Throughput
160–170k RPS locally; ~250k RPS on 24‑core bare‑metal (50GB cache).
High‑performance in‑memory HTTP cache & reverse proxy for latency‑sensitive workloads.
Built in Go with sharded storage, TinyLFU admission, background refresh, upstream controls, and observability.
I’m Borislav Glazunov, 29 y.o., senior/lead developer (Golang, Rust, PHP).
Open to visa sponsorship in New Zealand, Australia, Canada, EU, and Cyprus.
advCache — open‑source (Apache‑2.0) in‑memory HTTP cache & reverse proxy.
160–170k RPS locally; ~250k RPS on 24‑core bare‑metal (50GB cache).
1.5–3GB overhead at 50GB (no traces); ~7GB at 100% OTEL sampling.
Zero allocations, sharded counters, per‑shard LRU, TinyLFU admission.
Runtime toggles: admission, eviction, refresh, compression, observability.
Prometheus/VictoriaMetrics + OpenTelemetry tracing.
Health probes, ConfigMap config, Docker image.
cache:
api:
port: '8020' # <-- CHANGEME
upstream:
backend:
addr: http://127.0.0.1:8081 # <-- CHANGEME origin
compression:
enabled: true
observability:
enabled: true
endpoint: 127.0.0.1:4318 # <-- CHANGEME OTEL Collector
admission:
enabled: true
See the full configuration in the repo README.
GET /{any:*}
GET /k8s/probe
GET /metrics
/cache/bypass
, /on
, /off
/cache/http/compression
, /on
, /off
/cache/config
/cache/entry?key=<uint64>
/cache/clear
→ ?token=
/cache/invalidate
/cache/upstream/policy
, /await
, /deny
/cache/eviction
, /on
, /off
, /scale
/cache/lifetime-manager
, /on
, /off
/cache/force-gc
, /on
, /off
, /call
/cache/admission
, /on
, /off
/cache/observability
, /on
, /off
Apache‑2.0 license. Contributions welcome.