Skip to content
This repository has been archived by the owner on Mar 31, 2023. It is now read-only.

[Performance Analysis] DPM/ACA gRPC Performance Report #384

Open
wants to merge 11 commits into
base: master
Choose a base branch
from
+237 −0
Open

[Performance Analysis] DPM/ACA gRPC Performance Report #384

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
76a66fc
add adoc for dpm aca grpc analysis
haboy52581 Sep 15, 2020
effc445
update the images
haboy52581 Sep 15, 2020
5e5e7a1
adoc is not full compatible with word
haboy52581 Sep 15, 2020
051c7a7
update table for test result
haboy52581 Sep 17, 2020
9fd3615
add pic
haboy52581 Sep 17, 2020
8a43224
update adoc with pic
haboy52581 Sep 17, 2020
85cdfc7
Update dpmAcaGrpcTest.adoc
haboy52581 Sep 17, 2020
8bc0ec3
add images
haboy52581 Sep 24, 2020
c0d9ea8
add images
haboy52581 Sep 24, 2020
d759317
add execution detail chart
haboy52581 Sep 24, 2020
7fb47ed
add matrix based on variety of dpm payload size
haboy52581 Oct 2, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 23 additions & 1 deletion docs/modules/ROOT/pages/performance_analysis/dpmAcaGrpcTest.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ image::p1.png["Test Deployment",width=488,height=302]

[arabic, start=3]
. *Test results*
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We would like to describe latency mentioned in the following table as latency for a single connection.


same payload size about 22k each (8 neighbors each)
[cols=",,,,,,,,",options="header",]
|===
|*Log Time Cost Summary (ms)* | | | | | | | |
Expand All @@ -65,6 +65,28 @@ image::p1.png["Test Deployment",width=488,height=302]
|*90% TILE* |12 |11 |32 |28 |78 |84 |292 |262
|===
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The column and row of this table is opposite of the next one. Could we make them consistent?


different payload sizes vary from 1 neighbor to 10000 neighbor(2MB) each

*1WR+other OV-MAX+average*
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you elaborate what this means?


[cols=",,,,,,,,,",options="header",]
|===
|*1WR+other OV- Summary (ms)* | | | | | | | | |
|*Thread* |*Average* |*MIN* |*MAX* |*MEDIAN* |*>AVERAGE* |*<AVERAGE* |*99% TILE* |*95% TILE* |*90% TILE*
|1thread-10000 neighbors |247683.79 |55 |494571 |247767 |50.02% |49.98% |489695 |469885 |445171
|56threads-10000 |95191.16 |321 |189348 |95136 |49.97% |50.03% |187976 |180442 |171017
|64t-296 neighbors |2770.43972 |6 |5508 |2768 |49.95% |50.05% |5470.04 |5249 |4974.8
|64t-596 neighbors|5535.235418 |13 |11003 |5536 |50.01% |49.99% |10929.16 |10488.2 |9937.4
|64t-1196 neighbors|11098.09625 |33 |22058 |11096 |49.99% |50.01% |21920 |21022.4 |19928
|64t-2696 neighbors|25071.42771 |71 |49821 |25072 |50.01% |49.99% |49493.2 |47496.4 |45006
|64t-5395 neighbors|50201.73107 |253 |99695 |50218 |50.01% |49.99% |99015.32 |94986.6 |90036.8
|64t-10000 neighbors |95923.25 |578 |190523 |95909 |49.98% |50.02% |188762 |181228 |171652
|128t-10000 neighbors -9961 success |2734746.24 |46565 |5594098 |2715434 |49.63% |50.37% |5489436 |5215610 |4927763
|*128t-10000 neighbors* |95916.16 |1384 |189431 |95898 |49.99% |50.01% |188713 |181143 |171737
|*5120threads-9990 neighbors* |138147.48 |1158 |233183 |131662 |49.27% |50.73% |189697 |188972 |187884
|*9900t-5395 success * |88211.46 |32607 |165891 |90100.5 |58.31% |41.69% |110381 |97727 |96985
|*10000 threads-9961 success * |170505.16 |1429 |302362 |174740.5 |61.09% |38.91% |204086 |187064 |185778
|===

[arabic, start=4]
. *Test results analysis*
Expand Down