[stats] lazyinit ClusterInfo::trafficStats()

envoy/stats/stats_macros.h

@@ -152,16 +152,41 @@ static inline std::string statPrefixJoin(absl::string_view prefix, absl::string_
  */
 #define MAKE_STATS_STRUCT(StatsStruct, StatNamesStruct, ALL_STATS)                                 \
   struct StatsStruct {                                                                             \
+    using StatNameType = StatNamesStruct;                                                          \
     StatsStruct(const StatNamesStruct& stat_names, Envoy::Stats::Scope& scope,                     \
                 Envoy::Stats::StatName prefix = Envoy::Stats::StatName())                          \
         : stat_names_(stat_names)                                                                  \
               ALL_STATS(MAKE_STATS_STRUCT_COUNTER_HELPER_, MAKE_STATS_STRUCT_GAUGE_HELPER_,        \
                         MAKE_STATS_STRUCT_HISTOGRAM_HELPER_,                                       \
                         MAKE_STATS_STRUCT_TEXT_READOUT_HELPER_,                                    \
                         MAKE_STATS_STRUCT_STATNAME_HELPER_) {}                                     \
-    const StatNamesStruct& stat_names_;                                                            \
+    const StatNameType& stat_names_;                                                               \
     ALL_STATS(GENERATE_COUNTER_STRUCT, GENERATE_GAUGE_STRUCT, GENERATE_HISTOGRAM_STRUCT,           \
               GENERATE_TEXT_READOUT_STRUCT, GENERATE_STATNAME_STRUCT)                              \
   }
 
+/**
+ * LazyInit$StatsStruct is a wrapper with creator of the actual "$StatsStruct"
+ * structure.
+ * It instantiate a $StatsStruct struct when any data member is referenced.
+ * See https://github.com/envoyproxy/envoy/issues/23575 for more details.
+ */
+template <typename StatsStructType> struct LazyInitStats {
+  LazyInitStats(Stats::Scope& scope, const typename StatsStructType::StatNameType& stat_names)
+      : scope_(scope), ctor_([&scope, &stat_names]() -> StatsStructType* {
+          ENVOY_LOG_MISC(error, "DDDD begin to create stats now...");
+          return new StatsStructType(stat_names, scope);
+        }) {}
+
+  StatsStructType* operator->() { return internal_stats_.get(ctor_); }
+  StatsStructType& operator*() { return *internal_stats_.get(ctor_); }
+
+  inline Stats::Scope& statsScope() { return scope_; }
+
+  Stats::Scope& scope_;
+  std::function<StatsStructType*()> ctor_;
+  Thread::AtomicPtr<StatsStructType, Thread::AtomicPtrAllocMode::DeleteOnDestruct>
+      internal_stats_{};
+};
+
 } // namespace Envoy

envoy/upstream/cluster_manager.h

@@ -378,7 +378,10 @@ class ClusterManager {
    *
    * @return the stat names.
    */
-  virtual const ClusterStatNames& clusterStatNames() const PURE;
+  virtual const ClusterUpstreamStatNames& clusterStatNames() const PURE;
+  virtual const ClusterConfigUpdateStatNames& clusterConfigUpdateStatNames() const PURE;
+  virtual const ClusterLbStatNames& clusterLbStatNames() const PURE;
+  virtual const ClusterEndpointStatNames& clusterEndpointStatNames() const PURE;
   virtual const ClusterLoadReportStatNames& clusterLoadReportStatNames() const PURE;
   virtual const ClusterCircuitBreakersStatNames& clusterCircuitBreakersStatNames() const PURE;
   virtual const ClusterRequestResponseSizeStatNames&

envoy/upstream/upstream.h

@@ -565,12 +565,39 @@ class PrioritySet {
 };
 
 /**
- * All cluster stats. @see stats_macros.h
+ * All cluster config update related stats.
+ * See https://github.com/envoyproxy/envoy/issues/23575 for details. Stats from ClusterInfo::stats()
+ * will be split into subgroups "config-update", "lb", "endpoint" and "upstream", roughly based on
+ * their semantics. This list of stats are separated from Cluster::stats() since they are "config
+ * pipeline related".
+ *
+ * Each group of
  */
-#define ALL_CLUSTER_STATS(COUNTER, GAUGE, HISTOGRAM, TEXT_READOUT, STATNAME)                       \
+#define ALL_CLUSTER_CONFIG_UPDATE_STATS(COUNTER, GAUGE, HISTOGRAM, TEXT_READOUT, STATNAME)         \
   COUNTER(assignment_stale)                                                                        \
   COUNTER(assignment_timeout_received)                                                             \
-  COUNTER(bind_errors)                                                                             \
+  COUNTER(update_attempt)                                                                          \
+  COUNTER(update_empty)                                                                            \
+  COUNTER(update_failure)                                                                          \
+  COUNTER(update_no_rebuild)                                                                       \
+  COUNTER(update_success)                                                                          \
+  GAUGE(version, NeverImport)
+
+/**
+ * All cluster endpoints related stats.
+ */
+#define ALL_CLUSTER_ENDPOINT_STATS(COUNTER, GAUGE, HISTOGRAM, TEXT_READOUT, STATNAME)              \
+  GAUGE(max_host_weight, NeverImport)                                                              \
+  COUNTER(membership_change)                                                                       \
+  GAUGE(membership_degraded, NeverImport)                                                          \
+  GAUGE(membership_excluded, NeverImport)                                                          \
+  GAUGE(membership_healthy, NeverImport)                                                           \
+  GAUGE(membership_total, NeverImport)
+
+/**
+ * All cluster loadbalancing related stats.
+ */
+#define ALL_CLUSTER_LB_STATS(COUNTER, GAUGE, HISTOGRAM, TEXT_READOUT, STATNAME)                    \
   COUNTER(lb_healthy_panic)                                                                        \
   COUNTER(lb_local_cluster_not_ok)                                                                 \
   COUNTER(lb_recalculate_zone_structures)                                                          \
@@ -585,14 +612,15 @@ class PrioritySet {
   COUNTER(lb_zone_routing_all_directly)                                                            \
   COUNTER(lb_zone_routing_cross_zone)                                                              \
   COUNTER(lb_zone_routing_sampled)                                                                 \
-  COUNTER(membership_change)                                                                       \
+  GAUGE(lb_subsets_active, Accumulate)
+
+/**
+ * All cluster stats. @see stats_macros.h
+ */
+#define ALL_CLUSTER_UPSTREAM_STATS(COUNTER, GAUGE, HISTOGRAM, TEXT_READOUT, STATNAME)              \
+  COUNTER(bind_errors)                                                                             \
   COUNTER(original_dst_host_invalid)                                                               \
   COUNTER(retry_or_shadow_abandoned)                                                               \
-  COUNTER(update_attempt)                                                                          \
-  COUNTER(update_empty)                                                                            \
-  COUNTER(update_failure)                                                                          \
-  COUNTER(update_no_rebuild)                                                                       \
-  COUNTER(update_success)                                                                          \
   COUNTER(upstream_cx_close_notify)                                                                \
   COUNTER(upstream_cx_connect_attempts_exceeded)                                                   \
   COUNTER(upstream_cx_connect_fail)                                                                \
@@ -644,18 +672,11 @@ class PrioritySet {
   COUNTER(upstream_rq_total)                                                                       \
   COUNTER(upstream_rq_tx_reset)                                                                    \
   COUNTER(upstream_http3_broken)                                                                   \
-  GAUGE(lb_subsets_active, Accumulate)                                                             \
-  GAUGE(max_host_weight, NeverImport)                                                              \
-  GAUGE(membership_degraded, NeverImport)                                                          \
-  GAUGE(membership_excluded, NeverImport)                                                          \
-  GAUGE(membership_healthy, NeverImport)                                                           \
-  GAUGE(membership_total, NeverImport)                                                             \
   GAUGE(upstream_cx_active, Accumulate)                                                            \
   GAUGE(upstream_cx_rx_bytes_buffered, Accumulate)                                                 \
   GAUGE(upstream_cx_tx_bytes_buffered, Accumulate)                                                 \
   GAUGE(upstream_rq_active, Accumulate)                                                            \
   GAUGE(upstream_rq_pending_active, Accumulate)                                                    \
-  GAUGE(version, NeverImport)                                                                      \
   HISTOGRAM(upstream_cx_connect_ms, Milliseconds)                                                  \
   HISTOGRAM(upstream_cx_length_ms, Milliseconds)
 
@@ -707,11 +728,30 @@ class PrioritySet {
   HISTOGRAM(upstream_rq_timeout_budget_percent_used, Unspecified)                                  \
   HISTOGRAM(upstream_rq_timeout_budget_per_try_percent_used, Unspecified)
 
+/**
+ * Struct definition for cluster config update stats. @see stats_macros.h
+ */
+MAKE_STAT_NAMES_STRUCT(ClusterConfigUpdateStatNames, ALL_CLUSTER_CONFIG_UPDATE_STATS);
+MAKE_STATS_STRUCT(ClusterConfigUpdateStats, ClusterConfigUpdateStatNames,
+                  ALL_CLUSTER_CONFIG_UPDATE_STATS);
+
+/**
+ * Struct definition for cluster endpoint related stats. @see stats_macros.h
+ */
+MAKE_STAT_NAMES_STRUCT(ClusterEndpointStatNames, ALL_CLUSTER_ENDPOINT_STATS);
+MAKE_STATS_STRUCT(ClusterEndpointStats, ClusterEndpointStatNames, ALL_CLUSTER_ENDPOINT_STATS);
+
+/**
+ * Struct definition for cluster load balancing stats. @see stats_macros.h
+ */
+MAKE_STAT_NAMES_STRUCT(ClusterLbStatNames, ALL_CLUSTER_LB_STATS);
+MAKE_STATS_STRUCT(ClusterLbStats, ClusterLbStatNames, ALL_CLUSTER_LB_STATS);
+
 /**
  * Struct definition for all cluster stats. @see stats_macros.h
  */
-MAKE_STAT_NAMES_STRUCT(ClusterStatNames, ALL_CLUSTER_STATS);
-MAKE_STATS_STRUCT(ClusterStats, ClusterStatNames, ALL_CLUSTER_STATS);
+MAKE_STAT_NAMES_STRUCT(ClusterUpstreamStatNames, ALL_CLUSTER_UPSTREAM_STATS);
+MAKE_STATS_STRUCT(ClusterUpstreamStats, ClusterUpstreamStatNames, ALL_CLUSTER_UPSTREAM_STATS);
 
 MAKE_STAT_NAMES_STRUCT(ClusterLoadReportStatNames, ALL_CLUSTER_LOAD_REPORT_STATS);
 MAKE_STATS_STRUCT(ClusterLoadReportStats, ClusterLoadReportStatNames,
@@ -992,9 +1032,24 @@ class ClusterInfo : public Http::FilterChainFactory {
   virtual TransportSocketMatcher& transportSocketMatcher() const PURE;
 
   /**
-   * @return ClusterStats& strongly named stats for this cluster.
+   * @return ClusterConfigUpdateStats& strongly named config update stats for this cluster.
+   */
+  virtual ClusterConfigUpdateStats& configUpdateStats() const PURE;
+
+  /**
+   * @return ClusterLbStats& strongly named stats for this cluster.
+   */
+  virtual ClusterLbStats& lbStats() const PURE;
+
+  /**
+   * @return ClusterEndpointStats& strongly named stats for this cluster.
+   */
+  virtual ClusterEndpointStats& endpointStats() const PURE;
+
+  /**
+   * @return ClusterUpstreamStats& strongly named stats for this cluster.
    */
-  virtual ClusterStats& stats() const PURE;
+  virtual LazyInitStats<ClusterUpstreamStats>& upstreamStats() const PURE;
 
   /**
    * @return the stats scope that contains all cluster stats. This can be used to produce dynamic