X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/simgrid.git/blobdiff_plain/d9cc5b0555a2321f2479c5dacbc8ea1854addd59..651c686416a79b08fcec961a4ba3baefe973c4f3:/examples/msg/masterslave/masterslave_failure.tesh diff --git a/examples/msg/masterslave/masterslave_failure.tesh b/examples/msg/masterslave/masterslave_failure.tesh index 38118c5a4a..9d347f60f1 100644 --- a/examples/msg/masterslave/masterslave_failure.tesh +++ b/examples/msg/masterslave/masterslave_failure.tesh @@ -2,114 +2,100 @@ 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) 1.506790] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(5) 1.506790] [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) 22.630969] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(5) 22.630969] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Tremblay:master:(1) 22.828461] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 22.828461] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 22.828461] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 22.828461] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 22.830484] [msg_test/INFO] Send completed -> [Tremblay:master:(1) 22.830484] [msg_test/INFO] All tasks have been dispatched. Let's tell everybody the computation is over. -> [Tremblay:slave:(2) 22.830484] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 22.830484] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 22.830484] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 23.286311] [msg_test/INFO] "Task" done -> [Tremblay:slave:(2) 23.340194] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 23.830484] [msg_test/INFO] Mmh. Can't reach 'Jupiter'! Nevermind. Let's keep going! -> [Fafard:slave:(4) 23.832460] [msg_test/INFO] Received "finalize" -> [Fafard:slave:(4) 23.832460] [msg_test/INFO] I'm done. See you! -> [Tremblay:master:(1) 23.832460] [msg_test/INFO] Mmh. Can't reach 'Ginette'! Nevermind. Let's keep going! -> [Ginette:slave:(5) 23.832460] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Bourassa:slave:(6) 23.859559] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 23.861514] [msg_test/INFO] Received "finalize" -> [Bourassa:slave:(6) 23.861514] [msg_test/INFO] I'm done. See you! -> [Tremblay:master:(1) 23.861529] [msg_test/INFO] Goodbye now! -> [Tremblay:slave:(2) 23.861529] [msg_test/INFO] Received "finalize" -> [Tremblay:slave:(2) 23.861529] [msg_test/INFO] I'm done. See you! -> [23.861529] [simix_kernel/INFO] Oops ! Deadlock or code not perfectly clean. -> [23.861529] [simix_kernel/INFO] 1 processes are still running, waiting for something. -> [23.861529] [simix_kernel/INFO] Legend of the following listing: " on : ." -> [23.861529] [simix_kernel/INFO] slave on Ginette: Blocked on condition 0x806fbf8; Waiting for the following actions: 'sleep'(0x806fba0). -> [23.861529] [simix_kernel/INFO] Return a Warning. -> [23.861529] [msg_test/INFO] Simulation time 23.8615 +! 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] (0:@) Restart processes on host: Fafard +> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! +> [ 2.000000] (0:@) Restart processes on host: Jupiter +> [ 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 +> [ 14.103093] (1:master@Tremblay) Send completed +> [ 14.103093] (6:slave@Jupiter) Received "Task" +> [ 14.103093] (6:slave@Jupiter) Communication time : "1.030928" +> [ 14.103093] (6:slave@Jupiter) Processing "Task" +> [ 15.061856] (5:slave@Bourassa) "Task" done +> [ 15.072165] (2:slave@Tremblay) "Task" done +> [ 16.103093] (6:slave@Jupiter) "Task" done +> [ 24.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 24.103093] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! +> [ 24.103093] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 25.134021] (1:master@Tremblay) Send completed +> [ 25.134021] (5:slave@Bourassa) Received "Task" +> [ 25.134021] (5:slave@Bourassa) Communication time : "1.030928" +> [ 25.134021] (5:slave@Bourassa) Processing "Task" +> [ 25.144330] (1:master@Tremblay) Send completed +> [ 25.144330] (2:slave@Tremblay) Received "Task" +> [ 25.144330] (2:slave@Tremblay) Communication time : "0.010309" +> [ 25.144330] (2:slave@Tremblay) Processing "Task" +> [ 26.175258] (1:master@Tremblay) Send completed +> [ 26.175258] (6:slave@Jupiter) Received "Task" +> [ 26.175258] (6:slave@Jupiter) Communication time : "1.030928" +> [ 26.175258] (6:slave@Jupiter) Processing "Task" +> [ 27.134021] (5:slave@Bourassa) "Task" done +> [ 27.144330] (2:slave@Tremblay) "Task" done +> [ 28.175258] (6:slave@Jupiter) "Task" done +> [ 36.175258] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 37.206186] (1:master@Tremblay) Send completed +> [ 37.206186] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! +> [ 37.206186] (4:slave@Ginette) Received "Task" +> [ 37.206186] (4:slave@Ginette) Communication time : "1.030928" +> [ 37.206186] (4:slave@Ginette) Processing "Task" +> [ 37.206186] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 37.216495] (1:master@Tremblay) Send completed +> [ 37.216495] (2:slave@Tremblay) Received "Task" +> [ 37.216495] (2:slave@Tremblay) Communication time : "0.010309" +> [ 37.216495] (2:slave@Tremblay) Processing "Task" +> [ 38.247423] (1:master@Tremblay) Send completed +> [ 38.247423] (6:slave@Jupiter) Received "Task" +> [ 38.247423] (6:slave@Jupiter) Communication time : "1.030928" +> [ 38.247423] (6:slave@Jupiter) Processing "Task" +> [ 39.206186] (4:slave@Ginette) "Task" done +> [ 39.216495] (2:slave@Tremblay) "Task" done +> [ 40.247423] (6:slave@Jupiter) "Task" done +> [ 48.247423] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 49.278351] (1:master@Tremblay) Send completed +> [ 49.278351] (4:slave@Ginette) Received "Task" +> [ 49.278351] (4:slave@Ginette) Communication time : "1.030928" +> [ 49.278351] (4:slave@Ginette) Processing "Task" +> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! +> [ 50.309278] (1:master@Tremblay) Send completed +> [ 50.309278] (5:slave@Bourassa) Received "Task" +> [ 50.309278] (5:slave@Bourassa) Communication time : "1.030928" +> [ 50.309278] (5:slave@Bourassa) Processing "Task" +> [ 50.319588] (1:master@Tremblay) Send completed +> [ 50.319588] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. +> [ 50.319588] (2:slave@Tremblay) Received "Task" +> [ 50.319588] (2:slave@Tremblay) Communication time : "0.010309" +> [ 50.319588] (2:slave@Tremblay) Processing "Task" +> [ 50.319588] (6:slave@Jupiter) Received "finalize" +> [ 50.319588] (6:slave@Jupiter) I'm done. See you! +> [ 51.319588] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 52.309278] (5:slave@Bourassa) "Task" done +> [ 52.319588] (0:@) Simulation time 52.3196 +> [ 52.319588] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [ 52.319588] (1:master@Tremblay) Goodbye now! +> [ 52.319588] (2:slave@Tremblay) "Task" done +> [ 52.319588] (2:slave@Tremblay) Received "finalize" +> [ 52.319588] (2:slave@Tremblay) I'm done. See you! +> [ 52.319588] (5:slave@Bourassa) Received "finalize" +> [ 52.319588] (5:slave@Bourassa) I'm done. See you!