From 5160fe051c0f2a507d0339b79b934665fb54030e Mon Sep 17 00:00:00 2001
From: Syed Paymaan Raza <1238752+spraza@users.noreply.github.com>
Date: Fri, 13 Dec 2024 15:28:16 -0800
Subject: [PATCH 1/2] Extend gray failure recentHealthTriggeredRecoveryTime
 state to reflect any recovery, including non-gray failure triggered ones

---
 fdbclient/include/fdbclient/ServerKnobs.h | 5 +++--
 fdbserver/ClusterController.actor.cpp     | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fdbclient/include/fdbclient/ServerKnobs.h b/fdbclient/include/fdbclient/ServerKnobs.h
index ee732445471..de719bd3601 100644
--- a/fdbclient/include/fdbclient/ServerKnobs.h
+++ b/fdbclient/include/fdbclient/ServerKnobs.h
@@ -776,8 +776,9 @@ class SWIFT_CXX_IMMORTAL_SINGLETON_TYPE ServerKnobs : public KnobsImpl<ServerKno
 	double CC_TRACKING_HEALTH_RECOVERY_INTERVAL; // The number of recovery count should not exceed
 	                                             // CC_MAX_HEALTH_RECOVERY_COUNT within
 	                                             // CC_TRACKING_HEALTH_RECOVERY_INTERVAL.
-	int CC_MAX_HEALTH_RECOVERY_COUNT; // The max number of recoveries can be triggered due to worker health within
-	                                  // CC_TRACKING_HEALTH_RECOVERY_INTERVAL
+	int CC_MAX_HEALTH_RECOVERY_COUNT; // The max number of gray failure recoveries that can be triggered due to worker
+	                                  // health within CC_TRACKING_HEALTH_RECOVERY_INTERVAL. This count accounts for any
+	                                  // recovery trigger including the ones by gray failure itself.
 	bool CC_HEALTH_TRIGGER_FAILOVER; // Whether to enable health triggered failover in CC.
 	int CC_FAILOVER_DUE_TO_HEALTH_MIN_DEGRADATION; // The minimum number of degraded servers that can trigger a
 	                                               // failover.
diff --git a/fdbserver/ClusterController.actor.cpp b/fdbserver/ClusterController.actor.cpp
index c79578cf6c2..8431db1e568 100644
--- a/fdbserver/ClusterController.actor.cpp
+++ b/fdbserver/ClusterController.actor.cpp
@@ -297,6 +297,7 @@ ACTOR Future<Void> clusterWatchDatabase(ClusterControllerData* cluster,
 
 			collection = actorCollection(db->recoveryData->addActor.getFuture());
 			recoveryCore = clusterRecoveryCore(db->recoveryData);
+			cluster->recentHealthTriggeredRecoveryTime.push(now());
 
 			// Master failure detection is pretty sensitive, but if we are in the middle of a very long recovery we
 			// really don't want to have to start over
@@ -3061,7 +3062,6 @@ ACTOR Future<Void> workerHealthMonitor(ClusterControllerData* self) {
 				if (self->shouldTriggerRecoveryDueToDegradedServers()) {
 					if (SERVER_KNOBS->CC_HEALTH_TRIGGER_RECOVERY) {
 						if (self->recentRecoveryCountDueToHealth() < SERVER_KNOBS->CC_MAX_HEALTH_RECOVERY_COUNT) {
-							self->recentHealthTriggeredRecoveryTime.push(now());
 							self->excludedDegradedServers.clear();
 							for (const auto& degradedServer : self->degradationInfo.degradedServers) {
 								self->excludedDegradedServers[degradedServer] = now();

From 49bcf0d5aeaf2b4a3e73515dcc811b1f80d0d86f Mon Sep 17 00:00:00 2001
From: Syed Paymaan Raza <1238752+spraza@users.noreply.github.com>
Date: Fri, 10 Jan 2025 16:16:40 -0800
Subject: [PATCH 2/2] Update knob documentation

---
 fdbclient/include/fdbclient/ServerKnobs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fdbclient/include/fdbclient/ServerKnobs.h b/fdbclient/include/fdbclient/ServerKnobs.h
index de719bd3601..5fb2914f612 100644
--- a/fdbclient/include/fdbclient/ServerKnobs.h
+++ b/fdbclient/include/fdbclient/ServerKnobs.h
@@ -776,9 +776,9 @@ class SWIFT_CXX_IMMORTAL_SINGLETON_TYPE ServerKnobs : public KnobsImpl<ServerKno
 	double CC_TRACKING_HEALTH_RECOVERY_INTERVAL; // The number of recovery count should not exceed
 	                                             // CC_MAX_HEALTH_RECOVERY_COUNT within
 	                                             // CC_TRACKING_HEALTH_RECOVERY_INTERVAL.
-	int CC_MAX_HEALTH_RECOVERY_COUNT; // The max number of gray failure recoveries that can be triggered due to worker
+	int CC_MAX_HEALTH_RECOVERY_COUNT; // The max number recoveries that can be triggered due to worker
 	                                  // health within CC_TRACKING_HEALTH_RECOVERY_INTERVAL. This count accounts for any
-	                                  // recovery trigger including the ones by gray failure itself.
+	                                  // recovery trigger including non-gray failure ones.
 	bool CC_HEALTH_TRIGGER_FAILOVER; // Whether to enable health triggered failover in CC.
 	int CC_FAILOVER_DUE_TO_HEALTH_MIN_DEGRADATION; // The minimum number of degraded servers that can trigger a
 	                                               // failover.