You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
we tried to explore the AIMD feature introduced in the Concurrency limit module. So we tried out our existing Spectra UCP example with helidon-4.1.4.
From tests we observed that,
Significant volume of requests rejection with 503 , even for few bad requests above KPI.
Ex : Even with backoff-ratio of 0.9, we see 68% request failures whereas only a small subset of 3% requests are above KPI of 1sec.
The requests also fail due to sudden spikes , as the increase in dynamic concurrency takes time to adjust for the high user concurrency.
Ex: 50 users test , it takes ~4.3sec to reach max-limit of 50 from initial-limit of 25. During this period, we do see ~ 3% of errors.
So it will be good if we have queuing support like in Fixed Limit, to avoid such request rejection errors.
The text was updated successfully, but these errors were encountered:
Environment Details
we tried to explore the AIMD feature introduced in the Concurrency limit module. So we tried out our existing Spectra UCP example with helidon-4.1.4.
From tests we observed that,
Ex : Even with backoff-ratio of 0.9, we see 68% request failures whereas only a small subset of 3% requests are above KPI of 1sec.
Ex: 50 users test , it takes ~4.3sec to reach max-limit of 50 from initial-limit of 25. During this period, we do see ~ 3% of errors.
So it will be good if we have queuing support like in Fixed Limit, to avoid such request rejection errors.
The text was updated successfully, but these errors were encountered: