subscription-benchmark-pr-413.md

MAAS Benchmark - subscription PR

Run metadata

• Executed at: 2026-02-24 05:13:54 UTC
• Repo: ~/vanilla/subscription-maas-413/maas-benchmark-vanilla/maas-benchmark
• Target host: maas.apps.rosa.uu2gf-j2mrj-mmg.iqgw.p3.openshiftapps.com
• Protocol: https
• Model ID detected from MAAS API: facebook/opt-125m
• Model URL detected from MAAS API: http://maas.apps.rosa.uu2gf-j2mrj-mmg.iqgw.p3.openshiftapps.com/llm/facebook-opt-125m-simulated
• k6 version: k6 v1.5.0 (commit/7961cefa12, go1.25.5, linux/amd64)

Setup done

• Created 5 benchmark tokens via:
  • POST https://$HOST/maas-api/v1/tokens using oc whoami -t
• Wrote token file expected by k6 script:
  • tokens/all/all_tokens.json
  • Free tokens: 5
  • Premium tokens: 0

Commands run

# Auto-discover gateway + model
GATEWAY_HOST=$(oc get gateway maas-default-gateway -n openshift-ingress \
  -o jsonpath='{.spec.listeners[0].hostname}')
OC_TOKEN=$(oc whoami -t)
MAAS_TOKEN=$(curl -sSk -X POST "https://${GATEWAY_HOST}/maas-api/v1/tokens" \
  -H "Authorization: Bearer ${OC_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{"expiration": "4h"}' | jq -r '.token')
DISCOVERY=$(curl -sSk "https://${GATEWAY_HOST}/v1/models" \
  -H "Authorization: Bearer ${MAAS_TOKEN}")
MODEL_PATH=$(echo "${DISCOVERY}" | jq -r '.data[0].url' | sed -E 's|https?://[^/]*||')
MODEL_ID=$(echo "${DISCOVERY}" | jq -r '.data[0].id')

# Baseline runs
k6 run -e HOST="$GATEWAY_HOST" -e PROTOCOL=https -e MODEL_PATH="$MODEL_PATH" -e MODEL_ID="$MODEL_ID" -e BURST_VUS=1 -e BURST_ITERATIONS=20 --summary-export=results/subscription-pr-burst-1vu-summary.json k6/maas-performance-test.js
k6 run -e HOST="$GATEWAY_HOST" -e PROTOCOL=https -e MODEL_PATH="$MODEL_PATH" -e MODEL_ID="$MODEL_ID" -e BURST_VUS=3 -e BURST_ITERATIONS=30 --summary-export=results/subscription-pr-burst-3vu-summary.json k6/maas-performance-test.js
k6 run -e HOST="$GATEWAY_HOST" -e PROTOCOL=https -e MODEL_PATH="$MODEL_PATH" -e MODEL_ID="$MODEL_ID" -e BURST_VUS=5 -e BURST_ITERATIONS=100 --summary-export=results/subscription-pr-burst-5vu-summary.json k6/maas-performance-test.js

Results

Test	HTTP reqs	Success rate	Failed req rate	p95 latency (ms)	Auth failure checks
1 VU, 20 iters	20	100.00%	0.00%	153.19	0
3 VUs, 30 iters	30	16.67%	83.33%	33.02	25
5 VUs, 100 iters	100	1.00%	99.00%	5.79	99

Artifacts

• results/subscription-pr-maas-benchmark.md
• tokens/all/all_tokens.json
• results/subscription-pr-burst-1vu-summary.json
• results/subscription-pr-burst-1vu.log
• results/subscription-pr-burst-3vu-summary.json
• results/subscription-pr-burst-3vu.log
• results/subscription-pr-burst-5vu-summary.json
• results/subscription-pr-burst-5vu.log