Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
Dirty hacks again: shot more bullets, it may be a zombie
[simgrid.git] / examples / msg / masterslave / masterslave_failure.tesh
index cefe5c6..edbfc33 100644 (file)
@@ -2,93 +2,94 @@
 
 p Testing a simple master/slave example application handling failures
 
-$ masterslave/masterslave_failure$EXEEXT small_platform_with_failures.xml masterslave/deployment_masterslave.xml
-> [0.000000] simix/smx_process.c:84: [simix_process/WARNING] Cannot launch process 'slave' on failed host 'Fafard'
-> [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"
-> [Jupiter:slave:(3) 0.802956] [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:master:(1) 10.147613] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 10.276113] [msg_test/INFO] Send completed
-> [Ginette:slave:(4) 10.276113] [msg_test/INFO] Received "Task"
-> [Ginette:slave:(4) 10.276113] [msg_test/INFO] Communication time : "0.128500"
-> [Ginette:slave:(4) 10.276113] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 10.473605] [msg_test/INFO] Send completed
-> [Bourassa:slave:(5) 10.473605] [msg_test/INFO] Received "Task"
-> [Bourassa:slave:(5) 10.473605] [msg_test/INFO] Communication time : "0.197492"
-> [Bourassa:slave:(5) 10.473605] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 10.475628] [msg_test/INFO] Send completed
-> [Tremblay:slave:(2) 10.475628] [msg_test/INFO] Received "Task"
-> [Tremblay:slave:(2) 10.475628] [msg_test/INFO] Communication time : "0.002023"
-> [Tremblay:slave:(2) 10.475628] [msg_test/INFO] Processing "Task"
-> [Tremblay:slave:(2) 10.985338] [msg_test/INFO] "Task" done
-> [Ginette:slave:(4) 11.307211] [msg_test/INFO] "Task" done
-> [Bourassa:slave:(5) 11.504703] [msg_test/INFO] "Task" done
-> [Tremblay:master:(1) 20.475628] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 30.475628] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 30.475628] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going!
-> [Ginette:slave:(4) 30.475628] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 30.673120] [msg_test/INFO] Send completed
-> [Bourassa:slave:(5) 30.673120] [msg_test/INFO] Received "Task"
-> [Bourassa:slave:(5) 30.673120] [msg_test/INFO] Communication time : "0.197492"
-> [Bourassa:slave:(5) 30.673120] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 30.675143] [msg_test/INFO] Send completed
-> [Tremblay:slave:(2) 30.675143] [msg_test/INFO] Received "Task"
-> [Tremblay:slave:(2) 30.675143] [msg_test/INFO] Communication time : "0.002023"
-> [Tremblay:slave:(2) 30.675143] [msg_test/INFO] Processing "Task"
-> [Tremblay:slave:(2) 31.184853] [msg_test/INFO] "Task" done
-> [Bourassa:slave:(5) 31.704218] [msg_test/INFO] "Task" done
-> [Tremblay:master:(1) 40.675143] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 50.675143] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 50.803643] [msg_test/INFO] Send completed
-> [Ginette:slave:(4) 50.803643] [msg_test/INFO] Received "Task"
-> [Ginette:slave:(4) 50.803643] [msg_test/INFO] Communication time : "0.128500"
-> [Ginette:slave:(4) 50.803643] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 51.001135] [msg_test/INFO] Send completed
-> [Bourassa:slave:(5) 51.001135] [msg_test/INFO] Received "Task"
-> [Bourassa:slave:(5) 51.001135] [msg_test/INFO] Communication time : "0.197492"
-> [Bourassa:slave:(5) 51.001135] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 51.003158] [msg_test/INFO] Send completed
-> [Tremblay:slave:(2) 51.003158] [msg_test/INFO] Received "Task"
-> [Tremblay:slave:(2) 51.003158] [msg_test/INFO] Communication time : "0.002023"
-> [Tremblay:slave:(2) 51.003158] [msg_test/INFO] Processing "Task"
-> [Tremblay:slave:(2) 51.512868] [msg_test/INFO] "Task" done
-> [Ginette:slave:(4) 51.834741] [msg_test/INFO] "Task" done
-> [Bourassa:slave:(5) 52.032233] [msg_test/INFO] "Task" done
-> [Tremblay:master:(1) 61.003158] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 71.003158] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going!
-> [Tremblay:master:(1) 71.131658] [msg_test/INFO] Send completed
-> [Ginette:slave:(4) 71.131658] [msg_test/INFO] Received "Task"
-> [Ginette:slave:(4) 71.131658] [msg_test/INFO] Communication time : "0.128500"
-> [Ginette:slave:(4) 71.131658] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 71.329150] [msg_test/INFO] Send completed
-> [Bourassa:slave:(5) 71.329150] [msg_test/INFO] Received "Task"
-> [Bourassa:slave:(5) 71.329150] [msg_test/INFO] Communication time : "0.197492"
-> [Bourassa:slave:(5) 71.329150] [msg_test/INFO] Processing "Task"
-> [Tremblay:master:(1) 71.331173] [msg_test/INFO] Send completed
-> [Tremblay:master:(1) 71.331173] [msg_test/INFO] All tasks have been dispatched. Let's tell everybody the computation is over.
-> [Tremblay:slave:(2) 71.331173] [msg_test/INFO] Received "Task"
-> [Tremblay:slave:(2) 71.331173] [msg_test/INFO] Communication time : "0.002023"
-> [Tremblay:slave:(2) 71.331173] [msg_test/INFO] Processing "Task"
-> [Tremblay:slave:(2) 71.840883] [msg_test/INFO] "Task" done
-> [Ginette:slave:(4) 72.162756] [msg_test/INFO] "Task" done
-> [Tremblay:master:(1) 72.331173] [msg_test/INFO] Mmh. Can't reach 'Jupiter'! Nevermind. Let's keep going!
-> [Bourassa:slave:(5) 72.360248] [msg_test/INFO] "Task" done
-> [Tremblay:master:(1) 73.331173] [msg_test/INFO] Mmh. Can't reach 'Fafard'! Nevermind. Let's keep going!
-> [Ginette:slave:(4) 73.332446] [msg_test/INFO] Received "finalize"
-> [Ginette:slave:(4) 73.332446] [msg_test/INFO] I'm done. See you!
-> [Bourassa:slave:(5) 73.334401] [msg_test/INFO] Received "finalize"
-> [Bourassa:slave:(5) 73.334401] [msg_test/INFO] I'm done. See you!
-> [Tremblay:master:(1) 73.334416] [msg_test/INFO] Goodbye now!
-> [Tremblay:slave:(2) 73.334416] [msg_test/INFO] Received "finalize"
-> [Tremblay:slave:(2) 73.334416] [msg_test/INFO] I'm done. See you!
-> [73.334416] [msg_test/INFO] Simulation time 73.3344
+! 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} "--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 :
+> [  0.165962] (1:master@Tremblay) Send completed
+> [  0.165962] (3:slave@Jupiter) Received "Task"
+> [  0.165962] (3:slave@Jupiter) Communication time : "0.165962"
+> [  0.165962] (3:slave@Jupiter) Processing "Task"
+> [  0.821304] (3:slave@Jupiter) "Task" done
+> [  1.100000] (3:slave@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
+> [ 10.165962] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going!
+> [ 10.306421] (1:master@Tremblay) Send completed
+> [ 10.306421] (4:slave@Ginette) Received "Task"
+> [ 10.306421] (4:slave@Ginette) Communication time : "0.140460"
+> [ 10.306421] (4:slave@Ginette) Processing "Task"
+> [ 10.522294] (1:master@Tremblay) Send completed
+> [ 10.522294] (5:slave@Bourassa) Received "Task"
+> [ 10.522294] (5:slave@Bourassa) Communication time : "0.215872"
+> [ 10.522294] (5:slave@Bourassa) Processing "Task"
+> [ 10.524632] (1:master@Tremblay) Send completed
+> [ 10.524632] (2:slave@Tremblay) Received "Task"
+> [ 10.524632] (2:slave@Tremblay) Communication time : "0.002339"
+> [ 10.524632] (2:slave@Tremblay) Processing "Task"
+> [ 11.034342] (2:slave@Tremblay) "Task" done
+> [ 11.337519] (4:slave@Ginette) "Task" done
+> [ 11.553392] (5:slave@Bourassa) "Task" done
+> [ 20.524632] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going!
+> [ 30.524632] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going!
+> [ 30.524632] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going!
+> [ 30.524632] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 30.740505] (1:master@Tremblay) Send completed
+> [ 30.740505] (5:slave@Bourassa) Received "Task"
+> [ 30.740505] (5:slave@Bourassa) Communication time : "0.215872"
+> [ 30.740505] (5:slave@Bourassa) Processing "Task"
+> [ 30.742843] (1:master@Tremblay) Send completed
+> [ 30.742843] (2:slave@Tremblay) Received "Task"
+> [ 30.742843] (2:slave@Tremblay) Communication time : "0.002339"
+> [ 30.742843] (2:slave@Tremblay) Processing "Task"
+> [ 31.252553] (2:slave@Tremblay) "Task" done
+> [ 31.771603] (5:slave@Bourassa) "Task" done
+> [ 40.742843] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going!
+> [ 50.742843] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going!
+> [ 50.883303] (1:master@Tremblay) Send completed
+> [ 50.883303] (4:slave@Ginette) Received "Task"
+> [ 50.883303] (4:slave@Ginette) Communication time : "0.140460"
+> [ 50.883303] (4:slave@Ginette) Processing "Task"
+> [ 51.099175] (1:master@Tremblay) Send completed
+> [ 51.099175] (5:slave@Bourassa) Received "Task"
+> [ 51.099175] (5:slave@Bourassa) Communication time : "0.215872"
+> [ 51.099175] (5:slave@Bourassa) Processing "Task"
+> [ 51.101514] (1:master@Tremblay) Send completed
+> [ 51.101514] (2:slave@Tremblay) Received "Task"
+> [ 51.101514] (2:slave@Tremblay) Communication time : "0.002339"
+> [ 51.101514] (2:slave@Tremblay) Processing "Task"
+> [ 51.611224] (2:slave@Tremblay) "Task" done
+> [ 51.914401] (4:slave@Ginette) "Task" done
+> [ 52.130273] (5:slave@Bourassa) "Task" done
+> [ 61.101514] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going!
+> [ 71.101514] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going!
+> [ 71.241973] (1:master@Tremblay) Send completed
+> [ 71.241973] (4:slave@Ginette) Received "Task"
+> [ 71.241973] (4:slave@Ginette) Communication time : "0.140460"
+> [ 71.241973] (4:slave@Ginette) Processing "Task"
+> [ 71.457846] (1:master@Tremblay) Send completed
+> [ 71.457846] (5:slave@Bourassa) Received "Task"
+> [ 71.457846] (5:slave@Bourassa) Communication time : "0.215872"
+> [ 71.457846] (5:slave@Bourassa) Processing "Task"
+> [ 71.460184] (1:master@Tremblay) Send completed
+> [ 71.460184] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
+> [ 71.460184] (2:slave@Tremblay) Received "Task"
+> [ 71.460184] (2:slave@Tremblay) Communication time : "0.002339"
+> [ 71.460184] (2:slave@Tremblay) Processing "Task"
+> [ 71.969894] (2:slave@Tremblay) "Task" done
+> [ 72.273071] (4:slave@Ginette) "Task" done
+> [ 72.460184] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going!
+> [ 72.488944] (5:slave@Bourassa) "Task" done
+> [ 73.460184] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going!
+> [ 73.473416] (4:slave@Ginette) Received "finalize"
+> [ 73.473416] (4:slave@Ginette) I'm done. See you!
+> [ 73.493752] (5:slave@Bourassa) Received "finalize"
+> [ 73.493752] (5:slave@Bourassa) I'm done. See you!
+> [ 73.493908] (0:@) Simulation time 73.4939
+> [ 73.493908] (1:master@Tremblay) Goodbye now!
+> [ 73.493908] (2:slave@Tremblay) Received "finalize"
+> [ 73.493908] (2:slave@Tremblay) I'm done. See you!