-
Notifications
You must be signed in to change notification settings - Fork 9
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
1659: Improve communication statistics in VT #1993
Conversation
Pipelines resultsPR tests (gcc-12, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-3.9, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-5, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-10, ubuntu, openmpi, no LB) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-7, ubuntu, mpich, trace runtime, LB) Build for 317f055 (2022-11-09 20:30:46 UTC)
PR tests (clang-5.0, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-9, ubuntu, mpich, zoltan) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-9, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-6, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-13, alpine, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-11, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (nvidia cuda 11.0, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (intel icpx, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-8, ubuntu, mpich, address sanitizer) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-12, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (nvidia cuda 10.1, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-13, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-14, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (gcc-11, ubuntu, mpich, json schema test) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (clang-10, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
PR tests (intel icpc, ubuntu, mpich) Build for 634004e (2022-11-14 20:53:30 UTC)
|
ee0a4b1
to
7ef11b7
Compare
bd63f4f
to
4d2b25d
Compare
Sample output generated with:
expand JSON{
"type": "LBStatsfile",
"phases": [
{
"id": 0,
"pre-LB": {
"Object_comm": {
"avg": 466.0,
"car": 4.0,
"imb": 0.7682403433476395,
"kur": -2.4373563791593496,
"max": 824.0,
"min": 112.0,
"npr": 4.0,
"skw": 0.00012438128147181126,
"std": 354.01129925469894,
"sum": 1864.0,
"var": 125324.0
},
"Object_load_modeled": {
"avg": 4.64694857068285e-05,
"car": 70.0,
"imb": 8.919304963295684,
"kur": 28.781199587775358,
"max": 0.0004609450002135418,
"min": 0.0,
"npr": 66.0,
"skw": 4.959831982971411,
"std": 6.113038713175178e-05,
"sum": 0.003252863999477995,
"var": 3.736924230877844e-09
},
"Object_load_raw": {
"avg": 4.64694857068285e-05,
"car": 70.0,
"imb": 8.919304963295684,
"kur": 28.781199587775358,
"max": 0.0004609450002135418,
"min": 0.0,
"npr": 66.0,
"skw": 4.959831982971411,
"std": 6.113038713175178e-05,
"sum": 0.003252863999477995,
"var": 3.736924230877844e-09
},
"Rank_comm": {
"avg": 932.0,
"car": 2.0,
"imb": 0.0042918454935623185,
"kur": -2.75,
"max": 936.0,
"min": 928.0,
"npr": 2.0,
"skw": 0.0,
"std": 4.0,
"sum": 1864.0,
"var": 16.0
},
"Rank_load_modeled": {
"avg": 0.0016264319997389975,
"car": 2.0,
"imb": 0.30121517548248056,
"kur": -2.75,
"max": 0.0021163379999507015,
"min": 0.0011365259995272936,
"npr": 2.0,
"skw": 0.0,
"std": 0.0004899060002117039,
"sum": 0.003252863999477995,
"var": 2.400078890434301e-07
},
"Rank_load_raw": {
"avg": 0.0016264319997389975,
"car": 2.0,
"imb": 0.30121517548248056,
"kur": -2.75,
"max": 0.0021163379999507015,
"min": 0.0011365259995272936,
"npr": 2.0,
"skw": 0.0,
"std": 0.0004899060002117039,
"sum": 0.003252863999477995,
"var": 2.400078890434301e-07
}
}
},
{
"id": 1,
"migration count": 8,
"post-LB": {
"Object_comm": {
"avg": 840.0,
"car": 4.0,
"imb": 0.06666666666666665,
"kur": -2.4375,
"max": 896.0,
"min": 784.0,
"npr": 4.0,
"skw": 0.0,
"std": 56.0,
"sum": 3360.0,
"var": 3136.0
},
"Object_load_modeled": {
"avg": 5.6572871423148694e-05,
"car": 70.0,
"imb": 4.605796416967453,
"kur": 17.54840783783443,
"max": 0.00031713599992144736,
"min": 0.0,
"npr": 66.0,
"skw": 3.3960689438183804,
"std": 4.28437352241483e-05,
"sum": 0.003960100999620408,
"var": 1.835585647956926e-09
},
"Object_load_raw": {
"avg": 5.6572871423148694e-05,
"car": 70.0,
"imb": 4.605796416967453,
"kur": 17.54840783783443,
"max": 0.00031713599992144736,
"min": 0.0,
"npr": 66.0,
"skw": 3.3960689438183804,
"std": 4.28437352241483e-05,
"sum": 0.003960100999620408,
"var": 1.835585647956926e-09
},
"Object_work_modeled": {
"avg": 5.6572871423148694e-05,
"car": 70.0,
"imb": 4.605796416967453,
"kur": 17.54840783783442,
"max": 0.00031713599992144736,
"min": 0.0,
"npr": 66.0,
"skw": 3.396068943818379,
"std": 4.284373522414831e-05,
"sum": 0.003960100999620408,
"var": 1.8355856479569265e-09
},
"Rank_comm": {
"avg": 1680.0,
"car": 2.0,
"imb": 0.0,
"kur": 0.0,
"max": 1680.0,
"min": 1680.0,
"npr": 2.0,
"skw": 0.0,
"std": 0.0,
"sum": 3360.0,
"var": 0.0
},
"Rank_load_modeled": {
"avg": 0.001980050499810204,
"car": 2.0,
"imb": 0.0024769568420375254,
"kur": -2.75,
"max": 0.001984954999443289,
"min": 0.0019751460001771193,
"npr": 2.0,
"skw": 0.0,
"std": 4.9044996330849244e-06,
"sum": 0.003960100999620408,
"var": 2.4054116650930158e-11
},
"Rank_load_raw": {
"avg": 0.001980050499810204,
"car": 2.0,
"imb": 0.0024769568420375254,
"kur": -2.75,
"max": 0.001984954999443289,
"min": 0.0019751460001771193,
"npr": 2.0,
"skw": 0.0,
"std": 4.9044996330849244e-06,
"sum": 0.003960100999620408,
"var": 2.4054116650930158e-11
},
"Rank_work_modeled": {
"avg": 0.001980050499810204,
"car": 2.0,
"imb": 0.26022391825216284,
"kur": -2.75,
"max": 0.002495306999207969,
"min": 0.0014647940004124393,
"npr": 2.0,
"skw": 0.0,
"std": 0.0005152564993977649,
"sum": 0.003960100999620408,
"var": 2.6548926017163883e-07
}
},
"pre-LB": {
"Object_comm": {
"avg": 840.0,
"car": 4.0,
"imb": 0.06666666666666665,
"kur": -2.4375,
"max": 896.0,
"min": 784.0,
"npr": 4.0,
"skw": 0.0,
"std": 56.0,
"sum": 3360.0,
"var": 3136.0
},
"Object_load_modeled": {
"avg": 5.6572871423148694e-05,
"car": 70.0,
"imb": 4.605796416967453,
"kur": 17.54840783783442,
"max": 0.00031713599992144736,
"min": 0.0,
"npr": 66.0,
"skw": 3.396068943818379,
"std": 4.284373522414831e-05,
"sum": 0.003960100999620408,
"var": 1.8355856479569265e-09
},
"Object_load_raw": {
"avg": 5.6572871423148694e-05,
"car": 70.0,
"imb": 4.605796416967453,
"kur": 17.54840783783442,
"max": 0.00031713599992144736,
"min": 0.0,
"npr": 66.0,
"skw": 3.396068943818379,
"std": 4.284373522414831e-05,
"sum": 0.003960100999620408,
"var": 1.8355856479569265e-09
},
"Rank_comm": {
"avg": 1680.0,
"car": 2.0,
"imb": 0.0,
"kur": 0.0,
"max": 1680.0,
"min": 1680.0,
"npr": 2.0,
"skw": 0.0,
"std": 0.0,
"sum": 3360.0,
"var": 0.0
},
"Rank_load_modeled": {
"avg": 0.001980050499810204,
"car": 2.0,
"imb": 0.26022391825216284,
"kur": -2.75,
"max": 0.002495306999207969,
"min": 0.0014647940004124393,
"npr": 2.0,
"skw": 0.0,
"std": 0.0005152564993977649,
"sum": 0.003960100999620408,
"var": 2.6548926017163883e-07
},
"Rank_load_raw": {
"avg": 0.001980050499810204,
"car": 2.0,
"imb": 0.26022391825216284,
"kur": -2.75,
"max": 0.002495306999207969,
"min": 0.0014647940004124393,
"npr": 2.0,
"skw": 0.0,
"std": 0.0005152564993977649,
"sum": 0.003960100999620408,
"var": 2.6548926017163883e-07
}
}
},
(...)
{
"id": 9,
"migration count": 0,
"post-LB": {
"Object_comm": {
"avg": 4632.0,
"car": 4.0,
"imb": 0.07081174438687388,
"kur": -2.4375,
"max": 4960.0,
"min": 4304.0,
"npr": 4.0,
"skw": 0.0,
"std": 328.0,
"sum": 18528.0,
"var": 107584.0
},
"Object_load_modeled": {
"avg": 8.89744285359484e-05,
"car": 70.0,
"imb": 17.76672912338164,
"kur": 34.416259845604124,
"max": 0.0016697589992418216,
"min": 0.0,
"npr": 66.0,
"skw": 5.845439578625132,
"std": 0.00022748406793370163,
"sum": 0.006228209997516387,
"var": 5.1749001163664976e-08
},
"Object_load_raw": {
"avg": 8.89744285359484e-05,
"car": 70.0,
"imb": 17.76672912338164,
"kur": 34.416259845604124,
"max": 0.0016697589992418216,
"min": 0.0,
"npr": 66.0,
"skw": 5.845439578625132,
"std": 0.00022748406793370163,
"sum": 0.006228209997516387,
"var": 5.1749001163664976e-08
},
"Object_work_modeled": {
"avg": 8.89744285359484e-05,
"car": 70.0,
"imb": 17.76672912338164,
"kur": 34.416259845604124,
"max": 0.0016697589992418216,
"min": 0.0,
"npr": 66.0,
"skw": 5.845439578625132,
"std": 0.00022748406793370163,
"sum": 0.006228209997516387,
"var": 5.1749001163664976e-08
},
"Rank_comm": {
"avg": 9264.0,
"car": 2.0,
"imb": 0.0,
"kur": 0.0,
"max": 9264.0,
"min": 9264.0,
"npr": 2.0,
"skw": 0.0,
"std": 0.0,
"sum": 18528.0,
"var": 0.0
},
"Rank_load_modeled": {
"avg": 0.0031141049987581937,
"car": 2.0,
"imb": 0.002597214844879403,
"kur": -2.75,
"max": 0.0031221929984894814,
"min": 0.003106016999026906,
"npr": 2.0,
"skw": 0.0,
"std": 8.08799973128771e-06,
"sum": 0.006228209997516387,
"var": 6.541573965331006e-11
},
"Rank_load_raw": {
"avg": 0.0031141049987581937,
"car": 2.0,
"imb": 0.002597214844879403,
"kur": -2.75,
"max": 0.0031221929984894814,
"min": 0.003106016999026906,
"npr": 2.0,
"skw": 0.0,
"std": 8.08799973128771e-06,
"sum": 0.006228209997516387,
"var": 6.541573965331006e-11
},
"Rank_work_modeled": {
"avg": 0.0031141049987581937,
"car": 2.0,
"imb": 0.002597214844879403,
"kur": -2.75,
"max": 0.0031221929984894814,
"min": 0.003106016999026906,
"npr": 2.0,
"skw": 0.0,
"std": 8.08799973128771e-06,
"sum": 0.006228209997516387,
"var": 6.541573965331006e-11
}
},
"pre-LB": {
"Object_comm": {
"avg": 4632.0,
"car": 4.0,
"imb": 0.07081174438687388,
"kur": -2.4375,
"max": 4960.0,
"min": 4304.0,
"npr": 4.0,
"skw": 0.0,
"std": 328.0,
"sum": 18528.0,
"var": 107584.0
},
"Object_load_modeled": {
"avg": 8.89744285359484e-05,
"car": 70.0,
"imb": 17.76672912338164,
"kur": 34.416259845604124,
"max": 0.0016697589992418216,
"min": 0.0,
"npr": 66.0,
"skw": 5.845439578625132,
"std": 0.00022748406793370163,
"sum": 0.006228209997516387,
"var": 5.1749001163664976e-08
},
"Object_load_raw": {
"avg": 8.89744285359484e-05,
"car": 70.0,
"imb": 17.76672912338164,
"kur": 34.416259845604124,
"max": 0.0016697589992418216,
"min": 0.0,
"npr": 66.0,
"skw": 5.845439578625132,
"std": 0.00022748406793370163,
"sum": 0.006228209997516387,
"var": 5.1749001163664976e-08
},
"Object_work_modeled": {
"avg": 8.758099999275665e-05,
"car": 70.0,
"imb": 17.66915196946732,
"kur": 35.73043645952325,
"max": 0.0016350629985026899,
"min": 0.0,
"npr": 66.0,
"skw": 5.931927884228807,
"std": 0.00021919888106694175,
"sum": 0.006130669999492966,
"var": 4.804814946099927e-08
},
"Rank_comm": {
"avg": 9264.0,
"car": 2.0,
"imb": 0.0,
"kur": 0.0,
"max": 9264.0,
"min": 9264.0,
"npr": 2.0,
"skw": 0.0,
"std": 0.0,
"sum": 18528.0,
"var": 0.0
},
"Rank_load_modeled": {
"avg": 0.0031141049987581937,
"car": 2.0,
"imb": 0.002597214844879403,
"kur": -2.75,
"max": 0.0031221929984894814,
"min": 0.003106016999026906,
"npr": 2.0,
"skw": 0.0,
"std": 8.08799973128771e-06,
"sum": 0.006228209997516387,
"var": 6.541573965331006e-11
},
"Rank_load_raw": {
"avg": 0.0031141049987581937,
"car": 2.0,
"imb": 0.002597214844879403,
"kur": -2.75,
"max": 0.0031221929984894814,
"min": 0.003106016999026906,
"npr": 2.0,
"skw": 0.0,
"std": 8.08799973128771e-06,
"sum": 0.006228209997516387,
"var": 6.541573965331006e-11
},
"Rank_work_modeled": {
"avg": 0.003065334999746483,
"car": 2.0,
"imb": 0.07422451348080084,
"kur": -2.75,
"max": 0.003292857998758336,
"min": 0.0028378120007346297,
"npr": 2.0,
"skw": 0.0,
"std": 0.00022752299901185324,
"sum": 0.006130669999492966,
"var": 5.176671507934777e-08
}
}
}
]
} |
041dc16
to
317f055
Compare
Codecov Report
@@ Coverage Diff @@
## develop #1993 +/- ##
===========================================
+ Coverage 84.45% 84.47% +0.01%
===========================================
Files 732 728 -4
Lines 25843 25850 +7
===========================================
+ Hits 21826 21837 +11
+ Misses 4017 4013 -4
|
I'm not a huge fan of this architecture, where strategy-specific stuff bleeds into the manager, but I understand the motivation well enough. Two points about not presenting this as something that application developers should see or their code should call: Instead of 'custom model', could we call it 'strategy specific model'? It would be nice if setting this model were a private method that was only called from a |
317f055
to
46b8f88
Compare
634004e
to
525c35e
Compare
525c35e
to
af22bed
Compare
af22bed
to
04e2408
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks great in general. I do have one concern but it's definitely open to discussion.
04e2408
to
f7c1611
Compare
JSON schema validator fails (correctly) with
|
e7ad6e6
to
fe6c671
Compare
fe6c671
to
484a4c4
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good
fixes #1659