Linux command
sh5util 命令
文本
复制后可按需替换文件名、目录或参数。
常用示例
Merge
sh5util -j [job_id]
Example
sh5util -j [job_id.step_id]
Extract
sh5util -j [job_id] -E -i [path/to/file.h5] -s [Energy|Filesystem|Network|Task]
Example
sh5util -j [job_id] -I -s [series] -d [data_item]
List
sh5util -j [job_id] -I -s [series] -L
Example
sh5util -j [job_id] -S
说明
sh5util merges HDF5 profiling files produced by Slurm's acct_gather_profile plugin across compute nodes into a single consolidated file for analysis. It supports three modes: merging node files, extracting data series to CSV, and extracting specific metrics from time series. The tool works with Slurm job profiling data that tracks energy consumption, filesystem I/O, network activity, and task-level metrics. Output files can be analyzed with HDF5 tools or converted to CSV for use with standard data analysis applications.
参数
- -j, --jobs _job.step_
- Merge HDF5 files for the specified job or job step
- -p, --profiledir _dir_
- Directory containing node-step HDF5 files
- -o, --output _path_
- Output file path (default: ./job_$jobid.h5)
- -S, --savefiles
- Keep node-step files after merging
- --user _user_
- User who ran the profiled job
- -E, --extract
- Extract data series to CSV format
- -i, --input _path_
- Input merged HDF5 file for extraction
- -N, --node _nodename_
- Extract data for specific node only
- -l, --level _level_
- Data level: Node:Totals or Node:TimeSeries
- -s, --series _series_
- Data series: Energy, Filesystem, Network, Task, or Task_#
- -I, --item-extract
- Extract single data item from all samples
- -d, --data _item_
- Specific data item name to extract
- -L, --list
- List available data items in a series
- -h, --help
- Display usage information
FAQ
What is the sh5util command used for?
sh5util merges HDF5 profiling files produced by Slurm's acct_gather_profile plugin across compute nodes into a single consolidated file for analysis. It supports three modes: merging node files, extracting data series to CSV, and extracting specific metrics from time series. The tool works with Slurm job profiling data that tracks energy consumption, filesystem I/O, network activity, and task-level metrics. Output files can be analyzed with HDF5 tools or converted to CSV for use with standard data analysis applications.
How do I run a basic sh5util example?
Run `sh5util -j [job_id]` in a terminal, then adjust file names, paths, flags, or remote targets for your system.
What does -j, --jobs _job.step_ do in sh5util?
Merge HDF5 files for the specified job or job step