Compspec IOR
A compspec (Composition spec) is a specification and model for comparing things. Compspec IOR is a plugin for extraction of IOR metadata from applications, and packaging in compatibility specification artifacts. This means that we also maintain the compatibility schema here. To learn more:
- Compspec: the Python library that discovers and loads this plugin.
- Compatibility: of container images and applications to a host environment.
- Compspec Go: the Go library that retrieves artifacts and makes graphs for image selection and scheduling.
Usage
Install compspec and the plugin here:
pip install compspec
pip install compspec-ior
Then run an extraction with IOR. You can use defaults, or add any parameters to IOR after the plugin name "ior" Here is how to print to the terminal:
compspec extract ior
IOR output
{
"version": "0.0.0",
"kind": "CompatibilitySpec",
"metadata": {
"name": "compat-experiment",
"schemas": {
"io.compspec.ior": "https://raw.githubusercontent.com/compspec/compspec-ior/main/compspec_ior/schema.json"
}
},
"compatibilities": [
{
"name": "io.compspec.ior",
"version": "0.0.0",
"attributes": {
"version": "4.0.0rc1",
"began": "Thu Feb 22 00:36:12 2024",
"machine": "Linux 2b3ee0c4c948",
"finished": "Thu Feb 22 00:36:12 2024",
"command_line": "ior -O summaryFormat=JSON",
"summary.write.operation": "write",
"summary.write.API": "POSIX",
"summary.write.TestID": 0,
"summary.write.ReferenceNumber": 0,
"summary.write.segmentCount": 1,
"summary.write.blockSize": 1048576,
"summary.write.transferSize": 262144,
"summary.write.numTasks": 1,
"summary.write.tasksPerNode": 1,
"summary.write.repetitions": 1,
"summary.write.filePerProc": 0,
"summary.write.reorderTasks": 0,
"summary.write.taskPerNodeOffset": 1,
"summary.write.reorderTasksRandom": 0,
"summary.write.reorderTasksRandomSeed": 0,
"summary.write.bwMaxMIB": 904.92,
"summary.write.bwMinMIB": 904.92,
"summary.write.bwMeanMIB": 904.92,
"summary.write.bwStdMIB": 0.0,
"summary.write.OPsMax": 3619.6798,
"summary.write.OPsMin": 3619.6798,
"summary.write.OPsMean": 3619.6798,
"summary.write.OPsSD": 0.0,
"summary.write.MeanTime": 0.0011,
"summary.write.xsizeMiB": 1.0,
"summary.read.operation": "read",
"summary.read.API": "POSIX",
"summary.read.TestID": 0,
"summary.read.ReferenceNumber": 0,
"summary.read.segmentCount": 1,
"summary.read.blockSize": 1048576,
"summary.read.transferSize": 262144,
"summary.read.numTasks": 1,
"summary.read.tasksPerNode": 1,
"summary.read.repetitions": 1,
"summary.read.filePerProc": 0,
"summary.read.reorderTasks": 0,
"summary.read.taskPerNodeOffset": 1,
"summary.read.reorderTasksRandom": 0,
"summary.read.reorderTasksRandomSeed": 0,
"summary.read.bwMaxMIB": 6615.6215,
"summary.read.bwMinMIB": 6615.6215,
"summary.read.bwMeanMIB": 6615.6215,
"summary.read.bwStdMIB": 0.0,
"summary.read.OPsMax": 26462.4858,
"summary.read.OPsMin": 26462.4858,
"summary.read.OPsMean": 26462.4858,
"summary.read.OPsSD": 0.0,
"summary.read.MeanTime": 0.0002,
"summary.read.xsizeMiB": 1.0,
"test.0.starttime": "Thu Feb 22 00:36:12 2024",
"test.0.capacity": "1.8 TiB",
"test.0.used_capacity": "20.2%",
"test.0.inodes": "116.4 Mi",
"test.0.used_inodes": "5.3%",
"test.0.parameters.testID": 0,
"test.0.parameters.refnum": 0,
"test.0.parameters.api": "POSIX",
"test.0.parameters.platform": "2b3ee0c4c(Linux)",
"test.0.parameters.testFileName": "testFile",
"test.0.parameters.deadlineForStonewall": 0,
"test.0.parameters.stoneWallingWearOut": 0,
"test.0.parameters.maxTimeDuration": 0,
"test.0.parameters.outlierThreshold": 0,
"test.0.parameters.options": "(null)",
"test.0.parameters.dryRun": 0,
"test.0.parameters.nodes": 1,
"test.0.parameters.memoryPerTask": 0,
"test.0.parameters.memoryPerNode": 0,
"test.0.parameters.tasksPerNode": 1,
"test.0.parameters.repetitions": 1,
"test.0.parameters.multiFile": 0,
"test.0.parameters.interTestDelay": 0,
"test.0.parameters.fsync": 0,
"test.0.parameters.fsyncperwrite": 0,
"test.0.parameters.useExistingTestFile": 0,
"test.0.parameters.uniqueDir": 0,
"test.0.parameters.singleXferAttempt": 0,
"test.0.parameters.readFile": 1,
"test.0.parameters.writeFile": 1,
"test.0.parameters.filePerProc": 0,
"test.0.parameters.reorderTasks": 0,
"test.0.parameters.reorderTasksRandom": 0,
"test.0.parameters.reorderTasksRandomSeed": 0,
"test.0.parameters.randomOffset": 0,
"test.0.parameters.checkWrite": 0,
"test.0.parameters.checkRead": 0,
"test.0.parameters.dataPacketType": 0,
"test.0.parameters.keepFile": 0,
"test.0.parameters.keepFileWithError": 0,
"test.0.parameters.warningAsErrors": 0,
"test.0.parameters.verbose": 0,
"test.0.parameters.data packet type": "g",
"test.0.parameters.setTimeStampSignature/incompressibleSeed": 0,
"test.0.parameters.collective": 0,
"test.0.parameters.segmentCount": 1,
"test.0.parameters.transferSize": 262144,
"test.0.parameters.blockSize": 1048576,
"test.0.options.api": "POSIX",
"test.0.options.apiVersion": "",
"test.0.options.test filename": "testFile",
"test.0.options.access": "single-shared-file",
"test.0.options.type": "independent",
"test.0.options.segments": 1,
"test.0.options.ordering in a file": "sequential",
"test.0.options.ordering inter file": "no tasks offsets",
"test.0.options.nodes": 1,
"test.0.options.tasks": 1,
"test.0.options.clients per node": 1,
"test.0.options.repetitions": 1,
"test.0.options.xfersize": "262144 bytes",
"test.0.options.blocksize": "1 MiB",
"test.0.options.aggregate filesize": "1 MiB",
"test.0.results.0.access": "write",
"test.0.results.0.bwMiB": 904.92,
"test.0.results.0.blockKiB": 1024.0,
"test.0.results.0.xferKiB": 256.0,
"test.0.results.0.iops": 3842.6972,
"test.0.results.0.latency": 0.0003,
"test.0.results.0.openTime": 0.0001,
"test.0.results.0.wrRdTime": 0.001,
"test.0.results.0.closeTime": 0.0,
"test.0.results.0.totalTime": 0.0011,
"test.0.results.1.access": "read",
"test.0.results.1.bwMiB": 6615.6215,
"test.0.results.1.blockKiB": 1024.0,
"test.0.results.1.xferKiB": 256.0,
"test.0.results.1.iops": 27962.0267,
"test.0.results.1.latency": 0.0,
"test.0.results.1.openTime": 0.0,
"test.0.results.1.wrRdTime": 0.0001,
"test.0.results.1.closeTime": 0.0,
"test.0.results.1.totalTime": 0.0002
}
}
]
}
And how to save to file
compspec extract --outfile ior-test.json ior
And run the example to see how to use compspec-ior directly in Python to generate the same artifact.
python ./examples/singleton-run.py
Development
If you open the Development container in VSCode, you'll find ior on the path:
$ which ior
/usr/bin/ior
This allows us to easily develop and test the compatibility plugin. You can
TODO
- how to handle adding lists (with indices) to schema?
License
HPCIC DevTools is distributed under the terms of the MIT license. All new contributions must be made under this license.
See LICENSE, COPYRIGHT, and NOTICE for details.
SPDX-License-Identifier: (MIT)
LLNL-CODE- 842614
Metadata
Release files for compspec-ior 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| compspec-ior-0.0.1.tar.gz | 13.5 kB | Without provenance | Details for compspec-ior-0.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| compspec_ior-0.0.1-py3-none-any.whl | Python 3 | none | any | Details for compspec_ior-0.0.1-py3-none-any.whl |
Total release size: 24.6 kB
Release files / compspec-ior-0.0.1.tar.gz
| Download URL | compspec-ior-0.0.1.tar.gz |
|---|---|
| Size | 13.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
02c571a890f3860f1006b3590ced1428bd28f17c26af20a54ba3bccf7303de27
|
|
BLAKE2b-256 checksum How to use checksums |
8cf3685ae1cea1b33de8f20d2a12a20452573574ba8fee1b33fe0669f580a330
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.11.5
|
Release files / compspec_ior-0.0.1-py3-none-any.whl
| Download URL | compspec_ior-0.0.1-py3-none-any.whl |
|---|---|
| Size | 11.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b4412beff3f224113d753a9546f7d2a3faf70b5ea8cdd63c27609e2c575c2cb6
|
|
BLAKE2b-256 checksum How to use checksums |
b9ef523b9c1eaa7801c6e467c7246d8d6ccc19c46cf3848fda8f366199fed5b9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.11.5
|
Security for compspec-ior 0.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.