From 35e9f087f74d84bc9279fa97e95be566a2b77408 Mon Sep 17 00:00:00 2001
From: Arthur031221 <levi74108520963@gmail.com>
Date: Sat, 10 Oct 2026 13:29:52 +0800
Subject: [PATCH] BUG FIX: Shut down relaunched cluster workers when the plan
 is stopped

When a cluster worker is terminated (for example by cancel()) and then
relaunched, the new node was stored in the backend but not in the
cluster registry. stopCluster() then closed the old node and left the
relaunched worker process and its connection open until garbage
collection.
---
 NEWS.md                                       |  6 +++
 R/backend_api-11.ClusterFutureBackend-class.R | 15 +++++++
 inst/testme/test-cancel-relaunch-cluster.R    | 40 +++++++++++++++++++
 tests/test-cancel-relaunch-cluster.R          |  4 ++
 4 files changed, 65 insertions(+)
 create mode 100644 inst/testme/test-cancel-relaunch-cluster.R
 create mode 100644 tests/test-cancel-relaunch-cluster.R

diff --git a/NEWS.md b/NEWS.md
index d2106035..4b3fcd6e 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -23,6 +23,12 @@
 
  * Futures failed on R (< 4.0.0). This bug was introduced in **future**
    1.68.0 (2025-11-17).
+
+ * When a cluster worker that `plan()` had started was relaunched after
+   it was canceled, interrupted or had died, `plan()` never shut the
+   relaunched worker down, because the cluster registry kept the old
+   node. The worker process and its connection were left running until
+   garbage collection.
    
 
 # Version 1.76.0 [2026-09-24]
diff --git a/R/backend_api-11.ClusterFutureBackend-class.R b/R/backend_api-11.ClusterFutureBackend-class.R
index 7d289ff7..95fffa52 100644
--- a/R/backend_api-11.ClusterFutureBackend-class.R
+++ b/R/backend_api-11.ClusterFutureBackend-class.R
@@ -1231,6 +1231,7 @@ requestNode <- local({
 
         workers[[node_idx]] <- node2
         backend[["workers"]] <- workers
+        clusterRegistry$replaceNode(workers, node_idx, node2)
         node <- node2
 
         if (debug) {
@@ -1609,6 +1610,7 @@ handleInterruptedFuture <- local({
 
         ## Update backend
         backend[["workers"]] <- workers
+        clusterRegistry$replaceNode(workers, node_idx, node2)
 
         node <- NULL
         
@@ -1743,6 +1745,18 @@ clusterRegistry <- local({
     cluster
   } ## startCluster()
 
+  ## When a worker is relaunched, the registry must track the new node,
+  ## otherwise stopCluster() closes the old, already closed, node and leaves
+  ## the relaunched worker and its connection behind
+  replaceNode <- function(workers, idx, node) {
+    if (is.null(cluster)) return(invisible(FALSE))
+    if (!identical(attr(workers, "name", exact = TRUE), attr(cluster, "name", exact = TRUE))) {
+      return(invisible(FALSE))
+    }
+    cluster[[idx]] <<- node
+    invisible(TRUE)
+  } ## replaceNode()
+
   stopCluster <- function(debug = FALSE) {
     if (debug) {
       mdebug_push("Stopping existing cluster ...")
@@ -1800,6 +1814,7 @@ clusterRegistry <- local({
   list(
       getCluster = getCluster,
     startCluster = startCluster,
+     replaceNode = replaceNode,
      stopCluster = stopCluster
   )
 }) ## clusterRegistry()
diff --git a/inst/testme/test-cancel-relaunch-cluster.R b/inst/testme/test-cancel-relaunch-cluster.R
new file mode 100644
index 00000000..b62e0100
--- /dev/null
+++ b/inst/testme/test-cancel-relaunch-cluster.R
@@ -0,0 +1,40 @@
+#' @tags cancel
+#' @tags detritus-files
+#' @tags detritus-connections
+#' @tags multisession
+
+library(future)
+
+message("Relaunched cluster workers are shut down with the plan ...")
+
+covr_testing <- ("covr" %in% loadedNamespaces())
+
+## Terminated workers can leave truncated coverage traces.
+if (!covr_testing) {
+  n0 <- nrow(showConnections())
+
+  plan(multisession, workers = I(1))
+
+  ## Cancel a running future, which terminates its worker
+  f <- future({ Sys.sleep(30); 42 })
+  Sys.sleep(1.0)
+  f <- cancel(f)
+
+  ## The next future relaunches the terminated worker
+  f2 <- future(42)
+  stopifnot(value(f2) == 42)
+
+  ## Keep a reference, so that garbage collection cannot hide the leak
+  backend <- plan("backend")
+
+  plan(sequential)
+
+  ## The relaunched worker must be closed by plan(), not by garbage collection
+  n <- nrow(showConnections())
+  message("Connections: before = ", n0, ", after = ", n)
+  stopifnot(n <= n0)
+  rm(list = "backend")
+  gc()
+}
+
+message("Relaunched cluster workers are shut down with the plan ... done")
diff --git a/tests/test-cancel-relaunch-cluster.R b/tests/test-cancel-relaunch-cluster.R
new file mode 100644
index 00000000..2d530ad3
--- /dev/null
+++ b/tests/test-cancel-relaunch-cluster.R
@@ -0,0 +1,4 @@
+#! /usr/bin/env Rscript
+## This runs testme test script inst/testme/test-cancel-relaunch-cluster.R
+## Don't edit - it was autogenerated by inst/testme/deploy.R
+future:::testme("cancel-relaunch-cluster")