PHP web framework comparison: any two, head to head
swoole is quicker than hyperf on 13 of the 15 profiles they both run, and behind on 1. On the HTTP/1.1 composite they score 5037 and 1777.
Pick any two of the 5 PHP entries. Requests per second is the best of three runs and the delta is the first column against the second; every row is the same profile at the same connection count, on the same machine. What each profile measures.
| Profile | Conns | swoole req/sec | hyperf req/sec | Delta | swoole p99 | hyperf p99 |
|---|---|---|---|---|---|---|
| Baseline | 4,096 | 2,310,475 | 387,711 | +496% | 9.83ms | 12.90ms |
| Pipelined | 4,096 | 3,298,449 | 466,686 | +607% | 44.50ms | 300.30ms |
| Short-lived | 4,096 | 1,940,869 | 294,276 | +560% | 10.00ms | 17.80ms |
| Async Delay | 32,000 | 12,618 | 303,908 | -96% | 5.00s | 121.20ms |
| Latency-10K | 1,024 | 9,982 | 9,982 | +0% | 117.0us | 366.0us |
| Latency-1M | 1,024 | 997,438 | 307,541 | +224% | 210.0us | 13668352.0us |
| Latency-500K/8 | 1,024 | 331,021 | 80,607 | +311% | 10416128.0us | 16519168.0us |
| JSON Comp | 4,096 | 544,249 | 242,307 | +125% | 35.00ms | 22.80ms |
| JSON Comp | 16,384 | 539,064 | 241,986 | +123% | 100.20ms | 47.10ms |
| JSON TLS | 4,096 | 797,654 | 199,611 | +300% | 111.38ms | 422.16ms |
| 8Gbit | 512 | 49,356 | 48,988 | +1% | 142.0us | 1155.0us |
| Async DB | 1,024 | 249,837 | 63,281 | +295% | 25.70ms | 34.90ms |
| Echo | 512 | 3,056,601 | 431,538 | +608% | 3.04ms | 1.64ms |
| Echo | 4,096 | 3,354,954 | 429,659 | +681% | 6.79ms | 10.50ms |
| Echo | 16,384 | 3,168,894 | 414,613 | +664% | 13.70ms | 13.90ms |
Common comparisons
swoole vs hyperf · swoole vs php-fpm · swoole vs true-async-server · hyperf vs php-fpm · hyperf vs true-async-server · php-fpm vs true-async-server
Questions
Is swoole faster than hyperf?
swoole is quicker than hyperf on 13 of the 15 profiles they both run, and behind on 1. On the HTTP/1.1 composite they score 5037 and 1777. Both run on the same machine, in the same round, against the same profiles.
Is swoole faster than php-fpm?
swoole is quicker than php-fpm on 12 of the 16 profiles they both run, and behind on 3. On the HTTP/1.1 composite they score 5037 and 1356. Both run on the same machine, in the same round, against the same profiles.
Is swoole faster than true-async-server?
swoole is quicker than true-async-server on 8 of the 16 profiles they both run, and behind on 8. On the HTTP/1.1 composite they score 5037 and 5288. Both run on the same machine, in the same round, against the same profiles.
Is hyperf faster than php-fpm?
hyperf is quicker than php-fpm on 8 of the 12 profiles they both run, and behind on 3. On the HTTP/1.1 composite they score 1777 and 1356. Both run on the same machine, in the same round, against the same profiles.
Which PHP framework is fastest overall?
true-async-server holds the highest HTTP/1.1 composite of the PHP entries, at 5288. The composite is throughput over the whole suite; if a service is one shape of workload, compare that profile on its own in the table above, because the order changes.
Every PHP entry
Results updated · PHP composite ranking · Compare across languages · Other languages · Open the leaderboard