if( datacenters <= 2 ) {
 			TEST( true );  // Simulated cluster running in triple redundancy mode
 			set_config("triple");
 		}
-		else if( datacenters == 2 ) {
-			TEST( true );  // Simulated cluster running in 2 datacenter mode
-			set_config("two_datacenter");
-		}
 		else if( datacenters == 3 ) {
 			TEST( true );  // Simulated cluster running in 3 data-hall mode
 			set_config("three_data_hall");

fdbserver/workloads/ConsistencyCheck.actor.cpp

@@ -573,8 +573,12 @@ struct ConsistencyCheckWorkload : TestWorkload
 		state int increment = (self->distributed && !self->firstClient) ? effectiveClientCount * self->shardSampleFactor : 1;
 		state Reference<IRateControl> rateLimiter = Reference<IRateControl>( new SpeedLimit(self->rateLimit, CLIENT_KNOBS->CONSISTENCY_CHECK_RATE_WINDOW) );
 
-		int64_t _dbSize = wait( self->getDatabaseSize( cx ) );
+		state double dbSize = 100e12;
-		state double dbSize = _dbSize;
+		if(g_network->isSimulated()) {
+			//This call will get all shard ranges in the database, which is too expensive on real clusters.
+			int64_t _dbSize = wait( self->getDatabaseSize( cx ) );
+			dbSize = _dbSize;
+		}
 
 		state vector<KeyRangeRef> ranges;
 

flow/Net2.actor.cpp

@@ -240,7 +240,7 @@ public:
 		try {
 			if (error) {
 				// Log the error...
-				TraceEvent(SevWarn, errContext, errID).detail("Message", error.value());
+				TraceEvent(SevWarn, errContext, errID).detail("Message", error.value()).suppressFor(1.0);
 				p.sendError( connection_failed() );
 			} else
 				p.send( Void() );