From eb2590b7742c06a6b99ed319c7ca5629fc1dc058 Mon Sep 17 00:00:00 2001
From: Chen Qin <qinnchen@gmail.com>
Date: Fri, 26 Oct 2018 12:39:31 -0700
Subject: [PATCH] workaround macosx java test race condition (#74)

* fix error in dmlc#57, clean up comments and naming

* include missing packages, disable recovery tests for now

* disable local_recover tests until we have a bug fix

* support larger cluster

* fix lint, merge with master

* fix mac osx test failure in https://github.com/dmlc/xgboost/pull/3818

* Update allreduce_robust.cc
---
 src/allreduce_robust.cc | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/src/allreduce_robust.cc b/src/allreduce_robust.cc
index 210d5d8a3..db829eaa5 100644
--- a/src/allreduce_robust.cc
+++ b/src/allreduce_robust.cc
@@ -50,6 +50,12 @@ void AllreduceRobust::Shutdown(void) {
   // execute check ack step, load happens here
   utils::Assert(RecoverExec(NULL, 0, ActionSummary::kCheckAck, ActionSummary::kSpecialOp),
                 "Shutdown: check ack must return true");
+#ifdef __APPLE__
+  // In OSX, one worker shutdowns and closes sockets while rest still run kCheckAck
+  // This cause rest workers checkandrecover and hang inf, https://github.com/dmlc/xgboost/pull/3818
+  // TODO: a fundamental fix for this
+  sleep(2);
+#endif
   AllreduceBase::Shutdown();
 }
 /*!