Hp XC System 4.x Software Manual de usuario Pagina 70
- Pagina / 135
- Tabla de contenidos
- MARCADORES
Valorado. / 5. Basado en revisión del cliente
7.2 Running Performance Health Tests
You can run the ovp command to generate reports on the performance health of the nodes. Use
the following format to run a specific performance health test:
ovp [options] [-verify=perf_health/test]
Where:
options Specify additional command line options for the test. The ovp --help
perf_health command lists the command line options for each test.
The following options apply to all the tests:
NOTE: Use the --opts= option to pass this option.
• The --nnodes=n option runs the test on n compute nodes.
• The --nodelist=nodelist option specifies the compute nodes to use.
NOTE: The --nodelist=nodelist option is particularly useful for
determining problematic nodes.
If you use this option and the --nnodes=n option, the --nnodes=n option is
ignored.
• The --queue LSF_queue option specifies the LSF queue for the performance
health tests.
test
Indicates the test to perform. The following tests are available:
cpu
Tests CPU core performance using the Linpack
benchmark.
cpu_usage
Tests CPU core usage. All CPU cores should be
idle during the test. This test reports a node if it
is using more than 10% (by default) of its CPU
cores.
The head node is excluded from this test.
memory
Uses the streams benchmark to test memory
performance.
memory_usage
Tests memory usage. This test reports a node that
uses more than 25 percent (by default) of its
memory.
network_stress
Tests network performance. Check network
performance under stress using the Pallas
benchmark's Alltoall, Allgather, and Allreduce
tests. These tests should be performed on a large
number of nodes for the most accurate results.
The default value for the number of nodes is 4,
which is the minimum value that should be used.
The --all_group option allows you to select
the node grouping size.
network_bidirectional
Tests network performance between pairs of
nodes using the Pallas benchmark's Exchange
test.
network_unidirectional
Tests network performance between pairs of
nodes using the HP MPI ping_pong_ring test.
70 Monitoring Node Activity
- HP XC System Software 1
- XC User Guide 1
- Table of Contents 3
- 4 Table of Contents 4
- Table of Contents 5 5
- 6 Table of Contents 6
- Table of Contents 7 7
- List of Figures 8
- List of Tables 9
- List of Examples 10
- About This Document 11
- Related Information 13
- Linux Web Sites 15
- Manpages 16
- HP Encourages Your Comments 17
- 1.1 System Architecture 19
- 1.1.4 Node Specialization 20
- 1.1.5 Storage and I/O 21
- 1.1.6 File System 21
- File System Layout 22
- 1.3 User Environment 23
- 1.3.3 Commands 24
- 1.4.1 Parallel Applications 24
- 1.5 Run-Time Environment 25
- 1.5.5 HP-MPI 26
- 2 Using the System 29
- 2.2.1 Introduction 30
- 2.2.5 Launching Jobs 31
- 2.2.8 Resuming Suspended Jobs 31
- 32 Using the System 32
- 3.1 Overview of Modules 33
- 3.2 Supplied Modulefiles 34
- 3.6 Loading a Modulefile 36
- 3.7 Unloading a Modulefile 37
- 3.9 Modulefile Conflicts 37
- 3.10 Creating a Modulefile 38
- 4 Developing Applications 39
- 4.2 Compilers 40
- 4.4 Interrupting a Job 41
- 4.5 Setting Debugging Options 41
- 42 Developing Applications 42
- 4.7.1.1 Modulefiles 43
- 4.7.1.2 HP-MPI 43
- 4.7.1.3 OpenMP 43
- 4.7.1.4 Pthreads 43
- 4.7.1.5 Quadrics SHMEM 43
- 44 Developing Applications 44
- $ module load mpi 45
- 4.8 Developing Libraries 46
- 4.8 Developing Libraries 47 47
- 48 Developing Applications 48
- 5 Submitting Jobs 49
- 50 Submitting Jobs 50
- 5.3 Submitting a Parallel Job 51
- 52 Submitting Jobs 52
- 56 Submitting Jobs 56
- 58 Submitting Jobs 58
- 60 Submitting Jobs 60
- -R "type=SLINUX64" 61
- 6 Debugging Applications 63
- 6.2.1.1 SSH and TotalView 64
- 6.2.1.2 Setting Up TotalView 64
- 66 Debugging Applications 66
- 6.2.1.8 Exiting TotalView 67
- 7 Monitoring Node Activity 69
- 70 Monitoring Node Activity 70
- 72 Monitoring Node Activity 72
- 8 Tuning Applications 75
- 76 Tuning Applications 76
- 8.2.1 Installation Kit 77
- Running a Program 78
- 9 Using SLURM 81
- 9.3.1.1 The srun Roles 82
- 9.3.1.2 The srun Modes 82
- 9.7 Job Accounting 84
- 9.8 Fault Tolerance 84
- 9.9 Security 84
- 10 Using LSF 85
- $ squeue --jobs $SLURM_JOBID 86
- 10.4 Job Terminology 89
- 90 Using LSF 90
- 10.6 Submitting Jobs 91
- DescriptionExit Code 92
- Success0 92
- 92 Using LSF 92
- SLURM_JOBID=53 93
- SLURM_NPROCS=4 93
- $ sinfo -p lsf -lNe 96
- 96 Using LSF 96
- $ bjobs 24 98
- 98 Using LSF 98
- 102 Using LSF 102
- $ unset SLURM_JOBID 103
- $ unset SLURM_NPROCS 103
- $ srun --jobid=250 uptime 103
- 11 Advanced Topics 107
- 108 Advanced Topics 108
- 110 Advanced Topics 110
- 11.3.1 Example Procedure 1 111
- 11.3.2 Example Procedure 2 111
- 11.3.3 Example Procedure 3 112
- 11.5.1 Shared File View 113
- 11.5.2 Private File View 113
- % srun -A options 114
- % ./wrapper 114
- % bsub -I options... wrapper 114
- A Examples 115
- Submit the job: 116
- View the job: 116
- 118 Examples 118
- Exit from the shell: 119
- Show the environment: 119
- Display the script: 119
- Run the job: 120
- Show the job allocation: 120
- Show the SLURM job ID: 121
- Exit the pseudo-terminal: 121
- View the interactive jobs: 121
- View the finished jobs: 121
- View the node state: 122
- View the running job: 122
- View the finished job: 123
- Glossary 125
- 126 Glossary 126
- 128 Glossary 128
- 130 Glossary 130
- 132 Index 132
- 134 Index 134
Relacionado con productos y manuales para Software Hp XC System 4.x Software
Software Hp SmartStart-Software Manual de usuario
(51 paginas)
(51 paginas)
Software Hp ProLiant Support Pack Manual de usuario
(32 paginas)
(32 paginas)
Software Hp OneView for VMware vCenter Manual de usuario
(107 paginas)
(107 paginas)
Software Hp Access Control Manual de usuario
(169 paginas)
(169 paginas)
© 2020, manymanuals.es. Todos los derechos reservados | 0.024 s |
Manymanuals.com
Manymanuals.de
Manymanuals.fr
Manymanuals.it
Manymanuals.pl
Manymanuals.cz
Manymanuals.es
Manymanuals-pt.com
Comentarios a estos manuales