Dear List for one project I put an HAProxy HTTPS frontend in front of two backends currently containing a single server each.
The nginx backend sits in front of a PHP application with a small number of workers. Because HAProxy handles queuing better than nginx I limited the nginx server to maxconn = 50. Now the question: How many in-flight requests will be passed in peak situations to nginx when I enable clear text HTTP/2 between HAProxy and nginx for that maxconn = 50 server? a) Is it 50 in-flight requests over a possibly smaller number of HTTP/2 connections? (requests <= 50) b) Is it 50 HTTP/2 connections with an unknown number of in-flight requests? (connections <= 50) c) Is it 50 HTTP/2 connections with a single in-flight request each? (connections = requests <= 50) Relevant configuration: > global > [...] > maxconn 2000 > > defaults > timeout connect 5s > timeout client 50s > timeout server 50s > [...] > > frontend fe_https > mode http > > bind :::443 v4v6 ssl crt-list /etc/haproxy/crt_list strict-sni alpn > h2,http/1.1 > > use_backend bk_AAAA if X Y > use_backend bk_nginx if X > > backend bk_nginx > mode http > > option forwardfor > > server foo [fdcb:*snip*]:8080 check source [fdcb:*snip*] maxconn 50 > proto h2 > > backend bk_AAAA > mode http > > option forwardfor > > server [...] [fdcb:*snip*]:6001 check source [fdcb:*snip*] > Best regards Tim Düsterhus
