HttpArena
Frameworks

mq-bridge-py

Emerging · Python · engine: mq-bridge · standard configuration · completeness 2/4

mq-bridge Python bindings (mq_bridge_py). A single http->response route dispatches on request metadata while HTTP framing stays in Rust; cleartext HTTP/1.1 + h2c run on 8080/8082, optional TLS listeners serve HTTP/2 on 8443 and HTTP/1.1 on 8081, and the inline-response fast path keeps responses off the GIL so the Python handler runs only the per-request dispatch. Postgres via psycopg for async-db, crud (Redis cache-aside) and fortunes, which renders per request with the Jinja2 template engine; static assets are read from /data/static per request, serving the on-disk .gz variant when the client accepts it; /delay waits with a blocking sleep, so async concurrency is the worker-process count.

Achievements

🥇 1 Gold · 🥉 1 Bronze. Top three of a field, taken in this entry's own league: the family composite, the same composite among entries written in the same language, and each test profile it is scored on. Every field is the one the badges publish, so a medal and a badge always say the same thing. How medals are awarded.

MedalAwardFieldRank
🥇 GoldWithin its languagePython · HTTP/1.11 of 9
🥉 BronzeTest profileHTTP/2 · Static3 of 16

Composite rank

Each profile of a family is worth 100 to the entry that leads it, and the composite is the sum over the family, less 2.5% for each of routing, middleware, request and response the entry does not do for you - its completeness factor, which the WebSocket and gRPC families do not carry. The field is this entry's own league: engines and reverse proxies are scored apart from frameworks. How it works.

FamilyRankComposite
HTTP/1.137 of 712219
HTTP/210 of 18614

Every result

Alpha Round, 20 runs. Requests per second is the best of three; latency, CPU and memory come from that run.

CategoryProfileConnsReq/secAvgp99CPUMemory
ConnectionBaseline4,0961,209,5373.39ms7.79ms6599.4%3.6GiB
ConnectionPipelined4,0962,654,61724.70ms58.10ms6527.2%3.2GiB
ConnectionShort-lived4,096953,8774.28ms20.60ms6504.6%5.2GiB
EfficiencyLatency-10K1,0249,980150.7us197.0us107.3%2.8GiB
EfficiencyLatency-1M1,024911,233864185.0us4999168.0us6546.8%3.1GiB
EfficiencyLatency-500K/81,024108,8357698735.9us15806464.0us775.4%3.6GiB
WorkloadJSON Comp4,09698,86141.28ms125.30ms6491.6%4.8GiB
WorkloadJSON Comp16,384118,351135.75ms303.50ms6256.4%6.4GiB
WorkloadJSON TLS4,096331,82612.35ms72.71ms6684.0%4.1GiB
Workload8Gbit51249,369198.3us304.0us883.0%2.9GiB
DatabaseAsync DB1,02477,50612.73ms59.80ms5400.8%5.2GiB
HTTP/2Baseline2561,010,29227.31ms138.55ms6615.9%13.4GiB
HTTP/2Baseline1,024929,222101.66ms333.62ms6550.6%21.0GiB
HTTP/2Static256234,81835.23ms384.90ms6595.9%7.1GiB
HTTP/2Static1,024265,705118.44ms456.67ms6542.7%9.5GiB
HTTP/2Baseline (h2c)256964,82028.19ms142.50ms6683.8%12.7GiB
HTTP/2Baseline (h2c)1,024904,557109.65ms392.56ms6665.8%19.8GiB
HTTP/2Baseline (h2c)4,096872,281411.23ms828.57ms6550.7%26.2GiB
HTTP/2JSON (h2c)1,024320,500100.18ms319.92ms6629.2%10.1GiB
HTTP/2JSON (h2c)4,096314,660385.57ms844.83ms6528.1%15.5GiB

Compared with

The Python entries around mq-bridge-py on the HTTP/1.1 composite, and the one leading them. The last column shows every profile side by side.

EntryCompositevs mq-bridge-py
fastpysgi-wsgi3148+42%head to head
pyronova2404+8%head to head
aiohttp2072-7%head to head
blackbull1658-25%head to head

Compare mq-bridge-py with any Python entry · Compare mq-bridge-py with any entry, in any language · Every Python entry, ranked

Results updated · How the benchmark is run · The machine · Add or fix an entry