From: Martin Quinson <martin.quinson@ens-rennes.fr>
Date: Fri, 15 Mar 2019 10:48:11 +0000 (+0100)
Subject: actors on failing hosts should die silently and with no delay
X-Git-Tag: v3_22~90
X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/simgrid.git/commitdiff_plain/5fa46b25d81881c427ca3233a43ce12aad4a0242

actors on failing hosts should die silently and with no delay
---

diff --git a/examples/deprecated/msg/platform-failures/platform-failures.tesh b/examples/deprecated/msg/platform-failures/platform-failures.tesh
index 9c64e17672..b903537584 100644
--- a/examples/deprecated/msg/platform-failures/platform-failures.tesh
+++ b/examples/deprecated/msg/platform-failures/platform-failures.tesh
@@ -19,9 +19,7 @@ $ $SG_TEST_EXENV ${bindir:=.}/platform-failures$EXEEXT --log=xbt_cfg.thres:criti
 > [  1.000000] (7:worker@Fafard) Waiting a message on worker-2
 > [  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] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
-> [  2.000000] (7:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
 > [  2.000000] (1:master@Tremblay) Send a message to worker-3
 > [  2.000000] (8:worker@Jupiter) Waiting a message on worker-1
@@ -126,12 +124,10 @@ $ $SG_TEST_EXENV ${bindir:=.}/platform-failures$EXEEXT --log=xbt_cfg.thres:criti
 > [  1.000000] (7:worker@Fafard) Waiting a message on worker-2
 > [  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
 > [  2.000000] (8:worker@Jupiter) Waiting a message on worker-1
 > [  2.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
 > [  2.000000] (1:master@Tremblay) Send a message to worker-3
-> [  2.000000] (7:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.010825] (2:worker@Tremblay) Execution complete.
 > [  2.010825] (2:worker@Tremblay) Waiting a message on worker-0
 > [  3.082474] (5:worker@Ginette) Start execution...
diff --git a/examples/s4u/platform-failures/s4u-platform-failures.cpp b/examples/s4u/platform-failures/s4u-platform-failures.cpp
index f0150d8d94..75669f5597 100644
--- a/examples/s4u/platform-failures/s4u-platform-failures.cpp
+++ b/examples/s4u/platform-failures/s4u-platform-failures.cpp
@@ -40,9 +40,6 @@ static int master(int argc, char* argv[])
       XBT_INFO("Send a message to %s", mailbox->get_cname());
       mailbox->put(payload, comm_size, 10.0);
       XBT_INFO("Send to %s completed", mailbox->get_cname());
-    } catch (simgrid::HostFailureException& e) {
-      XBT_INFO("Gloups. The cpu on which I'm running just turned off!. See you!");
-      return -1;
     } catch (simgrid::TimeoutError& e) {
       delete payload;
       XBT_INFO("Mmh. Got timeouted while speaking to '%s'. Nevermind. Let's keep going!", mailbox->get_cname());
diff --git a/examples/s4u/platform-failures/s4u-platform-failures.tesh b/examples/s4u/platform-failures/s4u-platform-failures.tesh
index 9d30015e26..b1acb0b80b 100644
--- a/examples/s4u/platform-failures/s4u-platform-failures.tesh
+++ b/examples/s4u/platform-failures/s4u-platform-failures.tesh
@@ -19,9 +19,7 @@ $ $SG_TEST_EXENV ${bindir:=.}/s4u-platform-failures$EXEEXT --log=xbt_cfg.thres:c
 > [  1.000000] (7:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. The communication with 'worker-1' failed. 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] (1:master@Tremblay) Mmh. The communication with 'worker-2' failed. Nevermind. Let's keep going!
-> [  2.000000] (7:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
 > [  2.000000] (1:master@Tremblay) Send a message to worker-3
 > [  2.000000] (8:worker@Jupiter) Waiting a message on worker-1
@@ -126,12 +124,10 @@ $ $SG_TEST_EXENV ${bindir:=.}/s4u-platform-failures$EXEEXT --log=xbt_cfg.thres:c
 > [  1.000000] (7:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. The communication with 'worker-1' failed. 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
 > [  2.000000] (8:worker@Jupiter) Waiting a message on worker-1
 > [  2.000000] (1:master@Tremblay) Mmh. The communication with 'worker-2' failed. Nevermind. Let's keep going!
 > [  2.000000] (1:master@Tremblay) Send a message to worker-3
-> [  2.000000] (7:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.010825] (2:worker@Tremblay) Execution complete.
 > [  2.010825] (2:worker@Tremblay) Waiting a message on worker-0
 > [  3.082474] (5:worker@Ginette) Start execution...
diff --git a/src/kernel/activity/CommImpl.cpp b/src/kernel/activity/CommImpl.cpp
index 5fbd6b33c9..8079463a78 100644
--- a/src/kernel/activity/CommImpl.cpp
+++ b/src/kernel/activity/CommImpl.cpp
@@ -585,8 +585,6 @@ void CommImpl::finish()
 
     if (not simcall->issuer->get_host()->is_on()) {
       simcall->issuer->context_->iwannadie = true;
-      simcall->issuer->exception_ =
-          std::make_exception_ptr(simgrid::HostFailureException(XBT_THROW_POINT, "Host failed"));
     } else {
       switch (state_) {
 
diff --git a/src/kernel/actor/ActorImpl.cpp b/src/kernel/actor/ActorImpl.cpp
index 4569badaab..8371aaeae5 100644
--- a/src/kernel/actor/ActorImpl.cpp
+++ b/src/kernel/actor/ActorImpl.cpp
@@ -302,7 +302,6 @@ void ActorImpl::yield()
   XBT_DEBUG("Control returned to me: '%s'", get_cname());
 
   if (context_->iwannadie) {
-
     XBT_DEBUG("Actor %s@%s is dead", get_cname(), host_->get_cname());
     // throw simgrid::kernel::context::ForcefulKillException(); Does not seem to properly kill the actor
     context_->stop();
diff --git a/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh b/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh
index f4857f0225..ef60921ccb 100644
--- a/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh
+++ b/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh
@@ -39,8 +39,6 @@ $ ${bindir}/host_on_off_processes ${platfdir}/small_platform.xml 5 --log=no_loc
 > [Tremblay:test_launcher:(1) 20.000000] [msg_test/INFO]   Turn Jupiter off
 > [Tremblay:test_launcher:(1) 20.000000] [msg_test/INFO] Test 5 seems ok (number of Process: 2, it should be 2)
 > [Tremblay:test_launcher:(1) 20.000000] [msg_test/INFO]   Test done. See you!
-> [Jupiter:commRX:(2) 20.000000] [msg_test/INFO]   Receive message: HOST_FAILURE
-> [Jupiter:commRX:(2) 20.000000] [msg_test/INFO]   RX Done
 > [Tremblay:commTX:(3) 40.000000] [msg_test/INFO]   TX done
 > [40.000000] [msg_test/INFO] Simulation time 40