From 766f8c30439932a18f59b4cd51421a6379f5488c Mon Sep 17 00:00:00 2001
From: JamesWrigley <james@puiterwijk.org>
Date: Fri, 6 Dec 2024 22:12:27 +0100
Subject: [PATCH] Replace a timeout task with timedwait()

According to a stacktrace from a hung DistributedNext CI job this task was
causing the process to hang before exiting:
```julia
InterruptException()
_jl_mutex_unlock at C:/workdir/src\threading.c:1012
jl_mutex_unlock at C:/workdir/src\julia_locks.h:80 [inlined]
ijl_task_get_next at C:/workdir/src\scheduler.c:458
poptask at .\task.jl:1163
wait at .\task.jl:1172
task_done_hook at .\task.jl:839
jfptr_task_done_hook_98752.1 at C:\hostedtoolcache\windows\julia\nightly\x64\lib\julia\sys.dll (unknown line)
jl_apply at C:/workdir/src\julia.h:2233 [inlined]
jl_finish_task at C:/workdir/src\task.c:338
start_task at C:/workdir/src\task.c:1274
      From worker 82:	fatal: error thrown and no exception handler available.Unhandled Task ERROR: InterruptException:
Stacktrace:
 [1] poptask(W::Base.IntrusiveLinkedListSynchronized{Task})
   @ Base .\task.jl:1163
 [2] wait()
   @ Base .\task.jl:1172
 [3] wait(c::Base.GenericCondition{ReentrantLock}; first::Bool)
   @ Base .\condition.jl:141
 [4] wait
   @ .\condition.jl:136 [inlined]
 [5] put_buffered(c::Channel{Any}, v::Int64)
   @ Base .\channels.jl:420
 [6] put!(c::Channel{Any}, v::Int64)
   @ Base .\channels.jl:398
 [7] put!(rv::DistributedNext.RemoteValue, args::Int64)
   @ DistributedNext D:\a\DistributedNext.jl\DistributedNext.jl\src\remotecall.jl:703
 [8] (::DistributedNext.var"#create_worker##11#create_worker##12"{DistributedNext.RemoteValue, Float64})()
   @ DistributedNext D:\a\DistributedNext.jl\DistributedNext.jl\src\cluster.jl:721
```

Replaced it with a call to `timedwait()`, which has the advantage of being a lot
simpler than an extra task.
---
 src/cluster.jl | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/src/cluster.jl b/src/cluster.jl
index 2444695..5712451 100644
--- a/src/cluster.jl
+++ b/src/cluster.jl
@@ -683,11 +683,9 @@ function create_worker(manager, wconfig)
     send_msg_now(w, MsgHeader(RRID(0,0), ntfy_oid), join_message)
 
     @async manage(w.manager, w.id, w.config, :register)
+
     # wait for rr_ntfy_join with timeout
-    timedout = false
-    @async (sleep($timeout); timedout = true; put!(rr_ntfy_join, 1))
-    wait(rr_ntfy_join)
-    if timedout
+    if timedwait(() -> isready(rr_ntfy_join), timeout) === :timed_out
         error("worker did not connect within $timeout seconds")
     end
     lock(client_refs) do