mirror of
http://git.haproxy.org/git/haproxy.git/
synced 2025-02-12 00:16:58 +00:00
0e875cf291
Sharding by-group is exactly identical to by-process for a single group, and will use the same number of file descriptors for more than one group, while significantly lowering the kernel's locking overhead. Now that all special listeners (cli, peers) are properly handled, and that support for SO_REUSEPORT is detected at runtime per protocol, there should be no more reason for now switching to by-group by default. That's what this patch does. It does only this and nothing else so that it's easy to revert, should any issue be raised. Testing on an AMD EPYC 74F3 featuring 24 cores and 48 threads distributed into 8 core complexes of 3 cores each, shows that configuring 8 groups (one per CCX) is sufficient to simply double the forwarded connection rate from 112k to 214k/s, reducing kernel locking from 71 to 55%. |
||
|---|---|---|
| .. | ||
| design-thoughts | ||
| internals | ||
| lua-api | ||
| 51Degrees-device-detection.txt | ||
| acl.fig | ||
| architecture.txt | ||
| close-options.txt | ||
| coding-style.txt | ||
| configuration.txt | ||
| cookie-options.txt | ||
| DeviceAtlas-device-detection.txt | ||
| gpl.txt | ||
| haproxy.1 | ||
| intro.txt | ||
| lgpl.txt | ||
| linux-syn-cookies.txt | ||
| lua.txt | ||
| management.txt | ||
| netscaler-client-ip-insertion-protocol.txt | ||
| network-namespaces.txt | ||
| peers-v2.0.txt | ||
| peers.txt | ||
| proxy-protocol.txt | ||
| queuing.fig | ||
| regression-testing.txt | ||
| seamless_reload.txt | ||
| SOCKS4.protocol.txt | ||
| SPOE.txt | ||
| WURFL-device-detection.txt | ||