t3.medium

Instance Configuration

AWS t3.medium Specifications:

• vCPUs: 2
• Memory: 4GB RAM
• Network Performance: Up to 5 Gigabit

DeepIntShield Configuration:

• Buffer Size: 15,000
• Initial Pool Size: 10,000
• Test Load: 5,000 requests per second (RPS)

Caution

This is a historical mocked-OpenAI run. The record does not identify a release SHA, test date, full percentile distribution, or CPU-credit state. Treat the numbers below as observations from that run, not a current capacity or SLO guarantee, and reproduce them with your build and policies.

---

Performance Results

Overall Performance Metrics

Metric	Value	Notes
Success Rate	100.00%	No failed requests in the recorded test window
Average Request Size	0.13 KB	Lightweight request payload
Average Response Size	1.37 KB	Standard response size for testing
Average Latency	2.12s	Total end-to-end response time
Peak Memory Usage	1,312.79 MB	~33% of available 4GB RAM

Where the time goes

In this run, the mocked upstream dominated end-to-end latency and the recorded gateway component was measured in microseconds.

Component	Latency	Notes
Upstream provider call	1.56s	The actual model API request (unavoidable in any setup)
DeepIntShield overhead	59 µs	Added latency from the gateway

DeepIntShield’s Total Overhead: 59 µs*

*Excludes the provider API call and JSON serialization, which are required in any implementation

---

Performance Analysis

Strengths on t3.medium

1. Recorded success rate: 100% during this 5,000-RPS run; reproduce over a production-length endurance test before setting a reliability target
2. Memory Efficiency: Uses only 33% of available RAM (1,312.79 MB / 4GB)
3. Minimal Overhead: Just 59 µs of added latency per request
4. Cost-effective: Sustains a 5,000 RPS workload on a low-cost instance

Resource Utilization

• Memory Usage: Very efficient at 1,312.79 MB peak usage
• CPU Performance: Handles 5,000 RPS workload effectively
• Recorded window: No failed requests or throughput degradation during the documented run; endurance behavior was not established

---

Configuration Recommendations

Optimal Settings for t3.medium

Based on test results, these configurations work well:

{
  "client": {
    "initial_pool_size": 10000,
    "buffer_size": 15000
  }
}

Tuning Opportunities

For Lower Memory Usage:

• Reduce initial_pool_size to 7,500-8,000
• Decrease buffer_size to 12,000-13,000
• Trade-off: Slightly higher latency

For Better Performance:

• Increase initial_pool_size to 12,000-13,000
• Increase buffer_size to 17,000-18,000
• Trade-off: Higher memory usage (monitor RAM limits)

---

Comparison Context

vs. t3.xlarge Performance

Metric	t3.medium	t3.xlarge	Difference
DeepIntShield Overhead	59 µs	11 µs	+81% slower
Average Latency	2.12s	1.61s	+24% slower
Memory Usage	1,312.79 MB	3,340.44 MB	-61% usage

Key Insights:

• t3.medium uses 61% less memory than t3.xlarge
• Performance trade-offs are reasonable for cost savings
• Most operations still complete in microseconds

---

Next Steps

When to upgrade to t3.xlarge:

• Sustained load approaches 4,000+ RPS

• Average latency climbs or success rate drops below 100%

• Memory usage approaches 75% of available RAM

• Run Your Own Benchmarks to test with your specific workload

• Compare with t3.xlarge for performance scaling analysis