Changes between Version 27 and Version 28 of Public/User_Guide/Batch_system
- Timestamp:
- Apr 3, 2020, 2:44:51 PM (4 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Public/User_Guide/Batch_system
v27 v28 240 240 241 241 #SBATCH --job-name=imb 242 # #SBATCH --account=cdeep242 #SBATCH --account=deep 243 243 #SBATCH --output=IMB-%j.out 244 244 #SBATCH --error=IMB-%j.err … … 271 271 {{{ 272 272 #!/bin/bash 273 # Script for the CN using InfiniBand 274 275 module load Intel ParaStationMPI pscom 273 # Script for the CM using InfiniBand 274 275 module --force purge 276 module use $OTHERSTAGES 277 module load Stages/Devel-2019a 278 module load Intel 279 module load ParaStationMPI 276 280 277 281 # Execution 278 282 EXEC=$PWD/mpi-benchmarks/IMB-MPI1 279 LD_LIBRARY_PATH=/opt/parastation/lib64:$LD_LIBRARY_PATH PSP_OPENIB_HCA=mlx5_0${EXEC} PingPong283 ${EXEC} PingPong 280 284 }}} 281 285 … … 284 288 # Script for the DAM using Extoll 285 289 286 module load Intel ParaStationMPI pscom extoll 290 module --force purge 291 module use $OTHERSTAGES 292 module load Stages/Devel-2019a 293 module load Intel 294 module load ParaStationMPI 287 295 288 296 # Execution 289 297 EXEC=$PWD/mpi-benchmarks/IMB-MPI1 290 LD_LIBRARY_PATH=/opt/parastation/lib64:/opt/extoll/x86_64/lib:$LD_LIBRARY_PATH PSP_DEBUG=3 PSP_EXTOLL=1 PSP_VELO=1 PSP_RENDEZVOUS_VELO=2048 PSP_OPENIB=0${EXEC} PingPong298 ${EXEC} PingPong 291 299 }}} 292 300 … … 296 304 297 305 **Attention:** some information provided on the JURECA documentation do not apply for the DEEP system. In particular: 298 * as of 09/01/2020, the DEEP system has 1 gateway node. In the next weeks at least one additional gateway node will be installed.306 * as of 31/03/2020, the DEEP system has 2 gateway nodes. 299 307 300 308 * As of 09/01/2020 the gateway nodes are exclusive to the job requesting them. Given the limited number of gateway nodes available on the system, this may change in the future. … … 337 345 }}} 338 346 347 On the Cluster (CM) nodes it's possible to query the consumed energy for a certain job: 348 349 {{{ 350 [kreutz1@deepv kreutz1]$ sacct -o ConsumedEnergy,JobName,JobID,CPUTime,AllocNodes -j 69326 351 ConsumedEnergy JobName JobID CPUTime AllocNodes 352 -------------- ---------- ------------ ---------- ---------- 353 496.70K hpl_MKL_O+ 69326 16:28:48 1 354 0 batch 69326.batch 16:28:48 1 355 496.70K xlinpack_+ 69326.0 08:10:24 1 356 }}} 357 358 This feature will also be for the ESB nodes. 359 339 360 340 361 == FAQ == … … 383 404 [deamicis1@deepv hybridhello]$ sinfo 384 405 PARTITION AVAIL TIMELIMIT NODES STATE NODELIST 385 sdv up 20:00:00 1 6 idle deeper-sdv[01-16]406 sdv up 20:00:00 11 idle deeper-sdv[06-16] 386 407 knl up 20:00:00 1 drain knl01 387 408 knl up 20:00:00 3 idle knl[04-06] … … 390 411 knl272 up 20:00:00 2 idle knl[04,06] 391 412 snc4 up 20:00:00 1 idle knl05 392 dam up 20:00:00 1 down* protodam01 393 dam up 20:00:00 3 idle protodam[02-04] 394 extoll up 20:00:00 16 idle deeper-sdv[01-16] 395 ml-gpu up 20:00:00 1 idle ml-gpu01 396 dp-cn up 20:00:00 1 drain dp-cn49 397 dp-cn up 20:00:00 2 alloc dp-cn[01,50] 398 dp-cn up 20:00:00 47 idle dp-cn[02-48] 399 dp-dam up 20:00:00 1 drain* dp-dam01 400 dp-dam up 20:00:00 1 drain dp-dam02 401 dp-dam up 20:00:00 14 down dp-dam[03-16] 402 dp-sdv-esb up 20:00:00 2 idle dp-sdv-esb[01-02] 403 psgw-cluster up 20:00:00 1 down* nfgw01 404 psgw-booster up 20:00:00 1 down* nfgw02 405 debug up 20:00:00 1 drain* dp-dam01 406 debug up 20:00:00 1 down* protodam01 407 debug up 20:00:00 3 drain dp-cn49,dp-dam02,knl01 408 debug up 20:00:00 14 down dp-dam[03-16] 409 debug up 20:00:00 2 alloc dp-cn[01,50] 410 debug up 20:00:00 69 idle deeper-sdv[01-16],dp-cn[02-48],knl[04-06],protodam[02-04] 413 extoll up 20:00:00 11 idle deeper-sdv[06-16] 414 ml-gpu up 20:00:00 3 idle ml-gpu[01-03] 415 dp-cn up 20:00:00 1 drain dp-cn33 416 dp-cn up 20:00:00 5 resv dp-cn[09-10,25,49-50] 417 dp-cn up 20:00:00 44 idle dp-cn[01-08,11-24,26-32,34-48] 418 dp-dam up 20:00:00 1 drain* dp-dam08 419 dp-dam up 20:00:00 2 drain dp-dam[03,07] 420 dp-dam up 20:00:00 3 resv dp-dam[05,09-10] 421 dp-dam up 20:00:00 2 alloc dp-dam[01,04] 422 dp-dam up 20:00:00 8 idle dp-dam[02,06,11-16] 423 dp-dam-ext up 20:00:00 2 resv dp-dam[09-10] 424 dp-dam-ext up 20:00:00 6 idle dp-dam[11-16] 425 dp-esb up 20:00:00 51 drain* dp-esb[11,26-75] 426 dp-esb up 20:00:00 2 drain dp-esb[08,23] 427 dp-esb up 20:00:00 2 alloc dp-esb[09-10] 428 dp-esb up 20:00:00 20 idle dp-esb[01-07,12-22,24-25] 429 dp-sdv-esb up 20:00:00 2 resv dp-sdv-esb[01-02] 430 psgw-cluster up 20:00:00 1 idle nfgw01 431 psgw-booster up 20:00:00 1 idle nfgw02 432 debug up 20:00:00 1 drain* dp-dam08 433 debug up 20:00:00 4 drain dp-cn33,dp-dam[03,07],knl01 434 debug up 20:00:00 10 resv dp-cn[09-10,25,49-50],dp-dam[05,09-10],dp-sdv-esb[01-02] 435 debug up 20:00:00 2 alloc dp-dam[01,04] 436 debug up 20:00:00 69 idle deeper-sdv[06-16],dp-cn[01-08,11-24,26-32,34-48],dp-dam[02,06,11-16],knl[04-06],ml-gpu[01-03] 411 437 }}} 412 438