Read+Write
TPS
16 K
Latency
30 ms p(99)
Cost
$42.89
per month / per 1K TPS
Read Only
TPS
0 K
Latency
0 ms p(99)
Write Only
TPS
16 K
Latency
30 ms p(99)
Configuration
Read / Write Allocation: 0% / 100%
Data Unit Size: 500 bytes
Testbed: 1 Gatling instances, 4 cores, 2 minutes progressive throughput, 24 minutes of max throughput
App: Akka 2023.10, 15K entities, event sourced log, source code
Infrastructure: Google Cloud Platform (GCP)
1 GKE cluster with 3 n2-std-4 nodes ($351.18 / mo with 1-yr full upfront)
1 PostgresSQL with 8 vCPUs 32GB memory, 333 GB SSD ($335.20 / mo with 1-yr full upfront)
Total Monthly Cost: $686.38
Definitions
TPS: # of transactional data units processed (read & write) / second
Latency: round trip HTTP request-response time measured during peak TPS
Cost: Total reserved instance costs for a 31 day month ratioed against 1K TPS
This was a sample test to demonstrate that 16,000 req/s of load with 0% reads and 100% writes was possible on GCP with Akka whose events are persisted to a Postgres database. This application simulates a digital twin solution, where a single Akka actor represented an IOT device that had to persist 500 bytes of information on each update.