diff options
18 files changed, 1369 insertions, 3 deletions
diff --git a/scripts/README.rst b/scripts/README.rst index 37cf2c0e..a751832e 100644 --- a/scripts/README.rst +++ b/scripts/README.rst @@ -1,4 +1,7 @@ -Soledad Scripts -=============== +Soledad Scripts directory +========================= -The scripts in this directory are meant to be used for development purposes. +This directory contains scripts for different purposes, created in different +times. They are here because at some point they were useful for development +purposes. Please check each sub directory's readme file to know more about what +is inside. diff --git a/scripts/legacy-vs-blobs/README.rst b/scripts/legacy-vs-blobs/README.rst new file mode 100644 index 00000000..3eedb3a4 --- /dev/null +++ b/scripts/legacy-vs-blobs/README.rst @@ -0,0 +1,43 @@ +Ploggin Legacy vs Blobs results +=============================== + +This script produces a bar graph comparing different implementations of the +mail pipeline (legacy, blobs, blobs with session cache, blobs with session +cache and persistent http connections) for different amount/sizes of incoming +data (1 x 10M, 10 x 1M, 100 x 100K, 1000 x 10K). + +Data acquisition +---------------- + +Data was gathered through different runs of the code in +`soledad/tests/benchmarks/test_legacy_vs_blobs.py`. As these tests are skipped +by default, you have to (1) remove the @pytest.mark.skip decorator and (2) +remove the second call to pytest in `tox.ini` that would cause a second run of +the tests for measuring memory. This script only plots time, for now. + +Once you done the above, chdir into `soledad/tests` and do something like this, +for each test group: + + tox -e benchmarks -- -m benchmark_test_legacy_vs_blobs_10_1000k --benchmark-autosave + +Each run of tox as above produces a JSON file in `soledad/tests/.benchmarks` +with stats. Each file has to be copied in a subdirectory of the `data/` +directory of the folder where this script lies. Code has to be adapted for each +extra set of results added to the `data/` directory. + +Currently, we are comparing 4 implementation variations: + + - data/no-cache: contains legacy as baseline and blobs as the current master + implementation of blobs. + - data/cache: adds twisted session cache to blobs connections. + - data/persistent: adds session cache and persistent HTTP connections. + +Plotting +-------- + +Once you have all your data in subdirectories of the `data/` directory and the +script is correctly tuned for your data, running `make` should be enough to +create a virtualenvironment with dependencies and plotting data. + +By default, the script will generate a file called `./legacy-vs-blobs.png` in +the current directory with the plot of the data. diff --git a/scripts/legacy-vs-blobs/data/cache/1000_10k.json b/scripts/legacy-vs-blobs/data/cache/1000_10k.json new file mode 100644 index 00000000..5be17758 --- /dev/null +++ b/scripts/legacy-vs-blobs/data/cache/1000_10k.json @@ -0,0 +1,111 @@ +{ + "datetime": "2017-09-02T04:22:20.074434", + "machine_info": { + "python_implementation": "CPython", + "python_compiler": "GCC 6.3.0 20170118", + "machine": "x86_64", + "cpu": { + "hardware": "unknown", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz", + "vendor_id": "GenuineIntel" + }, + "host": "pajeh", + "system": "Linux", + "processor": "", + "python_implementation_version": "2.7.13", + "release": "4.9.0-3-amd64", + "python_version": "2.7.13", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "node": "pajeh" + }, + "commit_info": { + "author_time": "2017-09-02T00:27:58-03:00", + "time": "2017-09-02T00:39:13-03:00", + "dirty": true, + "project": "soledad", + "id": "2dea7ebc513eaa506704fd7ae68bae94b220eea8", + "branch": "8856" + }, + "benchmarks": [ + { + "name": "test_legacy_1000_10k", + "stats": { + "median": 48.28695607185364, + "rounds": 4, + "ld15iqr": 36.51543307304382, + "iqr_outliers": 0, + "stddev": 10.431966763848191, + "q1": 40.382596015930176, + "min": 36.51543307304382, + "q3": 56.539175629615784, + "total": 193.84354329109192, + "iterations": 1, + "max": 60.75419807434082, + "stddev_outliers": 2, + "mean": 48.46088582277298, + "ops": 0.020635198532216573, + "hd15iqr": 60.75419807434082, + "outliers": "2;0", + "iqr": 16.156579613685608 + }, + "extra_info": { + "cpu_percent": 26.6, + "doc": "" + }, + "params": null, + "param": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_1000_10k", + "group": "test_legacy_vs_blobs_1000_10k", + "options": { + "timer": "time", + "min_rounds": 5, + "warmup": false, + "disable_gc": false, + "min_time": 5e-06, + "max_time": 1.0 + } + }, + { + "name": "test_blobs_1000_10k", + "stats": { + "median": 87.17049705982208, + "rounds": 4, + "ld15iqr": 65.08280301094055, + "iqr_outliers": 0, + "stddev": 19.00300388729206, + "q1": 72.67573952674866, + "min": 65.08280301094055, + "q3": 101.80426609516144, + "total": 348.9600112438202, + "iterations": 1, + "max": 109.53621411323547, + "stddev_outliers": 2, + "mean": 87.24000281095505, + "ops": 0.01146263145092914, + "hd15iqr": 109.53621411323547, + "outliers": "2;0", + "iqr": 29.12852656841278 + }, + "extra_info": { + "cpu_percent": 19.4, + "doc": "" + }, + "params": null, + "param": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_1000_10k", + "group": "test_legacy_vs_blobs_1000_10k", + "options": { + "timer": "time", + "min_rounds": 5, + "warmup": false, + "disable_gc": false, + "min_time": 5e-06, + "max_time": 1.0 + } + } + ], + "version": "3.1.1" +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/cache/100_100k.json b/scripts/legacy-vs-blobs/data/cache/100_100k.json new file mode 100644 index 00000000..17fc598b --- /dev/null +++ b/scripts/legacy-vs-blobs/data/cache/100_100k.json @@ -0,0 +1,111 @@ +{ + "benchmarks": [ + { + "params": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_100_100k", + "extra_info": { + "doc": "", + "cpu_percent": 25.1 + }, + "group": "test_legacy_vs_blobs_100_100k", + "stats": { + "q1": 11.39308750629425, + "rounds": 4, + "q3": 12.677581906318665, + "hd15iqr": 12.946987867355347, + "median": 12.090978026390076, + "stddev_outliers": 2, + "mean": 12.035334706306458, + "iqr_outliers": 0, + "iterations": 1, + "total": 48.14133882522583, + "min": 11.012394905090332, + "outliers": "2;0", + "ops": 0.08308867384269794, + "ld15iqr": 11.012394905090332, + "stddev": 0.833654348956266, + "iqr": 1.284494400024414, + "max": 12.946987867355347 + }, + "name": "test_legacy_100_100k", + "param": null, + "options": { + "min_rounds": 5, + "timer": "time", + "max_time": 1.0, + "min_time": 5e-06, + "warmup": false, + "disable_gc": false + } + }, + { + "params": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_100_100k", + "extra_info": { + "doc": "", + "cpu_percent": 24.9 + }, + "group": "test_legacy_vs_blobs_100_100k", + "stats": { + "q1": 5.015861988067627, + "rounds": 4, + "q3": 6.166973114013672, + "hd15iqr": 6.362173080444336, + "median": 5.64124858379364, + "stddev_outliers": 2, + "mean": 5.591417551040649, + "iqr_outliers": 0, + "iterations": 1, + "total": 22.365670204162598, + "min": 4.7209999561309814, + "outliers": "2;0", + "ops": 0.1788455236747405, + "ld15iqr": 4.7209999561309814, + "stddev": 0.7246033659461454, + "iqr": 1.151111125946045, + "max": 6.362173080444336 + }, + "name": "test_blobs_100_100k", + "param": null, + "options": { + "min_rounds": 5, + "timer": "time", + "max_time": 1.0, + "min_time": 5e-06, + "warmup": false, + "disable_gc": false + } + } + ], + "datetime": "2017-09-02T03:53:29.055256", + "version": "3.1.1", + "machine_info": { + "node": "pajeh", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "python_version": "2.7.13", + "machine": "x86_64", + "python_implementation": "CPython", + "cpu": { + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz", + "hardware": "unknown", + "vendor_id": "GenuineIntel" + }, + "python_implementation_version": "2.7.13", + "system": "Linux", + "host": "pajeh", + "python_compiler": "GCC 6.3.0 20170118", + "release": "4.9.0-3-amd64", + "processor": "" + }, + "commit_info": { + "project": "soledad", + "time": "2017-09-02T00:39:13-03:00", + "author_time": "2017-09-02T00:27:58-03:00", + "branch": "8856", + "id": "2dea7ebc513eaa506704fd7ae68bae94b220eea8", + "dirty": true + } +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/cache/10_1000k.json b/scripts/legacy-vs-blobs/data/cache/10_1000k.json new file mode 100644 index 00000000..1a733f2d --- /dev/null +++ b/scripts/legacy-vs-blobs/data/cache/10_1000k.json @@ -0,0 +1,111 @@ +{ + "benchmarks": [ + { + "params": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_10_1000k", + "extra_info": { + "doc": "", + "cpu_percent": 27.7 + }, + "group": "test_legacy_vs_blobs_10_1000k", + "stats": { + "q1": 8.741152048110962, + "rounds": 4, + "q3": 8.863584876060486, + "median": 8.83247196674347, + "stddev_outliers": 1, + "iqr": 0.12243282794952393, + "mean": 8.802368462085724, + "iqr_outliers": 0, + "iterations": 1, + "total": 35.209473848342896, + "min": 8.67733097076416, + "outliers": "1;0", + "ops": 0.11360578738634734, + "ld15iqr": 8.67733097076416, + "stddev": 0.08786766595777334, + "hd15iqr": 8.867198944091797, + "max": 8.867198944091797 + }, + "name": "test_legacy_10_1000k", + "param": null, + "options": { + "min_rounds": 5, + "timer": "time", + "max_time": 1.0, + "min_time": 5e-06, + "warmup": false, + "disable_gc": false + } + }, + { + "params": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_10_1000k", + "extra_info": { + "doc": "", + "cpu_percent": 37.0 + }, + "group": "test_legacy_vs_blobs_10_1000k", + "stats": { + "q1": 1.8672034740447998, + "rounds": 4, + "q3": 1.9366559982299805, + "median": 1.8831886053085327, + "stddev_outliers": 1, + "iqr": 0.06945252418518066, + "mean": 1.9019297361373901, + "iqr_outliers": 0, + "iterations": 1, + "total": 7.6077189445495605, + "min": 1.8517439365386963, + "outliers": "1;0", + "ops": 0.5257817788952025, + "ld15iqr": 1.8517439365386963, + "stddev": 0.06029736288568101, + "hd15iqr": 1.9895977973937988, + "max": 1.9895977973937988 + }, + "name": "test_blobs_10_1000k", + "param": null, + "options": { + "min_rounds": 5, + "timer": "time", + "max_time": 1.0, + "min_time": 5e-06, + "warmup": false, + "disable_gc": false + } + } + ], + "datetime": "2017-09-02T03:48:24.650044", + "version": "3.1.1", + "machine_info": { + "python_implementation_version": "2.7.13", + "system": "Linux", + "host": "pajeh", + "python_compiler": "GCC 6.3.0 20170118", + "release": "4.9.0-3-amd64", + "python_implementation": "CPython", + "processor": "", + "node": "pajeh", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "python_version": "2.7.13", + "machine": "x86_64", + "cpu": { + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz", + "hardware": "unknown", + "vendor_id": "GenuineIntel" + } + }, + "commit_info": { + "author_time": "2017-09-02T00:27:58-03:00", + "time": "2017-09-02T00:39:13-03:00", + "project": "soledad", + "branch": "8856", + "id": "2dea7ebc513eaa506704fd7ae68bae94b220eea8", + "dirty": true + } +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/cache/1_10000k.json b/scripts/legacy-vs-blobs/data/cache/1_10000k.json new file mode 100644 index 00000000..2d970c6e --- /dev/null +++ b/scripts/legacy-vs-blobs/data/cache/1_10000k.json @@ -0,0 +1,111 @@ +{ + "datetime": "2017-09-02T03:46:17.875002", + "machine_info": { + "processor": "", + "python_implementation_version": "2.7.13", + "python_version": "2.7.13", + "machine": "x86_64", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "python_implementation": "CPython", + "python_compiler": "GCC 6.3.0 20170118", + "cpu": { + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz", + "hardware": "unknown" + }, + "release": "4.9.0-3-amd64", + "system": "Linux", + "host": "pajeh", + "node": "pajeh" + }, + "version": "3.1.1", + "commit_info": { + "time": "2017-09-02T00:39:13-03:00", + "id": "2dea7ebc513eaa506704fd7ae68bae94b220eea8", + "project": "soledad", + "author_time": "2017-09-02T00:27:58-03:00", + "branch": "8856", + "dirty": true + }, + "benchmarks": [ + { + "extra_info": { + "cpu_percent": 25.8, + "doc": "" + }, + "name": "test_legacy_1_10000k", + "params": null, + "options": { + "max_time": 1.0, + "min_rounds": 5, + "min_time": 5e-06, + "warmup": false, + "timer": "time", + "disable_gc": false + }, + "group": "test_legacy_vs_blobs_1_10000k", + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_1_10000k", + "param": null, + "stats": { + "mean": 9.607597470283508, + "ld15iqr": 9.551655054092407, + "iqr_outliers": 0, + "outliers": "1;0", + "q3": 9.663439989089966, + "q1": 9.55175495147705, + "iqr": 0.11168503761291504, + "total": 38.43038988113403, + "rounds": 4, + "median": 9.563774466514587, + "stddev_outliers": 1, + "min": 9.551655054092407, + "hd15iqr": 9.751185894012451, + "ops": 0.10408429402803564, + "stddev": 0.09638854573531173, + "iterations": 1, + "max": 9.751185894012451 + } + }, + { + "extra_info": { + "cpu_percent": 40.2, + "doc": "" + }, + "name": "test_blobs_1_10000k", + "params": null, + "options": { + "max_time": 1.0, + "min_rounds": 5, + "min_time": 5e-06, + "warmup": false, + "timer": "time", + "disable_gc": false + }, + "group": "test_legacy_vs_blobs_1_10000k", + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_1_10000k", + "param": null, + "stats": { + "mean": 2.179791212081909, + "ld15iqr": 2.1572468280792236, + "iqr_outliers": 0, + "outliers": "2;0", + "q3": 2.193374514579773, + "q1": 2.1662079095840454, + "iqr": 0.02716660499572754, + "total": 8.719164848327637, + "rounds": 4, + "median": 2.1782270669937134, + "stddev_outliers": 2, + "min": 2.1572468280792236, + "hd15iqr": 2.2054638862609863, + "ops": 0.45875953369171735, + "stddev": 0.01992429175453132, + "iterations": 1, + "max": 2.2054638862609863 + } + } + ] +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/no-cache/1000_10k.json b/scripts/legacy-vs-blobs/data/no-cache/1000_10k.json new file mode 100644 index 00000000..a585ad3a --- /dev/null +++ b/scripts/legacy-vs-blobs/data/no-cache/1000_10k.json @@ -0,0 +1,111 @@ +{ + "commit_info": { + "dirty": true, + "branch": "8856", + "author_time": "2017-09-01T09:50:11-03:00", + "id": "365d9663cbbd524366b7dfe73ac5cccefeb357c8", + "time": "2017-09-01T09:50:20-03:00", + "project": "soledad" + }, + "machine_info": { + "node": "pajeh", + "processor": "", + "machine": "x86_64", + "system": "Linux", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "python_implementation": "CPython", + "python_implementation_version": "2.7.13", + "host": "pajeh", + "cpu": { + "hardware": "unknown", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz", + "vendor_id": "GenuineIntel" + }, + "release": "4.9.0-3-amd64", + "python_compiler": "GCC 6.3.0 20170118", + "python_version": "2.7.13" + }, + "datetime": "2017-09-01T16:28:31.243069", + "version": "3.1.1", + "benchmarks": [ + { + "stats": { + "ld15iqr": 38.49253582954407, + "outliers": "2;0", + "median": 52.51530361175537, + "iterations": 1, + "q3": 65.07869005203247, + "iqr_outliers": 0, + "rounds": 4, + "ops": 0.018550090252706083, + "total": 215.63237404823303, + "mean": 53.90809351205826, + "max": 72.10923099517822, + "iqr": 22.341193079948425, + "stddev_outliers": 2, + "q1": 42.737496972084045, + "min": 38.49253582954407, + "hd15iqr": 72.10923099517822, + "stddev": 14.537598498896823 + }, + "name": "test_legacy_1000_10k", + "param": null, + "group": "test_legacy_vs_blobs_1000_10k", + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_1000_10k", + "params": null, + "extra_info": { + "doc": "", + "cpu_percent": 26.9 + }, + "options": { + "warmup": false, + "max_time": 1.0, + "min_time": 5e-06, + "min_rounds": 5, + "timer": "time", + "disable_gc": false + } + }, + { + "stats": { + "ld15iqr": 176.17668509483337, + "outliers": "2;0", + "median": 192.90700149536133, + "iterations": 1, + "q3": 206.93408203125, + "iqr_outliers": 0, + "rounds": 4, + "ops": 0.005138941398078599, + "total": 778.3704249858856, + "mean": 194.5926062464714, + "max": 216.3797369003296, + "iqr": 24.68295156955719, + "stddev_outliers": 2, + "q1": 182.2511304616928, + "min": 176.17668509483337, + "hd15iqr": 216.3797369003296, + "stddev": 16.94586147142875 + }, + "name": "test_blobs_1000_10k", + "param": null, + "group": "test_legacy_vs_blobs_1000_10k", + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_1000_10k", + "params": null, + "extra_info": { + "doc": "", + "cpu_percent": 10.9 + }, + "options": { + "warmup": false, + "max_time": 1.0, + "min_time": 5e-06, + "min_rounds": 5, + "timer": "time", + "disable_gc": false + } + } + ] +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/no-cache/100_100k.json b/scripts/legacy-vs-blobs/data/no-cache/100_100k.json new file mode 100644 index 00000000..2cbbe638 --- /dev/null +++ b/scripts/legacy-vs-blobs/data/no-cache/100_100k.json @@ -0,0 +1,111 @@ +{ + "commit_info": { + "time": "2017-09-01T09:50:20-03:00", + "branch": "8856", + "id": "365d9663cbbd524366b7dfe73ac5cccefeb357c8", + "project": "soledad", + "dirty": true, + "author_time": "2017-09-01T09:50:11-03:00" + }, + "version": "3.1.1", + "benchmarks": [ + { + "stats": { + "stddev_outliers": 1, + "ops": 0.08172728164268425, + "stddev": 1.0083003646390902, + "hd15iqr": 13.605333805084229, + "total": 48.943264961242676, + "iqr": 1.4744374752044678, + "iqr_outliers": 0, + "q1": 11.498597502708435, + "q3": 12.973034977912903, + "ld15iqr": 11.303098917007446, + "min": 11.303098917007446, + "iterations": 1, + "max": 13.605333805084229, + "outliers": "1;0", + "rounds": 4, + "median": 12.0174161195755, + "mean": 12.235816240310669 + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_100_100k", + "options": { + "warmup": false, + "min_time": 5e-06, + "max_time": 1.0, + "disable_gc": false, + "min_rounds": 5, + "timer": "time" + }, + "param": null, + "name": "test_legacy_100_100k", + "group": "test_legacy_vs_blobs_100_100k", + "extra_info": { + "doc": "", + "cpu_percent": 25.2 + }, + "params": null + }, + { + "stats": { + "stddev_outliers": 2, + "ops": 0.052999047893223836, + "stddev": 0.6994077398028641, + "hd15iqr": 19.686198949813843, + "total": 75.47305393218994, + "iqr": 1.0998969078063965, + "iqr_outliers": 0, + "q1": 18.318315029144287, + "q3": 19.418211936950684, + "ld15iqr": 18.07945704460144, + "min": 18.07945704460144, + "iterations": 1, + "max": 19.686198949813843, + "outliers": "2;0", + "rounds": 4, + "median": 18.85369896888733, + "mean": 18.868263483047485 + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_100_100k", + "options": { + "warmup": false, + "min_time": 5e-06, + "max_time": 1.0, + "disable_gc": false, + "min_rounds": 5, + "timer": "time" + }, + "param": null, + "name": "test_blobs_100_100k", + "group": "test_legacy_vs_blobs_100_100k", + "extra_info": { + "doc": "", + "cpu_percent": 14.7 + }, + "params": null + } + ], + "datetime": "2017-09-01T15:44:20.745800", + "machine_info": { + "host": "pajeh", + "python_compiler": "GCC 6.3.0 20170118", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "python_implementation": "CPython", + "cpu": { + "hardware": "unknown", + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz" + }, + "node": "pajeh", + "release": "4.9.0-3-amd64", + "processor": "", + "python_implementation_version": "2.7.13", + "python_version": "2.7.13", + "system": "Linux", + "machine": "x86_64" + } +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/no-cache/10_1000k.json b/scripts/legacy-vs-blobs/data/no-cache/10_1000k.json new file mode 100644 index 00000000..778e5c63 --- /dev/null +++ b/scripts/legacy-vs-blobs/data/no-cache/10_1000k.json @@ -0,0 +1,111 @@ +{ + "version": "3.1.1", + "machine_info": { + "python_implementation": "CPython", + "host": "pajeh", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "cpu": { + "hardware": "unknown", + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz" + }, + "release": "4.9.0-3-amd64", + "python_version": "2.7.13", + "machine": "x86_64", + "python_implementation_version": "2.7.13", + "processor": "", + "node": "pajeh", + "system": "Linux", + "python_compiler": "GCC 6.3.0 20170118" + }, + "commit_info": { + "id": "365d9663cbbd524366b7dfe73ac5cccefeb357c8", + "time": "2017-09-01T09:50:20-03:00", + "project": "soledad", + "dirty": true, + "branch": "8856", + "author_time": "2017-09-01T09:50:11-03:00" + }, + "datetime": "2017-09-01T15:37:48.278845", + "benchmarks": [ + { + "param": null, + "extra_info": { + "cpu_percent": 27.9, + "doc": "" + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_10_1000k", + "group": "test_legacy_vs_blobs_10_1000k", + "params": null, + "name": "test_legacy_10_1000k", + "stats": { + "mean": 8.937849223613739, + "min": 8.711518049240112, + "outliers": "2;0", + "total": 35.751396894454956, + "iqr_outliers": 0, + "iterations": 1, + "ops": 0.11188374014612, + "rounds": 4, + "stddev": 0.20914882546041347, + "hd15iqr": 9.213748931884766, + "median": 8.913064956665039, + "stddev_outliers": 2, + "max": 9.213748931884766, + "q1": 8.794075012207031, + "ld15iqr": 8.711518049240112, + "q3": 9.081623435020447, + "iqr": 0.2875484228134155 + }, + "options": { + "disable_gc": false, + "min_time": 5e-06, + "min_rounds": 5, + "timer": "time", + "max_time": 1.0, + "warmup": false + } + }, + { + "param": null, + "extra_info": { + "cpu_percent": 31.7, + "doc": "" + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_10_1000k", + "group": "test_legacy_vs_blobs_10_1000k", + "params": null, + "name": "test_blobs_10_1000k", + "stats": { + "mean": 3.1771076917648315, + "min": 3.077280044555664, + "outliers": "1;0", + "total": 12.708430767059326, + "iqr_outliers": 0, + "iterations": 1, + "ops": 0.3147516851858793, + "rounds": 4, + "stddev": 0.0741566234351459, + "hd15iqr": 3.2503108978271484, + "median": 3.190419912338257, + "stddev_outliers": 1, + "max": 3.2503108978271484, + "q1": 3.1237324476242065, + "ld15iqr": 3.077280044555664, + "q3": 3.2304829359054565, + "iqr": 0.10675048828125 + }, + "options": { + "disable_gc": false, + "min_time": 5e-06, + "min_rounds": 5, + "timer": "time", + "max_time": 1.0, + "warmup": false + } + } + ] +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/no-cache/1_10000k.json b/scripts/legacy-vs-blobs/data/no-cache/1_10000k.json new file mode 100644 index 00000000..0697cd6b --- /dev/null +++ b/scripts/legacy-vs-blobs/data/no-cache/1_10000k.json @@ -0,0 +1,111 @@ +{ + "benchmarks": [ + { + "options": { + "disable_gc": false, + "timer": "time", + "min_rounds": 5, + "min_time": 5e-06, + "max_time": 1.0, + "warmup": false + }, + "params": null, + "extra_info": { + "cpu_percent": 25.8, + "doc": "" + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_legacy_1_10000k", + "group": "test_legacy_vs_blobs_1_10000k", + "name": "test_legacy_1_10000k", + "param": null, + "stats": { + "hd15iqr": 9.522547006607056, + "stddev": 0.04062225700829493, + "ops": 0.10556240321945518, + "iterations": 1, + "min": 9.423872947692871, + "total": 37.89227867126465, + "stddev_outliers": 2, + "max": 9.522547006607056, + "q1": 9.445196866989136, + "mean": 9.473069667816162, + "iqr_outliers": 0, + "rounds": 4, + "iqr": 0.055745601654052734, + "median": 9.47292935848236, + "q3": 9.500942468643188, + "ld15iqr": 9.423872947692871, + "outliers": "2;0" + } + }, + { + "options": { + "disable_gc": false, + "timer": "time", + "min_rounds": 5, + "min_time": 5e-06, + "max_time": 1.0, + "warmup": false + }, + "params": null, + "extra_info": { + "cpu_percent": 33.3, + "doc": "" + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_1_10000k", + "group": "test_legacy_vs_blobs_1_10000k", + "name": "test_blobs_1_10000k", + "param": null, + "stats": { + "hd15iqr": 3.758697032928467, + "stddev": 0.619090853876154, + "ops": 0.3292143381447483, + "iterations": 1, + "min": 2.344238042831421, + "total": 12.150139093399048, + "stddev_outliers": 2, + "max": 3.758697032928467, + "q1": 2.5475854873657227, + "mean": 3.037534773349762, + "iqr_outliers": 0, + "rounds": 4, + "iqr": 0.9798985719680786, + "median": 3.02360200881958, + "q3": 3.5274840593338013, + "ld15iqr": 2.344238042831421, + "outliers": "2;0" + } + } + ], + "version": "3.1.1", + "commit_info": { + "author_time": "2017-09-01T14:16:21-03:00", + "project": "soledad", + "id": "7a5698ad8c1457460d95cbd6dd237fb96e218d43", + "time": "2017-09-01T14:16:26-03:00", + "dirty": true, + "branch": "8856" + }, + "machine_info": { + "host": "pajeh", + "python_version": "2.7.13", + "python_compiler": "GCC 6.3.0 20170118", + "system": "Linux", + "python_implementation": "CPython", + "python_implementation_version": "2.7.13", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "machine": "x86_64", + "release": "4.9.0-3-amd64", + "processor": "", + "node": "pajeh", + "cpu": { + "hardware": "unknown", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz", + "vendor_id": "GenuineIntel" + } + }, + "datetime": "2017-09-01T22:20:37.591520" +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/persistent/1000_10k.json b/scripts/legacy-vs-blobs/data/persistent/1000_10k.json new file mode 100644 index 00000000..909e6f21 --- /dev/null +++ b/scripts/legacy-vs-blobs/data/persistent/1000_10k.json @@ -0,0 +1,73 @@ +{ + "version": "3.1.1", + "machine_info": { + "python_version": "2.7.13", + "processor": "", + "node": "pajeh", + "python_compiler": "GCC 6.3.0 20170118", + "python_implementation_version": "2.7.13", + "python_implementation": "CPython", + "machine": "x86_64", + "system": "Linux", + "host": "pajeh", + "cpu": { + "hardware": "unknown", + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz" + }, + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "release": "4.9.0-3-amd64" + }, + "commit_info": { + "id": "1e132568857e6c2d4fbbbf886d3b7ab2009c3c9e", + "time": "2017-09-02T02:38:57-03:00", + "dirty": true, + "branch": "8856", + "author_time": "2017-09-02T02:38:57-03:00", + "project": "soledad" + }, + "benchmarks": [ + { + "param": null, + "stats": { + "ld15iqr": 50.158271074295044, + "total": 290.0146920681, + "iterations": 1, + "stddev": 19.375312299153435, + "stddev_outliers": 2, + "mean": 72.503673017025, + "q1": 56.99843108654022, + "rounds": 4, + "q3": 88.00891494750977, + "iqr": 31.010483860969543, + "max": 93.9663679599762, + "iqr_outliers": 0, + "hd15iqr": 93.9663679599762, + "median": 72.94502651691437, + "ops": 0.013792404693279255, + "min": 50.158271074295044, + "outliers": "2;0" + }, + "params": null, + "name": "test_blobs_1000_10k", + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_1000_10k", + "group": "test_legacy_vs_blobs_1000_10k", + "options": { + "timer": "time", + "disable_gc": false, + "min_rounds": 5, + "min_time": 5e-06, + "warmup": false, + "max_time": 1.0 + }, + "extra_info": { + "cpu_percent": 17.4, + "doc": "" + } + } + ], + "datetime": "2017-09-02T05:51:50.400601" +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/persistent/100_100k.json b/scripts/legacy-vs-blobs/data/persistent/100_100k.json new file mode 100644 index 00000000..48f0e077 --- /dev/null +++ b/scripts/legacy-vs-blobs/data/persistent/100_100k.json @@ -0,0 +1,73 @@ +{ + "machine_info": { + "host": "pajeh", + "python_compiler": "GCC 6.3.0 20170118", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "python_implementation": "CPython", + "processor": "", + "cpu": { + "hardware": "unknown", + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz" + }, + "node": "pajeh", + "system": "Linux", + "release": "4.9.0-3-amd64", + "python_version": "2.7.13", + "machine": "x86_64", + "python_implementation_version": "2.7.13" + }, + "commit_info": { + "branch": "8856", + "author_time": "2017-09-02T02:38:57-03:00", + "time": "2017-09-02T02:38:57-03:00", + "id": "1e132568857e6c2d4fbbbf886d3b7ab2009c3c9e", + "project": "soledad", + "dirty": true + }, + "version": "3.1.1", + "benchmarks": [ + { + "group": "test_legacy_vs_blobs_100_100k", + "params": null, + "name": "test_blobs_100_100k", + "stats": { + "total": 20.738121271133423, + "stddev_outliers": 2, + "stddev": 0.9161744731162039, + "hd15iqr": 6.378293991088867, + "rounds": 4, + "max": 6.378293991088867, + "median": 5.054657578468323, + "iqr": 1.3696125745773315, + "q3": 5.8693366050720215, + "q1": 4.49972403049469, + "mean": 5.184530317783356, + "ops": 0.1928815029916827, + "iqr_outliers": 0, + "min": 4.25051212310791, + "iterations": 1, + "ld15iqr": 4.25051212310791, + "outliers": "2;0" + }, + "options": { + "timer": "time", + "disable_gc": false, + "warmup": false, + "max_time": 1.0, + "min_rounds": 5, + "min_time": 5e-06 + }, + "param": null, + "extra_info": { + "cpu_percent": 24.7, + "doc": "" + }, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_100_100k" + } + ], + "datetime": "2017-09-02T05:56:28.497384" +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/persistent/10_1000k.json b/scripts/legacy-vs-blobs/data/persistent/10_1000k.json new file mode 100644 index 00000000..529cca8c --- /dev/null +++ b/scripts/legacy-vs-blobs/data/persistent/10_1000k.json @@ -0,0 +1,73 @@ +{ + "machine_info": { + "python_compiler": "GCC 6.3.0 20170118", + "python_implementation_version": "2.7.13", + "node": "pajeh", + "machine": "x86_64", + "host": "pajeh", + "cpu": { + "hardware": "unknown", + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz" + }, + "system": "Linux", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "release": "4.9.0-3-amd64", + "python_version": "2.7.13", + "processor": "", + "python_implementation": "CPython" + }, + "commit_info": { + "id": "1e132568857e6c2d4fbbbf886d3b7ab2009c3c9e", + "time": "2017-09-02T02:38:57-03:00", + "dirty": true, + "branch": "8856", + "author_time": "2017-09-02T02:38:57-03:00", + "project": "soledad" + }, + "version": "3.1.1", + "benchmarks": [ + { + "stats": { + "ops": 0.4919825789326136, + "stddev": 0.1042862860397157, + "mean": 2.032592296600342, + "stddev_outliers": 2, + "q3": 2.112483024597168, + "q1": 1.9527015686035156, + "rounds": 4, + "max": 2.1607320308685303, + "hd15iqr": 2.1607320308685303, + "iqr_outliers": 0, + "ld15iqr": 1.91776704788208, + "iterations": 1, + "median": 2.0259350538253784, + "iqr": 0.15978145599365234, + "total": 8.130369186401367, + "outliers": "2;0", + "min": 1.91776704788208 + }, + "param": null, + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_10_1000k", + "params": null, + "name": "test_blobs_10_1000k", + "group": "test_legacy_vs_blobs_10_1000k", + "options": { + "disable_gc": false, + "min_rounds": 5, + "timer": "time", + "warmup": false, + "min_time": 5e-06, + "max_time": 1.0 + }, + "extra_info": { + "cpu_percent": 36.3, + "doc": "" + } + } + ], + "datetime": "2017-09-02T05:57:48.679847" +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/data/persistent/1_10000k.json b/scripts/legacy-vs-blobs/data/persistent/1_10000k.json new file mode 100644 index 00000000..30d362ea --- /dev/null +++ b/scripts/legacy-vs-blobs/data/persistent/1_10000k.json @@ -0,0 +1,73 @@ +{ + "machine_info": { + "python_compiler": "GCC 6.3.0 20170118", + "host": "pajeh", + "python_build": [ + "default", + "Jan 19 2017 14:48:08" + ], + "cpu": { + "hardware": "unknown", + "vendor_id": "GenuineIntel", + "brand": "Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz" + }, + "node": "pajeh", + "system": "Linux", + "release": "4.9.0-3-amd64", + "python_implementation": "CPython", + "processor": "", + "python_implementation_version": "2.7.13", + "python_version": "2.7.13", + "machine": "x86_64" + }, + "commit_info": { + "branch": "8856", + "author_time": "2017-09-02T02:38:57-03:00", + "dirty": true, + "time": "2017-09-02T02:38:57-03:00", + "id": "1e132568857e6c2d4fbbbf886d3b7ab2009c3c9e", + "project": "soledad" + }, + "version": "3.1.1", + "benchmarks": [ + { + "stats": { + "max": 2.1960339546203613, + "median": 2.1957188844680786, + "stddev_outliers": 1, + "q3": 2.19601047039032, + "iqr_outliers": 0, + "q1": 2.194662928581238, + "ld15iqr": 2.1938750743865967, + "ops": 0.4555109930218146, + "stddev": 0.001009686487541645, + "hd15iqr": 2.1960339546203613, + "rounds": 4, + "iterations": 1, + "total": 8.781346797943115, + "mean": 2.195336699485779, + "iqr": 0.0013475418090820312, + "outliers": "1;0", + "min": 2.1938750743865967 + }, + "options": { + "warmup": false, + "max_time": 1.0, + "timer": "time", + "min_rounds": 5, + "min_time": 5e-06, + "disable_gc": false + }, + "group": "test_legacy_vs_blobs_1_10000k", + "params": null, + "name": "test_blobs_1_10000k", + "fullname": "tests/benchmarks/test_legacy_vs_blobs.py::test_blobs_1_10000k", + "param": null, + "extra_info": { + "cpu_percent": 40.2, + "doc": "" + } + } + ], + "datetime": "2017-09-02T06:00:45.837579" +}
\ No newline at end of file diff --git a/scripts/legacy-vs-blobs/legacy-vs-blobs.png b/scripts/legacy-vs-blobs/legacy-vs-blobs.png Binary files differnew file mode 100644 index 00000000..6de5bab8 --- /dev/null +++ b/scripts/legacy-vs-blobs/legacy-vs-blobs.png diff --git a/scripts/legacy-vs-blobs/legacy-vs-blobs.py b/scripts/legacy-vs-blobs/legacy-vs-blobs.py new file mode 100755 index 00000000..c10ac269 --- /dev/null +++ b/scripts/legacy-vs-blobs/legacy-vs-blobs.py @@ -0,0 +1,124 @@ +#!/usr/bin/env python + +# Plot bars comparing different implementations of mail pipeline. +# +# This script can be improved to account for arbitrary number of data sets, but +# it is not doing it right now. + +import json +import numpy as np +import matplotlib.pyplot as plt + +# make a prettier graph +from mpltools import style +style.use('ggplot') + +OUTPUT_FILENAME = 'legacy-vs-blobs.png' + +# each value below will generate one bar for each for each (amount, size) pair. +# The script expects to find files in ./data/SET/ for each set of +# implementations. +# +# The baseline values will be the legacy results in ./data/no-cache/. + +graphs = [ + '1_10000k', + '10_1000k', + '100_100k', + '1000_10k', +] + + +# the JSON structure returned by the following function is ugly, but the +# original JSONs are even uglier, so this is here just to make the life of the +# script easier. +# +# We want to have something like: +# +# data[variation][graph][implementation] = <stats> +# +# Where: +# +# - variation is one data set under ./data (i.e. no-cache, cache, persistent, +# etc). +# - graph is one of the values in graphs variable above. +# - implementation is either legacy or blobs (we just need legacy for the +# no-cache variation, as that is the one we are using as baseline. + +def get_data(): + folders = ['cache', 'no-cache', 'persistent'] + data = {} + for folder in folders: + data[folder] = {} + for graph in graphs: + with open('data/%s/%s.json' % (folder, graph)) as f: + d = json.loads(f.read()) + benchmarks = d['benchmarks'] + data[folder][graph] = {} + for t in ['blobs', 'legacy']: + result = filter(lambda b: t in b['name'], benchmarks) + if result: + result = result.pop() + data[folder][graph][t] = result['stats'] + return data + + +def plot_data(data): + + N = 4 + + # this is our baseline (i.e. legacy / legacy) + absolutes = (1, 1, 1, 1) + + ind = np.arange(N) # the x locations for the groups + width = 0.20 # the width of the bars + + fig, ax = plt.subplots() + rects1 = ax.bar(ind, absolutes, width) + + # for each graph, calculate the ratios + ratios = {'no-cache': [], 'cache': [], 'persistent': []} + for graph in graphs: + legacy = data['no-cache'][graph]['legacy']['mean'] + + # calculate ratios for no-cache / legacy + ratio = data['no-cache'][graph]['blobs']['mean'] / legacy + ratios['no-cache'].append(ratio) + + # calculate ratios for cache / legacy + ratio = data['cache'][graph]['blobs']['mean'] / legacy + ratios['cache'].append(ratio) + + # calculate ratios for persistent / legacy + ratio = data['persistent'][graph]['blobs']['mean'] / legacy + ratios['persistent'].append(ratio) + + # create the boxes with the ratios + nocache = tuple(ratios['no-cache']) + rects2 = ax.bar(ind + width, nocache, width) + + cache = tuple(ratios['cache']) + rects3 = ax.bar(ind + (2 * width), cache, width) + + persistent = tuple(ratios['persistent']) + rects4 = ax.bar(ind + (3 * width), persistent, width) + + # add some text for labels, title and axes ticks + ax.set_ylabel('Normalized execution time') + ax.set_title('Legacy vs Blobs mail pipeline') + ax.set_xticks(ind + (1.5 * width)) + ax.set_xticklabels(tuple(map(lambda name: name.replace('_', ' '), graphs))) + + ax.legend( + (rects1[0], rects2[0], rects3[0], rects4[0]), + ('legacy', 'blobs', 'blobs + session cache', + 'blobs + session cache + persistent http')) + # ax.grid() + + plt.savefig(OUTPUT_FILENAME) + # plt.show() + + +if __name__ == '__main__': + data = get_data() + plot_data(data) diff --git a/scripts/legacy-vs-blobs/makefile b/scripts/legacy-vs-blobs/makefile new file mode 100644 index 00000000..649e181c --- /dev/null +++ b/scripts/legacy-vs-blobs/makefile @@ -0,0 +1,14 @@ +VIRTUALENV_NAME = plot +VIRTUALENV_ROOT = ~/.virtualenvs/$(VIRTUALENV_NAME) + +all: graph + +env: + if [ ! -d $(VIRTUALENV_ROOT) ]; then \ + mkdir -p $$(dirname $(VIRTUALENV_ROOT)); \ + virtualenv $(VIRTUALENV_ROOT); \ + $(VIRTUALENV_ROOT)/bin/pip install requirements.pip; \ + fi + +graph: env + $(VIRTUALENV_ROOT)/bin/python ./legacy-vs-blobs.py diff --git a/scripts/legacy-vs-blobs/requirements.pip b/scripts/legacy-vs-blobs/requirements.pip new file mode 100644 index 00000000..db5d81e0 --- /dev/null +++ b/scripts/legacy-vs-blobs/requirements.pip @@ -0,0 +1,2 @@ +matplotlib +numpy |
