X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/simgrid.git/blobdiff_plain/b3b06f46c40d606b77e60a172ba3142a15b24431..d975d091cf9e3d8c1fac962248dd73b609de9947:/examples/msg/masterslave/masterslave_failure.tesh diff --git a/examples/msg/masterslave/masterslave_failure.tesh b/examples/msg/masterslave/masterslave_failure.tesh index e2ef81184a..f07ef5d77f 100644 --- a/examples/msg/masterslave/masterslave_failure.tesh +++ b/examples/msg/masterslave/masterslave_failure.tesh @@ -2,109 +2,74 @@ p Testing a simple master/slave example application handling failures -$ masterslave/masterslave_failure$EXEEXT small_platform_with_failures.xml masterslave/deployment_masterslave.xml -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Got 5 slave(s) : -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Jupiter -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Fafard -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Ginette -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Bourassa -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Tremblay -> [Tremblay:master:(1) 0.000000] [msg_test/INFO] Got 20 task to process : -> [Tremblay:master:(1) 0.147613] [msg_test/INFO] Send completed -> [Jupiter:slave:(3) 0.147613] [msg_test/INFO] Received "Task" -> [Jupiter:slave:(3) 0.147613] [msg_test/INFO] Communication time : "0.147613" -> [Jupiter:slave:(3) 0.147613] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.347192] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 0.347192] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 0.347192] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 0.347192] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.475692] [msg_test/INFO] Send completed -> [Ginette:slave:(5) 0.475692] [msg_test/INFO] Received "Task" -> [Ginette:slave:(5) 0.475692] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(5) 0.475692] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.673184] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 0.673184] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 0.673184] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 0.673184] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.675207] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 0.675207] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 0.675207] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 0.675207] [msg_test/INFO] Processing "Task" -> [Jupiter:slave:(3) 0.802956] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 0.950569] [msg_test/INFO] Send completed -> [Jupiter:slave:(3) 0.950569] [msg_test/INFO] Received "Task" -> [Jupiter:slave:(3) 0.950569] [msg_test/INFO] Communication time : "0.147613" -> [Jupiter:slave:(3) 0.950569] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 1.002534] [msg_test/INFO] "Task" done -> [Jupiter:slave:(3) 1.100000] [msg_test/INFO] Gloups. The cpu on which I'm running just turned off!. See you! -> [Tremblay:slave:(2) 1.184917] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 1.202113] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 1.202113] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 1.202113] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 1.202113] [msg_test/INFO] Processing "Task" -> [Ginette:slave:(5) 1.506790] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 1.508062] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(5) 1.508062] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Bourassa:slave:(6) 1.704282] [msg_test/INFO] "Task" done -> [Fafard:slave:(4) 1.857455] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 1.901774] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 1.901774] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 1.901774] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 1.901774] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 1.903797] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 1.903797] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 1.903797] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 1.903797] [msg_test/INFO] Processing "Task" -> [Tremblay:slave:(2) 2.413507] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 2.932871] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 11.903797] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 12.103375] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 12.103375] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 12.103375] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 12.103375] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 12.231875] [msg_test/INFO] Send completed -> [Ginette:slave:(5) 12.231875] [msg_test/INFO] Received "Task" -> [Ginette:slave:(5) 12.231875] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(5) 12.231875] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 12.429367] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 12.429367] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 12.429367] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 12.429367] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 12.431390] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 12.431390] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 12.431390] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 12.431390] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 12.758717] [msg_test/INFO] "Task" done -> [Tremblay:slave:(2) 12.941100] [msg_test/INFO] "Task" done -> [Ginette:slave:(5) 13.262973] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 13.460465] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 22.431390] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 22.630969] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 22.630969] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 22.630969] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 22.630969] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 22.632241] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(5) 22.632241] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Tremblay:master:(1) 22.829733] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 22.829733] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 22.829733] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 22.829733] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 22.831756] [msg_test/INFO] Send completed -> [Tremblay:master:(1) 22.831756] [msg_test/INFO] All tasks have been dispatched. Let's tell everybody the computation is over. -> [Tremblay:slave:(2) 22.831756] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 22.831756] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 22.831756] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 23.286311] [msg_test/INFO] "Task" done -> [Tremblay:slave:(2) 23.341466] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 23.831756] [msg_test/INFO] Mmh. Can't reach 'Jupiter'! Nevermind. Let's keep going! -> [Fafard:slave:(4) 23.833732] [msg_test/INFO] Received "finalize" -> [Fafard:slave:(4) 23.833732] [msg_test/INFO] I'm done. See you! -> [Ginette:slave:(5) 23.835004] [msg_test/INFO] Received "finalize" -> [Ginette:slave:(5) 23.835004] [msg_test/INFO] I'm done. See you! -> [Bourassa:slave:(6) 23.860831] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 23.862786] [msg_test/INFO] Received "finalize" -> [Bourassa:slave:(6) 23.862786] [msg_test/INFO] I'm done. See you! -> [Tremblay:master:(1) 23.862801] [msg_test/INFO] Goodbye now! -> [Tremblay:slave:(2) 23.862801] [msg_test/INFO] Received "finalize" -> [Tremblay:slave:(2) 23.862801] [msg_test/INFO] I'm done. See you! -> [23.862801] [msg_test/INFO] Simulation time 23.8628 +! output sort +$ masterslave/masterslave_failure$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/small_platform_with_failures.xml ${srcdir:=.}/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} --cfg=network/crosstraffic:0 "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" +> [ 0.000000] (0:@) 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] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! +> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 12.030928] (1:master@Tremblay) Send completed +> [ 12.030928] (4:slave@Ginette) Received "Task" +> [ 12.030928] (4:slave@Ginette) Communication time : "1.030928" +> [ 12.030928] (4:slave@Ginette) Processing "Task" +> [ 13.061856] (1:master@Tremblay) Send completed +> [ 13.061856] (5:slave@Bourassa) Received "Task" +> [ 13.061856] (5:slave@Bourassa) Communication time : "1.030928" +> [ 13.061856] (5:slave@Bourassa) Processing "Task" +> [ 13.072165] (1:master@Tremblay) Send completed +> [ 13.072165] (2:slave@Tremblay) Received "Task" +> [ 13.072165] (2:slave@Tremblay) Communication time : "0.010309" +> [ 13.072165] (2:slave@Tremblay) Processing "Task" +> [ 14.030928] (4:slave@Ginette) "Task" done +> [ 15.061856] (5:slave@Bourassa) "Task" done +> [ 15.072165] (2:slave@Tremblay) "Task" done +> [ 23.072165] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [ 33.072165] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 34.103093] (1:master@Tremblay) Send completed +> [ 34.103093] (4:slave@Ginette) Received "Task" +> [ 34.103093] (4:slave@Ginette) Communication time : "1.030928" +> [ 34.103093] (4:slave@Ginette) Processing "Task" +> [ 35.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! +> [ 35.000000] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 35.010309] (1:master@Tremblay) Send completed +> [ 35.010309] (2:slave@Tremblay) Received "Task" +> [ 35.010309] (2:slave@Tremblay) Communication time : "0.010309" +> [ 35.010309] (2:slave@Tremblay) Processing "Task" +> [ 36.103093] (4:slave@Ginette) "Task" done +> [ 37.010309] (2:slave@Tremblay) "Task" done +> [ 45.010309] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [ 55.010309] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 65.010309] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [ 66.041237] (1:master@Tremblay) Send completed +> [ 66.041237] (5:slave@Bourassa) Received "Task" +> [ 66.041237] (5:slave@Bourassa) Communication time : "1.030928" +> [ 66.041237] (5:slave@Bourassa) Processing "Task" +> [ 66.051546] (1:master@Tremblay) Send completed +> [ 66.051546] (2:slave@Tremblay) Received "Task" +> [ 66.051546] (2:slave@Tremblay) Communication time : "0.010309" +> [ 66.051546] (2:slave@Tremblay) Processing "Task" +> [ 68.051546] (2:slave@Tremblay) "Task" done +> [ 76.051546] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [ 86.051546] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 96.051546] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [106.051546] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Bourassa'. Nevermind. Let's keep going! +> [106.061856] (1:master@Tremblay) Send completed +> [106.061856] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. +> [106.061856] (2:slave@Tremblay) Received "Task" +> [106.061856] (2:slave@Tremblay) Communication time : "0.010309" +> [106.061856] (2:slave@Tremblay) Processing "Task" +> [107.061856] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [108.061856] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [108.061856] (2:slave@Tremblay) "Task" done +> [109.061856] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [110.061856] (0:@) Simulation time 110.062 +> [110.061856] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Bourassa'. Nevermind. Let's keep going! +> [110.061856] (1:master@Tremblay) Goodbye now! +> [110.061856] (2:slave@Tremblay) Received "finalize" +> [110.061856] (2:slave@Tremblay) I'm done. See you!