sparkscope 0.2.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sparkscope-0.2.0/LICENSE +201 -0
- sparkscope-0.2.0/PKG-INFO +161 -0
- sparkscope-0.2.0/README.md +143 -0
- sparkscope-0.2.0/pyproject.toml +37 -0
- sparkscope-0.2.0/setup.cfg +4 -0
- sparkscope-0.2.0/src/sparkscope/__init__.py +0 -0
- sparkscope-0.2.0/src/sparkscope/analyzer.py +20 -0
- sparkscope-0.2.0/src/sparkscope/cli.py +76 -0
- sparkscope-0.2.0/src/sparkscope/findings.py +16 -0
- sparkscope-0.2.0/src/sparkscope/models.py +36 -0
- sparkscope-0.2.0/src/sparkscope/rules/__init__.py +0 -0
- sparkscope-0.2.0/src/sparkscope/rules/aqe.py +24 -0
- sparkscope-0.2.0/src/sparkscope/rules/executor.py +63 -0
- sparkscope-0.2.0/src/sparkscope/rules/joins.py +102 -0
- sparkscope-0.2.0/src/sparkscope/rules/partitions.py +95 -0
- sparkscope-0.2.0/src/sparkscope/workload.py +27 -0
- sparkscope-0.2.0/src/sparkscope/workload_analyzer.py +20 -0
- sparkscope-0.2.0/src/sparkscope.egg-info/PKG-INFO +161 -0
- sparkscope-0.2.0/src/sparkscope.egg-info/SOURCES.txt +25 -0
- sparkscope-0.2.0/src/sparkscope.egg-info/dependency_links.txt +1 -0
- sparkscope-0.2.0/src/sparkscope.egg-info/entry_points.txt +2 -0
- sparkscope-0.2.0/src/sparkscope.egg-info/requires.txt +5 -0
- sparkscope-0.2.0/src/sparkscope.egg-info/top_level.txt +1 -0
- sparkscope-0.2.0/tests/test_analyzer.py +32 -0
- sparkscope-0.2.0/tests/test_cli.py +67 -0
- sparkscope-0.2.0/tests/test_workload.py +36 -0
- sparkscope-0.2.0/tests/test_workload_analyzer.py +134 -0
sparkscope-0.2.0/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
@@ -0,0 +1,161 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: sparkscope
|
|
3
|
+
Version: 0.2.0
|
|
4
|
+
Summary: Open-source PySpark performance analysis toolkit
|
|
5
|
+
Author: Vincent Kanka
|
|
6
|
+
License: Apache-2.0
|
|
7
|
+
Project-URL: Homepage, https://github.com/vincentkanka/sparkscope
|
|
8
|
+
Project-URL: Repository, https://github.com/vincentkanka/sparkscope
|
|
9
|
+
Project-URL: Issues, https://github.com/vincentkanka/sparkscope/issues
|
|
10
|
+
Requires-Python: >=3.11
|
|
11
|
+
Description-Content-Type: text/markdown
|
|
12
|
+
License-File: LICENSE
|
|
13
|
+
Provides-Extra: dev
|
|
14
|
+
Requires-Dist: pytest>=8.0.0; extra == "dev"
|
|
15
|
+
Requires-Dist: build>=1.2.0; extra == "dev"
|
|
16
|
+
Requires-Dist: twine>=5.0.0; extra == "dev"
|
|
17
|
+
Dynamic: license-file
|
|
18
|
+
|
|
19
|
+
# SparkScope
|
|
20
|
+
|
|
21
|
+
SparkScope is an open-source performance analysis toolkit for Apache Spark and PySpark workloads.
|
|
22
|
+
|
|
23
|
+
It helps data engineers detect inefficient Spark configurations, excessive partitioning, expensive joins, missing Adaptive Query Execution settings, and other common performance bottlenecks before they become production incidents.
|
|
24
|
+
|
|
25
|
+
## Why SparkScope?
|
|
26
|
+
|
|
27
|
+
Spark performance problems are often discovered only after pipelines become slow, unstable, or expensive. Engineers then spend significant time reviewing Spark configurations, execution plans, event logs, and application behavior manually.
|
|
28
|
+
|
|
29
|
+
SparkScope aims to make this process more systematic by applying a documented set of performance assessment rules and producing clear, actionable recommendations.
|
|
30
|
+
|
|
31
|
+
## Initial Capabilities
|
|
32
|
+
|
|
33
|
+
SparkScope will analyze Spark configurations and identify issues such as:
|
|
34
|
+
|
|
35
|
+
* Adaptive Query Execution being disabled
|
|
36
|
+
* Excessive or insufficient shuffle partitions
|
|
37
|
+
* Potential broadcast join opportunities
|
|
38
|
+
* Inefficient executor memory and core configurations
|
|
39
|
+
* Missing Kryo serialization
|
|
40
|
+
* Common data-skew risks
|
|
41
|
+
* Potentially expensive shuffle operations
|
|
42
|
+
|
|
43
|
+
## Quick Start
|
|
44
|
+
|
|
45
|
+
Install locally for development:
|
|
46
|
+
|
|
47
|
+
```bash
|
|
48
|
+
python -m pip install -e ".[dev]"
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
Run SparkScope against the sample configuration:
|
|
52
|
+
|
|
53
|
+
```bash
|
|
54
|
+
sparkscope analyze examples/sample_config.json
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
Analyze workload metadata:
|
|
58
|
+
|
|
59
|
+
```bash
|
|
60
|
+
sparkscope analyze-workload examples/sample_workload.json
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
## Example
|
|
64
|
+
|
|
65
|
+
Input:
|
|
66
|
+
|
|
67
|
+
```json
|
|
68
|
+
{
|
|
69
|
+
"spark.sql.adaptive.enabled": "false",
|
|
70
|
+
"spark.sql.shuffle.partitions": "2000",
|
|
71
|
+
"spark.executor.cores": "8",
|
|
72
|
+
"spark.serializer": "org.apache.spark.serializer.JavaSerializer"
|
|
73
|
+
}
|
|
74
|
+
```
|
|
75
|
+
|
|
76
|
+
Expected output:
|
|
77
|
+
|
|
78
|
+
```text
|
|
79
|
+
HIGH: Adaptive Query Execution is disabled.
|
|
80
|
+
Recommendation: Enable spark.sql.adaptive.enabled for supported Spark workloads.
|
|
81
|
+
|
|
82
|
+
MEDIUM: The configured shuffle partition count may be excessive.
|
|
83
|
+
Recommendation: Review partition sizing based on shuffle volume and target partition size.
|
|
84
|
+
|
|
85
|
+
MEDIUM: Java serialization is configured.
|
|
86
|
+
Recommendation: Evaluate KryoSerializer for workloads containing complex objects.
|
|
87
|
+
```
|
|
88
|
+
|
|
89
|
+
## Project Roadmap
|
|
90
|
+
|
|
91
|
+
### Version 0.1.0 — Configuration Analyzer
|
|
92
|
+
|
|
93
|
+
* Analyze Spark configuration files
|
|
94
|
+
* Detect missing or inefficient settings
|
|
95
|
+
* Assign severity levels
|
|
96
|
+
* Produce terminal output
|
|
97
|
+
* Support JSON configuration input
|
|
98
|
+
|
|
99
|
+
### Version 0.2.0 — Join and Partition Analyzer
|
|
100
|
+
|
|
101
|
+
* Detect possible broadcast join opportunities
|
|
102
|
+
* Analyze partition counts
|
|
103
|
+
* Identify potential repartitioning problems
|
|
104
|
+
* Add structured JSON reports
|
|
105
|
+
|
|
106
|
+
### Version 0.3.0 — Spark Event Log Analysis
|
|
107
|
+
|
|
108
|
+
* Parse Spark event logs
|
|
109
|
+
* Identify slow stages
|
|
110
|
+
* Analyze task distribution
|
|
111
|
+
* Detect skew indicators
|
|
112
|
+
* Estimate shuffle overhead
|
|
113
|
+
|
|
114
|
+
### Version 0.4.0 — Reporting
|
|
115
|
+
|
|
116
|
+
* Generate HTML performance reports
|
|
117
|
+
* Rank recommendations by severity
|
|
118
|
+
* Add pipeline health scoring
|
|
119
|
+
* Add historical comparison support
|
|
120
|
+
|
|
121
|
+
### Version 1.0.0 — Complete Performance Assessment Framework
|
|
122
|
+
|
|
123
|
+
* Configuration analysis
|
|
124
|
+
* Event-log analysis
|
|
125
|
+
* Join analysis
|
|
126
|
+
* Partition analysis
|
|
127
|
+
* Performance scoring
|
|
128
|
+
* CLI and Python API
|
|
129
|
+
* Extensible rule engine
|
|
130
|
+
|
|
131
|
+
## Performance Assessment Methodology
|
|
132
|
+
|
|
133
|
+
SparkScope follows a five-stage assessment model:
|
|
134
|
+
|
|
135
|
+
1. Collect workload and configuration metadata
|
|
136
|
+
2. Evaluate configurations against performance rules
|
|
137
|
+
3. Detect likely bottlenecks and risks
|
|
138
|
+
4. Rank findings by severity and expected impact
|
|
139
|
+
5. Generate actionable engineering recommendations
|
|
140
|
+
|
|
141
|
+
The methodology will evolve as the project gains additional rules, workloads, benchmarks, and community feedback.
|
|
142
|
+
|
|
143
|
+
## Installation
|
|
144
|
+
|
|
145
|
+
SparkScope is currently under active development and is not yet available on PyPI.
|
|
146
|
+
|
|
147
|
+
Development installation instructions will be added with the first release.
|
|
148
|
+
|
|
149
|
+
## Contributing
|
|
150
|
+
|
|
151
|
+
Contributions, bug reports, performance rules, test cases, and documentation improvements are welcome.
|
|
152
|
+
|
|
153
|
+
See `CONTRIBUTING.md` for contribution guidelines.
|
|
154
|
+
|
|
155
|
+
## Disclaimer
|
|
156
|
+
|
|
157
|
+
SparkScope recommendations are diagnostic guidance. Spark performance depends on workload characteristics, data distribution, cluster configuration, infrastructure, and execution patterns. Recommendations should be validated through workload testing before production deployment.
|
|
158
|
+
|
|
159
|
+
## License
|
|
160
|
+
|
|
161
|
+
This project is licensed under the Apache License 2.0.
|
|
@@ -0,0 +1,143 @@
|
|
|
1
|
+
# SparkScope
|
|
2
|
+
|
|
3
|
+
SparkScope is an open-source performance analysis toolkit for Apache Spark and PySpark workloads.
|
|
4
|
+
|
|
5
|
+
It helps data engineers detect inefficient Spark configurations, excessive partitioning, expensive joins, missing Adaptive Query Execution settings, and other common performance bottlenecks before they become production incidents.
|
|
6
|
+
|
|
7
|
+
## Why SparkScope?
|
|
8
|
+
|
|
9
|
+
Spark performance problems are often discovered only after pipelines become slow, unstable, or expensive. Engineers then spend significant time reviewing Spark configurations, execution plans, event logs, and application behavior manually.
|
|
10
|
+
|
|
11
|
+
SparkScope aims to make this process more systematic by applying a documented set of performance assessment rules and producing clear, actionable recommendations.
|
|
12
|
+
|
|
13
|
+
## Initial Capabilities
|
|
14
|
+
|
|
15
|
+
SparkScope will analyze Spark configurations and identify issues such as:
|
|
16
|
+
|
|
17
|
+
* Adaptive Query Execution being disabled
|
|
18
|
+
* Excessive or insufficient shuffle partitions
|
|
19
|
+
* Potential broadcast join opportunities
|
|
20
|
+
* Inefficient executor memory and core configurations
|
|
21
|
+
* Missing Kryo serialization
|
|
22
|
+
* Common data-skew risks
|
|
23
|
+
* Potentially expensive shuffle operations
|
|
24
|
+
|
|
25
|
+
## Quick Start
|
|
26
|
+
|
|
27
|
+
Install locally for development:
|
|
28
|
+
|
|
29
|
+
```bash
|
|
30
|
+
python -m pip install -e ".[dev]"
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
Run SparkScope against the sample configuration:
|
|
34
|
+
|
|
35
|
+
```bash
|
|
36
|
+
sparkscope analyze examples/sample_config.json
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
Analyze workload metadata:
|
|
40
|
+
|
|
41
|
+
```bash
|
|
42
|
+
sparkscope analyze-workload examples/sample_workload.json
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
## Example
|
|
46
|
+
|
|
47
|
+
Input:
|
|
48
|
+
|
|
49
|
+
```json
|
|
50
|
+
{
|
|
51
|
+
"spark.sql.adaptive.enabled": "false",
|
|
52
|
+
"spark.sql.shuffle.partitions": "2000",
|
|
53
|
+
"spark.executor.cores": "8",
|
|
54
|
+
"spark.serializer": "org.apache.spark.serializer.JavaSerializer"
|
|
55
|
+
}
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
Expected output:
|
|
59
|
+
|
|
60
|
+
```text
|
|
61
|
+
HIGH: Adaptive Query Execution is disabled.
|
|
62
|
+
Recommendation: Enable spark.sql.adaptive.enabled for supported Spark workloads.
|
|
63
|
+
|
|
64
|
+
MEDIUM: The configured shuffle partition count may be excessive.
|
|
65
|
+
Recommendation: Review partition sizing based on shuffle volume and target partition size.
|
|
66
|
+
|
|
67
|
+
MEDIUM: Java serialization is configured.
|
|
68
|
+
Recommendation: Evaluate KryoSerializer for workloads containing complex objects.
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
## Project Roadmap
|
|
72
|
+
|
|
73
|
+
### Version 0.1.0 — Configuration Analyzer
|
|
74
|
+
|
|
75
|
+
* Analyze Spark configuration files
|
|
76
|
+
* Detect missing or inefficient settings
|
|
77
|
+
* Assign severity levels
|
|
78
|
+
* Produce terminal output
|
|
79
|
+
* Support JSON configuration input
|
|
80
|
+
|
|
81
|
+
### Version 0.2.0 — Join and Partition Analyzer
|
|
82
|
+
|
|
83
|
+
* Detect possible broadcast join opportunities
|
|
84
|
+
* Analyze partition counts
|
|
85
|
+
* Identify potential repartitioning problems
|
|
86
|
+
* Add structured JSON reports
|
|
87
|
+
|
|
88
|
+
### Version 0.3.0 — Spark Event Log Analysis
|
|
89
|
+
|
|
90
|
+
* Parse Spark event logs
|
|
91
|
+
* Identify slow stages
|
|
92
|
+
* Analyze task distribution
|
|
93
|
+
* Detect skew indicators
|
|
94
|
+
* Estimate shuffle overhead
|
|
95
|
+
|
|
96
|
+
### Version 0.4.0 — Reporting
|
|
97
|
+
|
|
98
|
+
* Generate HTML performance reports
|
|
99
|
+
* Rank recommendations by severity
|
|
100
|
+
* Add pipeline health scoring
|
|
101
|
+
* Add historical comparison support
|
|
102
|
+
|
|
103
|
+
### Version 1.0.0 — Complete Performance Assessment Framework
|
|
104
|
+
|
|
105
|
+
* Configuration analysis
|
|
106
|
+
* Event-log analysis
|
|
107
|
+
* Join analysis
|
|
108
|
+
* Partition analysis
|
|
109
|
+
* Performance scoring
|
|
110
|
+
* CLI and Python API
|
|
111
|
+
* Extensible rule engine
|
|
112
|
+
|
|
113
|
+
## Performance Assessment Methodology
|
|
114
|
+
|
|
115
|
+
SparkScope follows a five-stage assessment model:
|
|
116
|
+
|
|
117
|
+
1. Collect workload and configuration metadata
|
|
118
|
+
2. Evaluate configurations against performance rules
|
|
119
|
+
3. Detect likely bottlenecks and risks
|
|
120
|
+
4. Rank findings by severity and expected impact
|
|
121
|
+
5. Generate actionable engineering recommendations
|
|
122
|
+
|
|
123
|
+
The methodology will evolve as the project gains additional rules, workloads, benchmarks, and community feedback.
|
|
124
|
+
|
|
125
|
+
## Installation
|
|
126
|
+
|
|
127
|
+
SparkScope is currently under active development and is not yet available on PyPI.
|
|
128
|
+
|
|
129
|
+
Development installation instructions will be added with the first release.
|
|
130
|
+
|
|
131
|
+
## Contributing
|
|
132
|
+
|
|
133
|
+
Contributions, bug reports, performance rules, test cases, and documentation improvements are welcome.
|
|
134
|
+
|
|
135
|
+
See `CONTRIBUTING.md` for contribution guidelines.
|
|
136
|
+
|
|
137
|
+
## Disclaimer
|
|
138
|
+
|
|
139
|
+
SparkScope recommendations are diagnostic guidance. Spark performance depends on workload characteristics, data distribution, cluster configuration, infrastructure, and execution patterns. Recommendations should be validated through workload testing before production deployment.
|
|
140
|
+
|
|
141
|
+
## License
|
|
142
|
+
|
|
143
|
+
This project is licensed under the Apache License 2.0.
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
[project]
|
|
2
|
+
name = "sparkscope"
|
|
3
|
+
version = "0.2.0"
|
|
4
|
+
description = "Open-source PySpark performance analysis toolkit"
|
|
5
|
+
readme = "README.md"
|
|
6
|
+
requires-python = ">=3.11"
|
|
7
|
+
license = { text = "Apache-2.0" }
|
|
8
|
+
authors = [
|
|
9
|
+
{ name = "Vincent Kanka" }
|
|
10
|
+
]
|
|
11
|
+
dependencies = []
|
|
12
|
+
|
|
13
|
+
[project.optional-dependencies]
|
|
14
|
+
dev = [
|
|
15
|
+
"pytest>=8.0.0",
|
|
16
|
+
"build>=1.2.0",
|
|
17
|
+
"twine>=5.0.0"
|
|
18
|
+
]
|
|
19
|
+
|
|
20
|
+
[project.scripts]
|
|
21
|
+
sparkscope = "sparkscope.cli:main"
|
|
22
|
+
|
|
23
|
+
[build-system]
|
|
24
|
+
requires = ["setuptools>=68"]
|
|
25
|
+
build-backend = "setuptools.build_meta"
|
|
26
|
+
|
|
27
|
+
[tool.setuptools.packages.find]
|
|
28
|
+
where = ["src"]
|
|
29
|
+
|
|
30
|
+
[tool.pytest.ini_options]
|
|
31
|
+
pythonpath = ["src"]
|
|
32
|
+
testpaths = ["tests"]
|
|
33
|
+
|
|
34
|
+
[project.urls]
|
|
35
|
+
Homepage = "https://github.com/vincentkanka/sparkscope"
|
|
36
|
+
Repository = "https://github.com/vincentkanka/sparkscope"
|
|
37
|
+
Issues = "https://github.com/vincentkanka/sparkscope/issues"
|
|
File without changes
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
from sparkscope.models import Finding
|
|
2
|
+
from sparkscope.rules.aqe import check_aqe_enabled
|
|
3
|
+
from sparkscope.rules.executor import check_executor_cores, check_serializer
|
|
4
|
+
from sparkscope.rules.partitions import check_shuffle_partitions
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
def analyze_config(config: dict[str, str]) -> list[Finding]:
|
|
8
|
+
findings: list[Finding] = []
|
|
9
|
+
|
|
10
|
+
checks = [
|
|
11
|
+
check_aqe_enabled,
|
|
12
|
+
check_shuffle_partitions,
|
|
13
|
+
check_executor_cores,
|
|
14
|
+
check_serializer,
|
|
15
|
+
]
|
|
16
|
+
|
|
17
|
+
for check in checks:
|
|
18
|
+
findings.extend(check(config))
|
|
19
|
+
|
|
20
|
+
return findings
|
|
@@ -0,0 +1,76 @@
|
|
|
1
|
+
import json
|
|
2
|
+
from pathlib import Path
|
|
3
|
+
from typing import Any
|
|
4
|
+
|
|
5
|
+
from sparkscope.analyzer import analyze_config
|
|
6
|
+
from sparkscope.findings import print_findings
|
|
7
|
+
from sparkscope.workload import parse_workload_metadata
|
|
8
|
+
from sparkscope.workload_analyzer import analyze_workload
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def load_json_file(file_path: str) -> dict[str, Any]:
|
|
12
|
+
path = Path(file_path)
|
|
13
|
+
|
|
14
|
+
if not path.exists():
|
|
15
|
+
raise FileNotFoundError(f"File not found: {file_path}")
|
|
16
|
+
|
|
17
|
+
with path.open("r", encoding="utf-8") as file:
|
|
18
|
+
data = json.load(file)
|
|
19
|
+
|
|
20
|
+
if not isinstance(data, dict):
|
|
21
|
+
raise ValueError("Input file must contain a JSON object.")
|
|
22
|
+
|
|
23
|
+
return data
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
def analyze(config_path: str) -> None:
|
|
27
|
+
config = load_json_file(config_path)
|
|
28
|
+
findings = analyze_config(config)
|
|
29
|
+
print_findings(findings, "SparkScope Configuration Analysis Report")
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
def analyze_workload_file(workload_path: str) -> None:
|
|
33
|
+
data = load_json_file(workload_path)
|
|
34
|
+
workload = parse_workload_metadata(data)
|
|
35
|
+
findings = analyze_workload(workload)
|
|
36
|
+
print_findings(findings, "SparkScope Workload Analysis Report")
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
def main() -> None:
|
|
40
|
+
import argparse
|
|
41
|
+
|
|
42
|
+
parser = argparse.ArgumentParser(
|
|
43
|
+
prog="sparkscope",
|
|
44
|
+
description="Analyze Spark and PySpark workload configurations.",
|
|
45
|
+
)
|
|
46
|
+
|
|
47
|
+
subparsers = parser.add_subparsers(dest="command", required=True)
|
|
48
|
+
|
|
49
|
+
analyze_parser = subparsers.add_parser(
|
|
50
|
+
"analyze",
|
|
51
|
+
help="Analyze a Spark configuration JSON file.",
|
|
52
|
+
)
|
|
53
|
+
analyze_parser.add_argument(
|
|
54
|
+
"config_path",
|
|
55
|
+
help="Path to Spark configuration JSON file.",
|
|
56
|
+
)
|
|
57
|
+
|
|
58
|
+
workload_parser = subparsers.add_parser(
|
|
59
|
+
"analyze-workload",
|
|
60
|
+
help="Analyze Spark workload metadata JSON file.",
|
|
61
|
+
)
|
|
62
|
+
workload_parser.add_argument(
|
|
63
|
+
"workload_path",
|
|
64
|
+
help="Path to Spark workload metadata JSON file.",
|
|
65
|
+
)
|
|
66
|
+
|
|
67
|
+
args = parser.parse_args()
|
|
68
|
+
|
|
69
|
+
if args.command == "analyze":
|
|
70
|
+
analyze(args.config_path)
|
|
71
|
+
elif args.command == "analyze-workload":
|
|
72
|
+
analyze_workload_file(args.workload_path)
|
|
73
|
+
|
|
74
|
+
|
|
75
|
+
if __name__ == "__main__":
|
|
76
|
+
main()
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
from sparkscope.models import Finding
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
def print_findings(findings: list[Finding], report_title: str) -> None:
|
|
5
|
+
if not findings:
|
|
6
|
+
print("No findings detected.")
|
|
7
|
+
return
|
|
8
|
+
|
|
9
|
+
print(f"\n{report_title}")
|
|
10
|
+
print("=" * len(report_title))
|
|
11
|
+
|
|
12
|
+
for finding in findings:
|
|
13
|
+
print(f"\n[{finding.severity}] {finding.title}")
|
|
14
|
+
print(f"Rule: {finding.rule_id}")
|
|
15
|
+
print(f"Description: {finding.description}")
|
|
16
|
+
print(f"Recommendation: {finding.recommendation}")
|