Send server_id for statistics reports. (#1698)

This change introduces the `pg_dist_node_metadata` which has a single jsonb value. When creating
the extension, a random server id is generated and stored in there. Everything in the metadata table
is added as a nested objected to the json payload that is sent to the reports server.

src/backend/distributed/Makefile

@@ -12,7 +12,7 @@ EXTVERSIONS = 5.0 5.0-1 5.0-2  \
 	6.1-1 6.1-2 6.1-3 6.1-4 6.1-5 6.1-6 6.1-7 6.1-8 6.1-9 6.1-10 6.1-11 6.1-12 6.1-13 6.1-14 6.1-15 6.1-16 6.1-17 \
 	6.2-1 6.2-2 6.2-3 6.2-4 \
 	7.0-1 7.0-2 7.0-3 7.0-4 7.0-5 7.0-6 7.0-7 7.0-8 7.0-9 7.0-10 7.0-11 7.0-12 7.0-13 7.0-14 7.0-15 \
-	7.1-1 7.1-2
+	7.1-1 7.1-2 7.1-3
 
 # All citus--*.sql files in the source directory
 DATA = $(patsubst $(citus_abs_srcdir)/%.sql,%.sql,$(wildcard $(citus_abs_srcdir)/$(EXTENSION)--*--*.sql))
@@ -174,6 +174,8 @@ $(EXTENSION)--7.1-1.sql: $(EXTENSION)--7.0-15.sql $(EXTENSION)--7.0-15--7.1-1.sq
 	cat $^ > $@
 $(EXTENSION)--7.1-2.sql: $(EXTENSION)--7.1-1.sql $(EXTENSION)--7.1-1--7.1-2.sql
 	cat $^ > $@
+$(EXTENSION)--7.1-3.sql: $(EXTENSION)--7.1-2.sql $(EXTENSION)--7.1-2--7.1-3.sql
+	cat $^ > $@
 
 NO_PGXS = 1
 

src/backend/distributed/citus--7.1-2--7.1-3.sql

@@ -0,0 +1,17 @@
+/* citus--7.1-2--7.1-3 */
+
+CREATE TABLE citus.pg_dist_node_metadata(
+    metadata jsonb NOT NULL
+);
+ALTER TABLE citus.pg_dist_node_metadata SET SCHEMA pg_catalog;
+GRANT SELECT ON pg_catalog.pg_dist_node_metadata TO public;
+
+CREATE FUNCTION pg_catalog.citus_server_id()
+    RETURNS uuid
+    LANGUAGE C STRICT
+    AS 'MODULE_PATHNAME', $$citus_server_id$$;
+COMMENT ON FUNCTION citus_server_id()
+    IS 'generates a random UUID to be used as server identifier';
+
+INSERT INTO pg_dist_node_metadata
+    VALUES (jsonb_build_object('server_id', citus_server_id()::text));

src/backend/distributed/citus.control

@@ -1,6 +1,6 @@
 # Citus extension
 comment = 'Citus distributed database'
-default_version = '7.1-2'
+default_version = '7.1-3'
 module_pathname = '$libdir/citus'
 relocatable = false
 schema = pg_catalog

src/backend/distributed/utils/metadata_cache.c

@@ -31,6 +31,7 @@
 #include "distributed/metadata_cache.h"
 #include "distributed/multi_logical_optimizer.h"
 #include "distributed/pg_dist_local_group.h"
+#include "distributed/pg_dist_node_metadata.h"
 #include "distributed/pg_dist_node.h"
 #include "distributed/pg_dist_partition.h"
 #include "distributed/pg_dist_shard.h"
@@ -3167,3 +3168,51 @@ CitusInvalidateRelcacheByShardId(int64 shardId)
 	/* bump command counter, to force invalidation to take effect */
 	CommandCounterIncrement();
 }
+
+
+/*
+ * DistNodeMetadata returns the single metadata jsonb object stored in
+ * pg_dist_node_metadata.
+ */
+Datum
+DistNodeMetadata(void)
+{
+	Datum metadata = 0;
+	SysScanDesc scanDescriptor = NULL;
+	ScanKeyData scanKey[1];
+	const int scanKeyCount = 0;
+	HeapTuple heapTuple = NULL;
+	Oid metadataTableOid = InvalidOid;
+	Relation pgDistNodeMetadata = NULL;
+	TupleDesc tupleDescriptor = NULL;
+
+	metadataTableOid = get_relname_relid("pg_dist_node_metadata", PG_CATALOG_NAMESPACE);
+	if (metadataTableOid == InvalidOid)
+	{
+		ereport(ERROR, (errmsg("pg_dist_node_metadata was not found")));
+	}
+
+	pgDistNodeMetadata = heap_open(metadataTableOid, AccessShareLock);
+	scanDescriptor = systable_beginscan(pgDistNodeMetadata,
+										InvalidOid, false,
+										NULL, scanKeyCount, scanKey);
+	tupleDescriptor = RelationGetDescr(pgDistNodeMetadata);
+
+	heapTuple = systable_getnext(scanDescriptor);
+	if (HeapTupleIsValid(heapTuple))
+	{
+		bool isNull = false;
+		metadata = heap_getattr(heapTuple, Anum_pg_dist_node_metadata_metadata,
+								tupleDescriptor, &isNull);
+		Assert(!isNull);
+	}
+	else
+	{
+		ereport(ERROR, (errmsg("could not find any entries in pg_dist_metadata")));
+	}
+
+	systable_endscan(scanDescriptor);
+	heap_close(pgDistNodeMetadata, AccessShareLock);
+
+	return metadata;
+}

src/backend/distributed/utils/statistics_collection.c

@@ -11,6 +11,12 @@
 #include "postgres.h"
 
 #include "citus_version.h"
+#include "fmgr.h"
+#include "utils/uuid.h"
+
+#if PG_VERSION_NUM >= 100000
+#include "utils/backend_random.h"
+#endif
 
 bool EnableStatisticsCollection = true; /* send basic usage statistics to Citus */
 
@@ -25,6 +31,11 @@ bool EnableStatisticsCollection = true; /* send basic usage statistics to Citus
 #include "distributed/worker_manager.h"
 #include "lib/stringinfo.h"
 #include "utils/json.h"
+#include "utils/jsonb.h"
+
+#if PG_VERSION_NUM >= 100000
+#include "utils/fmgrprotos.h"
+#endif
 
 static uint64 NextPow2(uint64 n);
 static uint64 ClusterSize(List *distributedTableList);
@@ -61,6 +72,8 @@ CollectBasicUsageStatistics(void)
 	uint64 roundedClusterSize = 0;
 	uint32 workerNodeCount = 0;
 	StringInfo fields = makeStringInfo();
+	Datum metadataJsonbDatum = 0;
+	char *metadataJsonbStr = NULL;
 	struct utsname unameData;
 	memset(&unameData, 0, sizeof(unameData));
 
@@ -80,8 +93,9 @@ CollectBasicUsageStatistics(void)
 	roundedDistTableCount = NextPow2(list_length(distributedTables));
 	roundedClusterSize = NextPow2(ClusterSize(distributedTables));
 	workerNodeCount = ActivePrimaryNodeCount();
-	CommitTransactionCommand();
-
+	metadataJsonbDatum = DistNodeMetadata();
+	metadataJsonbStr = DatumGetCString(DirectFunctionCall1(jsonb_out,
+														   metadataJsonbDatum));
 	uname(&unameData);
 
 	appendStringInfoString(fields, "{\"citus_version\": ");
@@ -95,8 +109,11 @@ CollectBasicUsageStatistics(void)
 	escape_json(fields, unameData.release);
 	appendStringInfoString(fields, ",\"hwid\": ");
 	escape_json(fields, unameData.machine);
+	appendStringInfo(fields, ",\"node_metadata\": %s", metadataJsonbStr);
 	appendStringInfoString(fields, "}");
 
+	CommitTransactionCommand();
+
 	return SendHttpPostJsonRequest(STATS_COLLECTION_HOST "/v1/usage_reports",
 								   fields->data, HTTP_TIMEOUT_SECONDS);
 }
@@ -224,3 +241,39 @@ SendHttpPostJsonRequest(const char *url, const char *jsonObj, long timeoutSecond
 
 
 #endif /* HAVE_LIBCURL */
+
+PG_FUNCTION_INFO_V1(citus_server_id);
+
+/*
+ * citus_server_id returns a random UUID value as server identifier. This is
+ * modeled after PostgreSQL's pg_random_uuid().
+ */
+Datum
+citus_server_id(PG_FUNCTION_ARGS)
+{
+	uint8 *buf = (uint8 *) palloc(UUID_LEN);
+
+#if PG_VERSION_NUM >= 100000
+	if (!pg_backend_random((char *) buf, UUID_LEN))
+	{
+		ereport(ERROR, (errmsg("failed to generate server identifier")));
+	}
+#else
+	{
+		int bufIdx = 0;
+		for (bufIdx = 0; bufIdx < UUID_LEN; bufIdx++)
+		{
+			buf[bufIdx] = (uint8) (random() & 0xFF);
+		}
+	}
+#endif
+
+	/*
+	 * Set magic numbers for a "version 4" (pseudorandom) UUID, see
+	 * http://tools.ietf.org/html/rfc4122#section-4.4
+	 */
+	buf[6] = (buf[6] & 0x0f) | 0x40;    /* "version" field */
+	buf[8] = (buf[8] & 0x3f) | 0x80;    /* "variant" field */
+
+	PG_RETURN_UUID_P((pg_uuid_t *) buf);
+}

src/include/distributed/metadata_cache.h

@@ -87,6 +87,7 @@ extern List * ShardPlacementList(uint64 shardId);
 extern void CitusInvalidateRelcacheByRelid(Oid relationId);
 extern void CitusInvalidateRelcacheByShardId(int64 shardId);
 extern void InvalidateMetadataSystemCache(void);
+extern Datum DistNodeMetadata(void);
 
 extern bool CitusHasBeenLoaded(void);
 extern bool CheckCitusVersion(int elevel);

src/include/distributed/pg_dist_node_metadata.h

@@ -0,0 +1,22 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_dist_node_metadata.h
+ *	  definition of the relation that holds the metadata table (pg_dist_node_metadata).
+ *
+ * Copyright (c) 2017, Citus Data, Inc.
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef PG_DIST_NODE_METADATA_H
+#define PG_DIST_NODE_METADATA_H
+
+
+/* ----------------
+ *      compiler constants for pg_dist_node_metadata
+ * ----------------
+ */
+#define Natts_pg_dist_node_metadata 1
+#define Anum_pg_dist_node_metadata_metadata 1
+
+#endif /* PG_DIST_NODE_METADATA_H */