dd-trace-java icon indicating copy to clipboard operation
dd-trace-java copied to clipboard

Llmobs java sdk integration

Open gary-huang opened this issue 5 months ago • 1 comments
trafficstars

What Does This Do

so we can get a nicer s3 link

Motivation

Additional Notes

Contributor Checklist

Jira ticket: [PROJ-IDENT]

gary-huang avatar Jun 11 '25 17:06 gary-huang

Benchmarks

Startup

Parameters

Baseline Candidate
baseline_or_candidate baseline candidate
git_branch master llmobs-java-sdk-integration
git_commit_date 1749638913 1749600946
git_commit_sha 089cf8fd47 8659686578
release_version 1.50.0-SNAPSHOT~089cf8fd47 1.50.0-SNAPSHOT~8659686578
See matching parameters
Baseline Candidate
application insecure-bank insecure-bank
ci_job_date 1749667271 1749667271
ci_job_id 977242415 977242415
ci_pipeline_id 67452334 67452334
cpu_model Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
kernel_version Linux runner-2ousnmcz-project-304-concurrent-1-9nrbd13k 6.8.0-1029-aws #31~22.04.1-Ubuntu SMP Thu Apr 24 21:16:18 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux Linux runner-2ousnmcz-project-304-concurrent-1-9nrbd13k 6.8.0-1029-aws #31~22.04.1-Ubuntu SMP Thu Apr 24 21:16:18 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
module Agent Agent
parent None None
variant iast iast

Summary

Found 0 performance improvements and 0 performance regressions! Performance is the same for 59 metrics, 12 unstable metrics.

Startup time reports for petclinic
gantt
    title petclinic - global startup overhead: candidate=1.50.0-SNAPSHOT~8659686578, baseline=1.50.0-SNAPSHOT~089cf8fd47

    dateFormat X
    axisFormat %s
section tracing
Agent [baseline] (1.024 s) : 0, 1023996
Total [baseline] (11.174 s) : 0, 11173840
Agent [candidate] (1.029 s) : 0, 1028861
Total [candidate] (11.061 s) : 0, 11061183
section appsec
Agent [baseline] (1.165 s) : 0, 1164856
Total [baseline] (11.227 s) : 0, 11226705
Agent [candidate] (1.162 s) : 0, 1162244
Total [candidate] (11.177 s) : 0, 11176827
section iast
Agent [baseline] (1.15 s) : 0, 1149767
Total [baseline] (11.314 s) : 0, 11313947
Agent [candidate] (1.157 s) : 0, 1157420
Total [candidate] (11.364 s) : 0, 11363782
section profiling
Agent [baseline] (1.264 s) : 0, 1263884
Total [baseline] (11.408 s) : 0, 11408030
Agent [candidate] (1.274 s) : 0, 1273931
Total [candidate] (11.452 s) : 0, 11451862
  • baseline results
Module Variant Duration Δ tracing
Agent tracing 1.024 s -
Agent appsec 1.165 s 140.86 ms (13.8%)
Agent iast 1.15 s 125.772 ms (12.3%)
Agent profiling 1.264 s 239.889 ms (23.4%)
Total tracing 11.174 s -
Total appsec 11.227 s 52.865 ms (0.5%)
Total iast 11.314 s 140.107 ms (1.3%)
Total profiling 11.408 s 234.191 ms (2.1%)
  • candidate results
Module Variant Duration Δ tracing
Agent tracing 1.029 s -
Agent appsec 1.162 s 133.383 ms (13.0%)
Agent iast 1.157 s 128.559 ms (12.5%)
Agent profiling 1.274 s 245.07 ms (23.8%)
Total tracing 11.061 s -
Total appsec 11.177 s 115.645 ms (1.0%)
Total iast 11.364 s 302.599 ms (2.7%)
Total profiling 11.452 s 390.679 ms (3.5%)
gantt
    title petclinic - break down per module: candidate=1.50.0-SNAPSHOT~8659686578, baseline=1.50.0-SNAPSHOT~089cf8fd47

    dateFormat X
    axisFormat %s
section tracing
BytebuddyAgent [baseline] (684.202 ms) : 0, 684202
BytebuddyAgent [candidate] (688.011 ms) : 0, 688011
GlobalTracer [baseline] (240.808 ms) : 0, 240808
GlobalTracer [candidate] (241.666 ms) : 0, 241666
AppSec [baseline] (57.007 ms) : 0, 57007
AppSec [candidate] (56.453 ms) : 0, 56453
Debugger [baseline] (6.191 ms) : 0, 6191
Debugger [candidate] (6.141 ms) : 0, 6141
Remote Config [baseline] (730.381 µs) : 0, 730
Remote Config [candidate] (734.104 µs) : 0, 734
Telemetry [baseline] (11.387 ms) : 0, 11387
Telemetry [candidate] (12.125 ms) : 0, 12125
section appsec
BytebuddyAgent [baseline] (701.607 ms) : 0, 701607
BytebuddyAgent [candidate] (700.094 ms) : 0, 700094
GlobalTracer [baseline] (238.171 ms) : 0, 238171
GlobalTracer [candidate] (237.716 ms) : 0, 237716
AppSec [baseline] (176.467 ms) : 0, 176467
AppSec [candidate] (176.092 ms) : 0, 176092
Debugger [baseline] (5.987 ms) : 0, 5987
Debugger [candidate] (5.958 ms) : 0, 5958
Remote Config [baseline] (635.006 µs) : 0, 635
Remote Config [candidate] (628.183 µs) : 0, 628
Telemetry [baseline] (7.392 ms) : 0, 7392
Telemetry [candidate] (7.32 ms) : 0, 7320
IAST [baseline] (22.05 ms) : 0, 22050
IAST [candidate] (21.794 ms) : 0, 21794
section iast
BytebuddyAgent [baseline] (801.675 ms) : 0, 801675
BytebuddyAgent [candidate] (806.659 ms) : 0, 806659
GlobalTracer [baseline] (230.516 ms) : 0, 230516
GlobalTracer [candidate] (231.318 ms) : 0, 231318
AppSec [baseline] (51.107 ms) : 0, 51107
AppSec [candidate] (52.697 ms) : 0, 52697
Debugger [baseline] (6.038 ms) : 0, 6038
Debugger [candidate] (6.088 ms) : 0, 6088
Remote Config [baseline] (597.004 µs) : 0, 597
Remote Config [candidate] (611.322 µs) : 0, 611
Telemetry [baseline] (7.926 ms) : 0, 7926
Telemetry [candidate] (8.03 ms) : 0, 8030
IAST [baseline] (28.449 ms) : 0, 28449
IAST [candidate] (28.185 ms) : 0, 28185
section profiling
BytebuddyAgent [baseline] (674.62 ms) : 0, 674620
BytebuddyAgent [candidate] (680.739 ms) : 0, 680739
GlobalTracer [baseline] (359.656 ms) : 0, 359656
GlobalTracer [candidate] (361.343 ms) : 0, 361343
AppSec [baseline] (61.363 ms) : 0, 61363
AppSec [candidate] (61.844 ms) : 0, 61844
Debugger [baseline] (6.069 ms) : 0, 6069
Debugger [candidate] (6.137 ms) : 0, 6137
Remote Config [baseline] (660.489 µs) : 0, 660
Remote Config [candidate] (664.096 µs) : 0, 664
Telemetry [baseline] (8.057 ms) : 0, 8057
Telemetry [candidate] (8.191 ms) : 0, 8191
ProfilingAgent [baseline] (102.702 ms) : 0, 102702
ProfilingAgent [candidate] (103.974 ms) : 0, 103974
Profiling [baseline] (102.726 ms) : 0, 102726
Profiling [candidate] (103.998 ms) : 0, 103998
Startup time reports for insecure-bank
gantt
    title insecure-bank - global startup overhead: candidate=1.50.0-SNAPSHOT~8659686578, baseline=1.50.0-SNAPSHOT~089cf8fd47

    dateFormat X
    axisFormat %s
section tracing
Agent [baseline] (1.031 s) : 0, 1030770
Total [baseline] (8.543 s) : 0, 8542628
Agent [candidate] (1.023 s) : 0, 1022796
Total [candidate] (8.493 s) : 0, 8492543
section iast
Agent [baseline] (1.15 s) : 0, 1149996
Total [baseline] (9.16 s) : 0, 9160209
Agent [candidate] (1.152 s) : 0, 1151668
Total [candidate] (9.165 s) : 0, 9165072
section iast_HARDCODED_SECRET_DISABLED
Agent [baseline] (1.156 s) : 0, 1156342
Total [baseline] (9.142 s) : 0, 9142016
Agent [candidate] (1.154 s) : 0, 1153536
Total [candidate] (9.128 s) : 0, 9128049
section iast_TELEMETRY_OFF
Agent [baseline] (1.15 s) : 0, 1150397
Total [baseline] (9.153 s) : 0, 9153232
Agent [candidate] (1.155 s) : 0, 1155423
Total [candidate] (9.222 s) : 0, 9222070
  • baseline results
Module Variant Duration Δ tracing
Agent tracing 1.031 s -
Agent iast 1.15 s 119.226 ms (11.6%)
Agent iast_HARDCODED_SECRET_DISABLED 1.156 s 125.572 ms (12.2%)
Agent iast_TELEMETRY_OFF 1.15 s 119.626 ms (11.6%)
Total tracing 8.543 s -
Total iast 9.16 s 617.581 ms (7.2%)
Total iast_HARDCODED_SECRET_DISABLED 9.142 s 599.388 ms (7.0%)
Total iast_TELEMETRY_OFF 9.153 s 610.603 ms (7.1%)
  • candidate results
Module Variant Duration Δ tracing
Agent tracing 1.023 s -
Agent iast 1.152 s 128.872 ms (12.6%)
Agent iast_HARDCODED_SECRET_DISABLED 1.154 s 130.74 ms (12.8%)
Agent iast_TELEMETRY_OFF 1.155 s 132.627 ms (13.0%)
Total tracing 8.493 s -
Total iast 9.165 s 672.529 ms (7.9%)
Total iast_HARDCODED_SECRET_DISABLED 9.128 s 635.506 ms (7.5%)
Total iast_TELEMETRY_OFF 9.222 s 729.526 ms (8.6%)
gantt
    title insecure-bank - break down per module: candidate=1.50.0-SNAPSHOT~8659686578, baseline=1.50.0-SNAPSHOT~089cf8fd47

    dateFormat X
    axisFormat %s
section tracing
BytebuddyAgent [baseline] (688.337 ms) : 0, 688337
BytebuddyAgent [candidate] (683.899 ms) : 0, 683899
GlobalTracer [baseline] (241.292 ms) : 0, 241292
GlobalTracer [candidate] (240.262 ms) : 0, 240262
AppSec [baseline] (57.778 ms) : 0, 57778
AppSec [candidate] (57.522 ms) : 0, 57522
Debugger [baseline] (6.168 ms) : 0, 6168
Debugger [candidate] (6.108 ms) : 0, 6108
Remote Config [baseline] (750.336 µs) : 0, 750
Remote Config [candidate] (737.633 µs) : 0, 738
Telemetry [baseline] (12.722 ms) : 0, 12722
Telemetry [candidate] (10.688 ms) : 0, 10688
section iast
BytebuddyAgent [baseline] (802.525 ms) : 0, 802525
BytebuddyAgent [candidate] (803.607 ms) : 0, 803607
GlobalTracer [baseline] (230.488 ms) : 0, 230488
GlobalTracer [candidate] (231.146 ms) : 0, 231146
IAST [baseline] (28.668 ms) : 0, 28668
IAST [candidate] (27.75 ms) : 0, 27750
AppSec [baseline] (50.348 ms) : 0, 50348
AppSec [candidate] (51.19 ms) : 0, 51190
Debugger [baseline] (5.955 ms) : 0, 5955
Debugger [candidate] (5.938 ms) : 0, 5938
Remote Config [baseline] (601.025 µs) : 0, 601
Remote Config [candidate] (602.618 µs) : 0, 603
Telemetry [baseline] (7.904 ms) : 0, 7904
Telemetry [candidate] (7.877 ms) : 0, 7877
section iast_HARDCODED_SECRET_DISABLED
BytebuddyAgent [baseline] (806.507 ms) : 0, 806507
BytebuddyAgent [candidate] (804.034 ms) : 0, 804034
GlobalTracer [baseline] (231.335 ms) : 0, 231335
GlobalTracer [candidate] (230.687 ms) : 0, 230687
IAST [baseline] (26.438 ms) : 0, 26438
IAST [candidate] (26.637 ms) : 0, 26637
AppSec [baseline] (53.711 ms) : 0, 53711
AppSec [candidate] (53.984 ms) : 0, 53984
Debugger [baseline] (6.028 ms) : 0, 6028
Debugger [candidate] (5.991 ms) : 0, 5991
Remote Config [baseline] (600.208 µs) : 0, 600
Remote Config [candidate] (591.763 µs) : 0, 592
Telemetry [baseline] (8.035 ms) : 0, 8035
Telemetry [candidate] (7.981 ms) : 0, 7981
section iast_TELEMETRY_OFF
BytebuddyAgent [baseline] (802.399 ms) : 0, 802399
BytebuddyAgent [candidate] (805.236 ms) : 0, 805236
GlobalTracer [baseline] (230.671 ms) : 0, 230671
GlobalTracer [candidate] (232.66 ms) : 0, 232660
IAST [baseline] (28.167 ms) : 0, 28167
IAST [candidate] (28.208 ms) : 0, 28208
AppSec [baseline] (51.082 ms) : 0, 51082
AppSec [candidate] (50.443 ms) : 0, 50443
Debugger [baseline] (5.985 ms) : 0, 5985
Debugger [candidate] (5.993 ms) : 0, 5993
Remote Config [baseline] (604.56 µs) : 0, 605
Remote Config [candidate] (599.23 µs) : 0, 599
Telemetry [baseline] (7.882 ms) : 0, 7882
Telemetry [candidate] (7.912 ms) : 0, 7912

Load

Parameters

Baseline Candidate
baseline_or_candidate baseline candidate
end_time 2025-06-11T18:10:47 2025-06-11T18:26:33
git_branch master llmobs-java-sdk-integration
git_commit_date 1749638913 1749600946
git_commit_sha 089cf8fd47 8659686578
release_version 1.50.0-SNAPSHOT~089cf8fd47 1.50.0-SNAPSHOT~8659686578
start_time 2025-06-11T18:10:32 2025-06-11T18:26:18
See matching parameters
Baseline Candidate
application insecure-bank insecure-bank
ci_job_date 1749667121 1749667121
ci_job_id 977242417 977242417
ci_pipeline_id 67452334 67452334
cpu_model Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
kernel_version Linux runner-66eemyw1-project-304-concurrent-1-gcgw2fgd 6.8.0-1029-aws #31~22.04.1-Ubuntu SMP Thu Apr 24 21:16:18 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux Linux runner-66eemyw1-project-304-concurrent-1-gcgw2fgd 6.8.0-1029-aws #31~22.04.1-Ubuntu SMP Thu Apr 24 21:16:18 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
thresholds_or_results results results
variant iast iast

Summary

Found 3 performance improvements and 5 performance regressions! Performance is the same for 7 metrics, 13 unstable metrics.

scenario Δ mean http_req_duration Δ mean throughput candidate mean http_req_duration candidate mean throughput baseline mean http_req_duration baseline mean throughput
scenario:load:petclinic:code_origins worse
[+589.926µs; +654.878µs] or [+7.188%; +7.980%]
worse
[-59.201op/s; -26.313op/s] or [-9.842%; -4.375%]
8.829ms 558.746op/s 8.207ms 601.504op/s
scenario:load:petclinic:iast better
[-935.808µs; -876.750µs] or [-11.621%; -10.887%]
better
[+56.379op/s; +92.162op/s] or [+9.162%; +14.976%]
7.147ms 689.655op/s 8.053ms 615.385op/s
scenario:load:petclinic:no_agent worse
[+743.228µs; +808.667µs] or [+8.489%; +9.236%]
worse
[-65.606op/s; -22.194op/s] or [-11.645%; -3.939%]
9.531ms 519.481op/s 8.755ms 563.380op/s
scenario:load:petclinic:profiling better
[-8.824ms; -8.765ms] or [-99.530%; -98.865%]
unstable
[+5194.003op/s; +20353.783op/s] or [+928.428%; +3638.239%]
0.071ms 13333.333op/s 8.866ms 559.441op/s
scenario:load:petclinic:tracing worse
[+723.267µs; +786.903µs] or [+inf%; +inf%]
unstable
[-20454.792op/s; -2133.444op/s] or [-127.842%; -13.334%]
755084.734ns 4705.882op/s 0.000ns 16000.000op/s

Dacapo

Parameters

Baseline Candidate
baseline_or_candidate baseline candidate
git_branch master llmobs-java-sdk-integration
git_commit_date 1749638913 1749600946
git_commit_sha 089cf8fd47 8659686578
release_version 1.50.0-SNAPSHOT~089cf8fd47 1.50.0-SNAPSHOT~8659686578
See matching parameters
Baseline Candidate
application biojava biojava
ci_job_date 1749666792 1749666792
ci_job_id 977242419 977242419
ci_pipeline_id 67452334 67452334
cpu_model Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
kernel_version Linux runner-2ousnmcz-project-304-concurrent-2-xyb6f67w 6.8.0-1029-aws #31~22.04.1-Ubuntu SMP Thu Apr 24 21:16:18 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux Linux runner-2ousnmcz-project-304-concurrent-2-xyb6f67w 6.8.0-1029-aws #31~22.04.1-Ubuntu SMP Thu Apr 24 21:16:18 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
variant appsec appsec

Summary

Found 0 performance improvements and 0 performance regressions! Performance is the same for 12 metrics, 0 unstable metrics.

Execution time for biojava
gantt
    title biojava - execution time [CI 0.99] : candidate=1.50.0-SNAPSHOT~8659686578, baseline=1.50.0-SNAPSHOT~089cf8fd47
    dateFormat X
    axisFormat %s
section baseline
no_agent (14.969 s) : 14969000, 14969000
.   : milestone, 14969000,
appsec (14.627 s) : 14627000, 14627000
.   : milestone, 14627000,
iast (18.749 s) : 18749000, 18749000
.   : milestone, 18749000,
iast_GLOBAL (17.793 s) : 17793000, 17793000
.   : milestone, 17793000,
profiling (15.763 s) : 15763000, 15763000
.   : milestone, 15763000,
tracing (14.896 s) : 14896000, 14896000
.   : milestone, 14896000,
section candidate
no_agent (15.379 s) : 15379000, 15379000
.   : milestone, 15379000,
appsec (14.834 s) : 14834000, 14834000
.   : milestone, 14834000,
iast (18.525 s) : 18525000, 18525000
.   : milestone, 18525000,
iast_GLOBAL (18.297 s) : 18297000, 18297000
.   : milestone, 18297000,
profiling (15.617 s) : 15617000, 15617000
.   : milestone, 15617000,
tracing (14.965 s) : 14965000, 14965000
.   : milestone, 14965000,
  • baseline results
Variant Execution Time [CI 0.99] Δ no_agent
no_agent 14.969 s [14.969 s, 14.969 s] -
appsec 14.627 s [14.627 s, 14.627 s] -342.0 ms (-2.3%)
iast 18.749 s [18.749 s, 18.749 s] 3.78 s (25.3%)
iast_GLOBAL 17.793 s [17.793 s, 17.793 s] 2.824 s (18.9%)
profiling 15.763 s [15.763 s, 15.763 s] 794.0 ms (5.3%)
tracing 14.896 s [14.896 s, 14.896 s] -73.0 ms (-0.5%)
  • candidate results
Variant Execution Time [CI 0.99] Δ no_agent
no_agent 15.379 s [15.379 s, 15.379 s] -
appsec 14.834 s [14.834 s, 14.834 s] -545.0 ms (-3.5%)
iast 18.525 s [18.525 s, 18.525 s] 3.146 s (20.5%)
iast_GLOBAL 18.297 s [18.297 s, 18.297 s] 2.918 s (19.0%)
profiling 15.617 s [15.617 s, 15.617 s] 238.0 ms (1.5%)
tracing 14.965 s [14.965 s, 14.965 s] -414.0 ms (-2.7%)
Execution time for tomcat
gantt
    title tomcat - execution time [CI 0.99] : candidate=1.50.0-SNAPSHOT~8659686578, baseline=1.50.0-SNAPSHOT~089cf8fd47
    dateFormat X
    axisFormat %s
section baseline
no_agent (1.47 ms) : 1459, 1482
.   : milestone, 1470,
appsec (2.391 ms) : 2343, 2440
.   : milestone, 2391,
iast (2.175 ms) : 2114, 2236
.   : milestone, 2175,
iast_GLOBAL (2.222 ms) : 2160, 2283
.   : milestone, 2222,
profiling (2.032 ms) : 1982, 2082
.   : milestone, 2032,
tracing (1.992 ms) : 1945, 2040
.   : milestone, 1992,
section candidate
no_agent (1.47 ms) : 1459, 1481
.   : milestone, 1470,
appsec (2.384 ms) : 2336, 2433
.   : milestone, 2384,
iast (2.174 ms) : 2113, 2235
.   : milestone, 2174,
iast_GLOBAL (2.225 ms) : 2163, 2286
.   : milestone, 2225,
profiling (2.026 ms) : 1977, 2075
.   : milestone, 2026,
tracing (2.001 ms) : 1954, 2049
.   : milestone, 2001,
  • baseline results
Variant Execution Time [CI 0.99] Δ no_agent
no_agent 1.47 ms [1.459 ms, 1.482 ms] -
appsec 2.391 ms [2.343 ms, 2.44 ms] 921.03 µs (62.6%)
iast 2.175 ms [2.114 ms, 2.236 ms] 705.1 µs (48.0%)
iast_GLOBAL 2.222 ms [2.16 ms, 2.283 ms] 751.35 µs (51.1%)
profiling 2.032 ms [1.982 ms, 2.082 ms] 561.694 µs (38.2%)
tracing 1.992 ms [1.945 ms, 2.04 ms] 522.099 µs (35.5%)
  • candidate results
Variant Execution Time [CI 0.99] Δ no_agent
no_agent 1.47 ms [1.459 ms, 1.481 ms] -
appsec 2.384 ms [2.336 ms, 2.433 ms] 914.492 µs (62.2%)
iast 2.174 ms [2.113 ms, 2.235 ms] 704.309 µs (47.9%)
iast_GLOBAL 2.225 ms [2.163 ms, 2.286 ms] 754.552 µs (51.3%)
profiling 2.026 ms [1.977 ms, 2.075 ms] 556.041 µs (37.8%)
tracing 2.001 ms [1.954 ms, 2.049 ms] 531.404 µs (36.2%)

pr-commenter[bot] avatar Jun 11 '25 18:06 pr-commenter[bot]