From a57d5bbf9f18a3ee8887dbc06befd8b9cdd0e5ea Mon Sep 17 00:00:00 2001 From: Frederic Suter Date: Fri, 25 Mar 2016 11:45:47 +0100 Subject: [PATCH] mv failure w/ cpu_ti test to the tesh --- examples/msg/failures/failures.tesh | 101 +++++++++++++++++ .../masterslave_cpu_ti_crosstraffic.tesh | 102 ------------------ 2 files changed, 101 insertions(+), 102 deletions(-) diff --git a/examples/msg/failures/failures.tesh b/examples/msg/failures/failures.tesh index 597e2142a7..30d0a33d5a 100644 --- a/examples/msg/failures/failures.tesh +++ b/examples/msg/failures/failures.tesh @@ -201,3 +201,104 @@ $ $SG_TEST_EXENV ${bindir:=.}/failures$EXEEXT --log=xbt_cfg.thres:critical --log > [ 52.785567] (2:slave@Tremblay) I'm done. See you! > [ 52.785567] (5:slave@Bourassa) Received "finalize" > [ 52.785567] (5:slave@Bourassa) I'm done. See you! + +p Testing a simple master/slave example application handling failures. CPU_TI optimization enabled + +! output sort 19 +$ $SG_TEST_EXENV ${bindir:=.}/failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/small_platform_with_failures.xml ${srcdir:=.}/../msg/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} -cfg=cpu/optim:TI "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" +> [ 0.000000] (0:maestro@) Cannot launch process 'slave' on failed host 'Fafard' +> [ 0.000000] (1:master@Tremblay) Got 5 slave(s) : +> [ 0.000000] (1:master@Tremblay) Jupiter +> [ 0.000000] (1:master@Tremblay) Fafard +> [ 0.000000] (1:master@Tremblay) Ginette +> [ 0.000000] (1:master@Tremblay) Bourassa +> [ 0.000000] (1:master@Tremblay) Tremblay +> [ 0.000000] (1:master@Tremblay) Got 20 task to process : +> [ 1.000000] (0:maestro@) Restart processes on host: Fafard +> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! +> [ 1.000000] (3:slave@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you! +> [ 2.000000] (0:maestro@) Restart processes on host: Jupiter +> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 12.082474] (1:master@Tremblay) Send completed +> [ 12.082474] (4:slave@Ginette) Received "Task" +> [ 12.082474] (4:slave@Ginette) Communication time : "1.082474" +> [ 12.082474] (4:slave@Ginette) Processing "Task" +> [ 13.164948] (1:master@Tremblay) Send completed +> [ 13.164948] (5:slave@Bourassa) Received "Task" +> [ 13.164948] (5:slave@Bourassa) Communication time : "1.082474" +> [ 13.164948] (5:slave@Bourassa) Processing "Task" +> [ 13.175773] (1:master@Tremblay) Send completed +> [ 13.175773] (2:slave@Tremblay) Received "Task" +> [ 13.175773] (2:slave@Tremblay) Communication time : "0.010825" +> [ 13.175773] (2:slave@Tremblay) Processing "Task" +> [ 14.082474] (4:slave@Ginette) "Task" done +> [ 14.258247] (1:master@Tremblay) Send completed +> [ 14.258247] (6:slave@Jupiter) Received "Task" +> [ 14.258247] (6:slave@Jupiter) Communication time : "1.082474" +> [ 14.258247] (6:slave@Jupiter) Processing "Task" +> [ 15.164948] (5:slave@Bourassa) "Task" done +> [ 15.175773] (2:slave@Tremblay) "Task" done +> [ 16.258247] (6:slave@Jupiter) "Task" done +> [ 24.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 24.258247] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! +> [ 24.258247] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 25.340722] (1:master@Tremblay) Send completed +> [ 25.340722] (5:slave@Bourassa) Received "Task" +> [ 25.340722] (5:slave@Bourassa) Communication time : "1.082474" +> [ 25.340722] (5:slave@Bourassa) Processing "Task" +> [ 25.351546] (1:master@Tremblay) Send completed +> [ 25.351546] (2:slave@Tremblay) Received "Task" +> [ 25.351546] (2:slave@Tremblay) Communication time : "0.010825" +> [ 25.351546] (2:slave@Tremblay) Processing "Task" +> [ 26.434021] (1:master@Tremblay) Send completed +> [ 26.434021] (6:slave@Jupiter) Received "Task" +> [ 26.434021] (6:slave@Jupiter) Communication time : "1.082474" +> [ 26.434021] (6:slave@Jupiter) Processing "Task" +> [ 27.340722] (5:slave@Bourassa) "Task" done +> [ 27.351546] (2:slave@Tremblay) "Task" done +> [ 28.434021] (6:slave@Jupiter) "Task" done +> [ 36.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 37.516495] (1:master@Tremblay) Send completed +> [ 37.516495] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! +> [ 37.516495] (4:slave@Ginette) Received "Task" +> [ 37.516495] (4:slave@Ginette) Communication time : "1.082474" +> [ 37.516495] (4:slave@Ginette) Processing "Task" +> [ 37.516495] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 37.527320] (1:master@Tremblay) Send completed +> [ 37.527320] (2:slave@Tremblay) Received "Task" +> [ 37.527320] (2:slave@Tremblay) Communication time : "0.010825" +> [ 37.527320] (2:slave@Tremblay) Processing "Task" +> [ 38.609794] (1:master@Tremblay) Send completed +> [ 38.609794] (6:slave@Jupiter) Received "Task" +> [ 38.609794] (6:slave@Jupiter) Communication time : "1.082474" +> [ 38.609794] (6:slave@Jupiter) Processing "Task" +> [ 39.516495] (4:slave@Ginette) "Task" done +> [ 39.527320] (2:slave@Tremblay) "Task" done +> [ 40.609794] (6:slave@Jupiter) "Task" done +> [ 48.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 49.692268] (1:master@Tremblay) Send completed +> [ 49.692268] (4:slave@Ginette) Received "Task" +> [ 49.692268] (4:slave@Ginette) Communication time : "1.082474" +> [ 49.692268] (4:slave@Ginette) Processing "Task" +> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! +> [ 50.774742] (1:master@Tremblay) Send completed +> [ 50.774742] (5:slave@Bourassa) Received "Task" +> [ 50.774742] (5:slave@Bourassa) Communication time : "1.082474" +> [ 50.774742] (5:slave@Bourassa) Processing "Task" +> [ 50.785567] (1:master@Tremblay) Send completed +> [ 50.785567] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. +> [ 50.785567] (2:slave@Tremblay) Received "Task" +> [ 50.785567] (2:slave@Tremblay) Communication time : "0.010825" +> [ 50.785567] (2:slave@Tremblay) Processing "Task" +> [ 50.785567] (6:slave@Jupiter) Received "finalize" +> [ 50.785567] (6:slave@Jupiter) I'm done. See you! +> [ 51.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 52.774742] (5:slave@Bourassa) "Task" done +> [ 52.785567] (0:maestro@) Simulation time 52.7856 +> [ 52.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [ 52.785567] (1:master@Tremblay) Goodbye now! +> [ 52.785567] (2:slave@Tremblay) "Task" done +> [ 52.785567] (2:slave@Tremblay) Received "finalize" +> [ 52.785567] (2:slave@Tremblay) I'm done. See you! +> [ 52.785567] (5:slave@Bourassa) Received "finalize" +> [ 52.785567] (5:slave@Bourassa) I'm done. See you! diff --git a/examples/msg/masterslave/masterslave_cpu_ti_crosstraffic.tesh b/examples/msg/masterslave/masterslave_cpu_ti_crosstraffic.tesh index 5dbbc77066..b3e8b1d1d5 100644 --- a/examples/msg/masterslave/masterslave_cpu_ti_crosstraffic.tesh +++ b/examples/msg/masterslave/masterslave_cpu_ti_crosstraffic.tesh @@ -274,105 +274,3 @@ $ $SG_TEST_EXENV ${bindir:=.}/masterslave_forwarder$EXEEXT ${srcdir:=.}/../platf > [ 45.299152] (2:forwarder@Jackson) I'm done. See you! > [ 45.299152] (9:slave@Stephen) Received "finalize" > [ 45.299152] (9:slave@Stephen) I'm done. See you! - - -p Testing a simple master/slave example application handling failures - -! output sort 19 -$ ${bindir:=.}/masterslave_failure$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/../platforms/small_platform_with_failures.xml masterslave/deployment_masterslave.xml --cfg=path:${srcdir} --cfg=cpu/optim:TI "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" -> [ 0.000000] (0:maestro@) Cannot launch process 'slave' on failed host 'Fafard' -> [ 0.000000] (1:master@Tremblay) Got 5 slave(s) : -> [ 0.000000] (1:master@Tremblay) Jupiter -> [ 0.000000] (1:master@Tremblay) Fafard -> [ 0.000000] (1:master@Tremblay) Ginette -> [ 0.000000] (1:master@Tremblay) Bourassa -> [ 0.000000] (1:master@Tremblay) Tremblay -> [ 0.000000] (1:master@Tremblay) Got 20 task to process : -> [ 1.000000] (0:maestro@) Restart processes on host: Fafard -> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [ 1.000000] (3:slave@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you! -> [ 2.000000] (0:maestro@) Restart processes on host: Jupiter -> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 12.082474] (1:master@Tremblay) Send completed -> [ 12.082474] (4:slave@Ginette) Received "Task" -> [ 12.082474] (4:slave@Ginette) Communication time : "1.082474" -> [ 12.082474] (4:slave@Ginette) Processing "Task" -> [ 13.164948] (1:master@Tremblay) Send completed -> [ 13.164948] (5:slave@Bourassa) Received "Task" -> [ 13.164948] (5:slave@Bourassa) Communication time : "1.082474" -> [ 13.164948] (5:slave@Bourassa) Processing "Task" -> [ 13.175773] (1:master@Tremblay) Send completed -> [ 13.175773] (2:slave@Tremblay) Received "Task" -> [ 13.175773] (2:slave@Tremblay) Communication time : "0.010825" -> [ 13.175773] (2:slave@Tremblay) Processing "Task" -> [ 14.082474] (4:slave@Ginette) "Task" done -> [ 14.258247] (1:master@Tremblay) Send completed -> [ 14.258247] (6:slave@Jupiter) Received "Task" -> [ 14.258247] (6:slave@Jupiter) Communication time : "1.082474" -> [ 14.258247] (6:slave@Jupiter) Processing "Task" -> [ 15.164948] (5:slave@Bourassa) "Task" done -> [ 15.175773] (2:slave@Tremblay) "Task" done -> [ 16.258247] (6:slave@Jupiter) "Task" done -> [ 24.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 24.258247] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [ 24.258247] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! -> [ 25.340722] (1:master@Tremblay) Send completed -> [ 25.340722] (5:slave@Bourassa) Received "Task" -> [ 25.340722] (5:slave@Bourassa) Communication time : "1.082474" -> [ 25.340722] (5:slave@Bourassa) Processing "Task" -> [ 25.351546] (1:master@Tremblay) Send completed -> [ 25.351546] (2:slave@Tremblay) Received "Task" -> [ 25.351546] (2:slave@Tremblay) Communication time : "0.010825" -> [ 25.351546] (2:slave@Tremblay) Processing "Task" -> [ 26.434021] (1:master@Tremblay) Send completed -> [ 26.434021] (6:slave@Jupiter) Received "Task" -> [ 26.434021] (6:slave@Jupiter) Communication time : "1.082474" -> [ 26.434021] (6:slave@Jupiter) Processing "Task" -> [ 27.340722] (5:slave@Bourassa) "Task" done -> [ 27.351546] (2:slave@Tremblay) "Task" done -> [ 28.434021] (6:slave@Jupiter) "Task" done -> [ 36.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 37.516495] (1:master@Tremblay) Send completed -> [ 37.516495] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! -> [ 37.516495] (4:slave@Ginette) Received "Task" -> [ 37.516495] (4:slave@Ginette) Communication time : "1.082474" -> [ 37.516495] (4:slave@Ginette) Processing "Task" -> [ 37.516495] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! -> [ 37.527320] (1:master@Tremblay) Send completed -> [ 37.527320] (2:slave@Tremblay) Received "Task" -> [ 37.527320] (2:slave@Tremblay) Communication time : "0.010825" -> [ 37.527320] (2:slave@Tremblay) Processing "Task" -> [ 38.609794] (1:master@Tremblay) Send completed -> [ 38.609794] (6:slave@Jupiter) Received "Task" -> [ 38.609794] (6:slave@Jupiter) Communication time : "1.082474" -> [ 38.609794] (6:slave@Jupiter) Processing "Task" -> [ 39.516495] (4:slave@Ginette) "Task" done -> [ 39.527320] (2:slave@Tremblay) "Task" done -> [ 40.609794] (6:slave@Jupiter) "Task" done -> [ 48.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 49.692268] (1:master@Tremblay) Send completed -> [ 49.692268] (4:slave@Ginette) Received "Task" -> [ 49.692268] (4:slave@Ginette) Communication time : "1.082474" -> [ 49.692268] (4:slave@Ginette) Processing "Task" -> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! -> [ 50.774742] (1:master@Tremblay) Send completed -> [ 50.774742] (5:slave@Bourassa) Received "Task" -> [ 50.774742] (5:slave@Bourassa) Communication time : "1.082474" -> [ 50.774742] (5:slave@Bourassa) Processing "Task" -> [ 50.785567] (1:master@Tremblay) Send completed -> [ 50.785567] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. -> [ 50.785567] (2:slave@Tremblay) Received "Task" -> [ 50.785567] (2:slave@Tremblay) Communication time : "0.010825" -> [ 50.785567] (2:slave@Tremblay) Processing "Task" -> [ 50.785567] (6:slave@Jupiter) Received "finalize" -> [ 50.785567] (6:slave@Jupiter) I'm done. See you! -> [ 51.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 52.774742] (5:slave@Bourassa) "Task" done -> [ 52.785567] (0:maestro@) Simulation time 52.7856 -> [ 52.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! -> [ 52.785567] (1:master@Tremblay) Goodbye now! -> [ 52.785567] (2:slave@Tremblay) "Task" done -> [ 52.785567] (2:slave@Tremblay) Received "finalize" -> [ 52.785567] (2:slave@Tremblay) I'm done. See you! -> [ 52.785567] (5:slave@Bourassa) Received "finalize" -> [ 52.785567] (5:slave@Bourassa) I'm done. See you! -- 2.20.1