Skip to main content
Version: 1.21.3 (latest)

Test results

Load testing

Load testing helps evaluate the quality and speed of OMNI Platform operation under a certain load at a given time interval. A test image used is 240 KB (512х512 px) png image.

Test machine specification

CPURAMSSD
    2 x Intel Xeon E5-2683 v4:
  • 16 cores (32 threads)
  • Clockspeed: 2.10 GHz
  • Maximum speed: 3 GHz
128 GB DDR4 2400 ECCSamsung EVO 870 500 GB

Metrics

Metric Name Description
Users Number of parallel requests
Num threads Number of CPU threads in use
RPS Number of requests processed per second
(50%, 60%, ...) 50th, 60th, ... percentile % of requests are completed in no more than this time, in ms
Max Maximum time to process 1 request, in ms
Avg Average time to process 1 request, in ms

Basic load test

Test conditions
  • Face recognition method: 12v1000
  • ipvs: enabled
  • Database size: two mln profiles
  • Scalability: load testing of OMNI Platform 1.21.3 uses the following scaling settings:
    • image-api-age-estimator-dep: 5 instances, 2 workers each
    • image-api-emotion-estimator-dep: 5 instances, 2 workers each
    • image-api-gender-estimator-dep: 5 instances, 2 workers each
    • image-api-face-detector-liveness-estimator-dep: 5 instances, 2 workers each
    • image-api-mask-estimator-dep: 5 instances, 2 workers each
    • image-api-face-detector-template-extractor-dep: 8 instances, 2 workers each
    • image-api-face-detector-face-fitter-dep: 5 instances, 2 workers each
    • image-api-quality-assessment-estimator-dep: 5 instances, 2 workers each
    • image-api-template-extractor-dep: 5 instances, 2 workers each
    • image-api-verify-matcher-dep: 5 instances, 2 workers each
    • other services: 1 instance for each service

Test results

Request*UsersNum_threadsRPSAvgMinMax
create_profile (create a profile from a face image)111.059529011093
16114.1611299972313
detect (detect a face and estimate facial attributes from a face image)111.109068621044
16114.8810749502372
profiles (get a list of created profiles)117.7812898279
2301243.239232624606
search (search a face in the database by image)111.168598151026
16116.609639052148
search_by_ sample_id (search a face in the database by sample ID)1117.3458451121
70145.7215291701938
verify (compare a face image with a sample to determine if they belong to the same person)111.099168691083
16114.6510919732421
verify_by_ sample_id (compare two samples to determine if they belong to the same person)1141.762419168
2601455.73565731128

/* Detailed information on the API requests specified in the table can be found in API Reference.

Load test for receiving events/activities from cameras

Check typeAvg (ms)Min (ms)Max (ms)RPS
Receiving events50011562688224.8
Receiving activities1372349616966.5
CONCLUSIONS

During the test, OMNI Platform successfully processes the activity reception load at a rate of 1800 activities/sec (300 cameras are connected to OMNI Platform, each of which sends activities at a rate of 6 activities/sec).

The event reception load is processed at a rate of 200 events/sec (200 cameras are connected to OMNI Platform, each of which sends events at a rate of 1 event/sec).