This benchmark compares the speed at which different web servers respond to requests for small PHP scripts. We used a tiny script to avoid saturating the network connection and to show raw speed differences between the different setups. In our testing, LiteSpeed outperformed nginx and Apache by as much as 1.3X and 4.5X, respectively.
You can run these same tests. We followed the methodology laid out on http2benchmark.org.
Summary
HTTP/2 Test Results
h2load -n 100000 -c 10 -t 1 -T 5 -m 10 -H 'Accept-Encoding: gzip,deflate' https://domain.com/hello.php
| Server | Requests / Sec | MB / Sec | Failures | Header Compression |
|---|---|---|---|---|
| LiteSpeed | 13571.9 | 0.88 | 0 | 96.19% |
| Nginx | 10570.9 | 1.77 | 0 | 29.61% |
| Apache | 3049.1 | 0.18 | 0 | 94.2% |
Please note: we usually run the h2load test with -c 100, but in this case there were too many errors occurring with nginx and Apache. We reduced -c to 10 for this reason.
LiteSpeed Web Server responds to PHP requests 1.3X faster than Nginx and 4.5X faster than Apache.
HTTP 1.1 Test Results
wrk -c 100 -t 1 -d 5s -H 'Accept-Encoding: gzip,deflate' https://domain.com/hello.php
| Server | Requests / Sec | MB / Sec | Failures | Header Compression |
|---|---|---|---|---|
| LiteSpeed | 12555.4 | 3.16 | N/A | N/A |
| Nginx | 10398.7 | 3.08 | N/A | N/A |
| Apache | 2953.98 | 0.79 | N/A | N/A |
LiteSpeed Web Server responds to PHP requests 1.2X faster than Nginx and 4.3X faster than Apache.
Test Environment
-
Server Tested:
- LiteSpeed Web Server v5.4.1
- nginx v1.16.1
- Apache v2.4.41
-
Client Machine:
- Memory Size: 1GB
- CPU number: 1
- CPU Threads: 1
- CPU Model: Virtual CPU 6db7dc0e7704
- Disk: NVMe SSD
-
Server Machine:
- Memory Size: 1GB
- CPU number: 1
- CPU Threads: 1
- CPU Model: Virtual CPU 6db7dc0e7704
- Disk: NVMe SSD
-
Network:
- Traffic: 7.82 Gbits/sec
- Latency: 0.374 ms
