From bf4e9e11d5a5851f8adea9bdaa8f4cfef417add3 Mon Sep 17 00:00:00 2001
From: Frederic Suter <frederic.suter@cc.in2p3.fr>
Date: Sun, 5 Aug 2018 14:46:25 +0200
Subject: [PATCH] add more info and revalidate to where it diverges

---
 .../s4u-platform-failures.cpp                 |  4 +++-
 .../s4u-platform-failures.tesh                | 22 ++++++++++++++-----
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/examples/s4u/platform-failures/s4u-platform-failures.cpp b/examples/s4u/platform-failures/s4u-platform-failures.cpp
index 941ea2aba8..db0ee4cf33 100644
--- a/examples/s4u/platform-failures/s4u-platform-failures.cpp
+++ b/examples/s4u/platform-failures/s4u-platform-failures.cpp
@@ -25,8 +25,9 @@ static int master(int argc, char* argv[])
     mailbox         = simgrid::s4u::Mailbox::by_name(std::string("worker-") + std::to_string(i % workers_count));
     double* payload = new double(comp_size);
     try {
+      XBT_INFO("Send a message to %s", mailbox->get_cname());
       mailbox->put(payload, comm_size, 10.0);
-      XBT_INFO("Send completed");
+      XBT_INFO("Send to %s completed", mailbox->get_cname());
     } catch (xbt_ex& e) {
       switch (e.category) {
         case host_error:
@@ -84,6 +85,7 @@ static int worker(int argc, char* argv[])
   double comp_size                 = -1;
   while (1) {
     try {
+      XBT_INFO("Waiting a message on %s", mailbox->get_cname());
       payload   = static_cast<double*>(mailbox->get());
       comp_size = *payload;
       delete payload;
diff --git a/examples/s4u/platform-failures/s4u-platform-failures.tesh b/examples/s4u/platform-failures/s4u-platform-failures.tesh
index 5738a23318..e51427bf26 100644
--- a/examples/s4u/platform-failures/s4u-platform-failures.tesh
+++ b/examples/s4u/platform-failures/s4u-platform-failures.tesh
@@ -6,16 +6,28 @@ p Testing a simple master/worker example application handling failures TCP cross
 $ $SG_TEST_EXENV ${bindir:=.}/s4u-platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${bindir}/../app-masterworker/s4u-app-masterworker_d.xml --cfg=path:${srcdir} --cfg=network/crosstraffic:0 "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
 > [  0.000000] (0:maestro@) Cannot launch process 'worker' on failed host 'Fafard'
 > [  0.000000] (1:master@Tremblay) Got 5 workers and 20 tasks to process
-> [  0.010309] (1:master@Tremblay) Send completed
+> [  0.000000] (1:master@Tremblay) Send a message to worker-0
+> [  0.010309] (1:master@Tremblay) Send to worker-0 completed
+> [  0.000000] (2:worker@Tremblay) Waiting a message on worker-0
+> [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
+> [  0.000000] (4:worker@Ginette) Waiting a message on worker-3
+> [  0.000000] (5:worker@Bourassa) Waiting a message on worker-4
+> [  0.010309] (1:master@Tremblay) Send a message to worker-1
 > [  1.000000] (0:maestro@) Restart processes on host Fafard
 > [  1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-1'. Nevermind. Let's keep going!
+> [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  1.000000] (3:worker@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
+> [  2.010309] (2:worker@Tremblay) Waiting a message on worker-0
 > [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 12.030928] (1:master@Tremblay) Send completed
-> [ 13.061856] (1:master@Tremblay) Send completed
-> [ 13.072165] (1:master@Tremblay) Send completed
-> [ 14.103093] (1:master@Tremblay) Send completed
+> [ 11.000000] (1:master@Tremblay) Send a message to worker-3
+> [ 12.030928] (1:master@Tremblay) Send to worker-3 completed
+> [ 12.030928] (1:master@Tremblay) Send a message to worker-4
+> [ 13.061856] (1:master@Tremblay) Send to worker-4 completed
+> [ 13.061856] (1:master@Tremblay) Send a message to worker-0
+> [ 13.072165] (1:master@Tremblay) Send to worker-0 completed
+> [ 13.072165] (1:master@Tremblay) Send a message to worker-1
+> [ 14.103093] (1:master@Tremblay) Send to worker-1 completed
 > [ 24.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 24.103093] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
 > [ 24.103093] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
-- 
2.20.1