Call for Papers ICEND2017 e-Technologies and Networks for Development

2016-11-13 Thread Jerika Joshua
Dear Colleague: The Fifth International Conference on e-Technologies and Networks for Development (ICeND2017) http://sdiwc.net/conferences/5th-international-conference- on-e-technologies-and-networks-for-development/ We invite you to attend and participate in the Fifth International Conference o

RE: AW: RE: slow https performance compared to http

2016-11-13 Thread Reinis Rozitis
> ab does not support TLS tickets (you can verify this with wireshark), so even > if > you do enable HTTP keepalive, the full TLS handshake has to be performed for > each request. > > it's a poor tool to measure total potential throughout of HTTPS servers. Now that you mention it I kind of remem

Re: AW: RE: slow https performance compared to http

2016-11-13 Thread Robert Paprocki
> Enabling keepalive on ab is one of the things you can do. I don't know > ab, so not sure if there is a better way. I also do not know if ab supports > SSL session caching or TLS tickets, which you would have to keep in > mind when benchmarking. ab does not support TLS tickets (you can verify th

Re: nginx upstream source ip address

2016-11-13 Thread Francis Daly
On Sat, Nov 12, 2016 at 03:25:49AM +, Michael Power wrote: Hi there, > I have an nginx web server with two ip addresses. I want to connect to two > upstream servers, where one upstream is configured to use one of the ip > addresses and the other upstream is configured to use the second ip

AW: RE: slow https performance compared to http

2016-11-13 Thread Lukas Tribus
> I'll do it but I guess the test will no longer be so relevant because I want > to simulate different users. Real user/browser DO keep-alive. Sendings thousands of requests per second in dedicated TLS session is not what you would see in real life from real users. > Anyway, the question is in

Re: RE: slow https performance compared to http

2016-11-13 Thread gigihc11
Just to help those not knowing about -k option: -k Enable the HTTP KeepAlive feature, i.e., perform multiple requests within one HTTP session. Default is no KeepAlive I'll do it but I guess the test will no longer be so relevant because I want to simulate different users. Anyway, the question

RE: slow https performance compared to http

2016-11-13 Thread Reinis Rozitis
> I test on running ab command on the same host as nginx is. Did you test with -k (keepalive) on or off? Without -k means that ab will do handshake every time and you will be limited by cpu and depending on the chosen cipher the performance (requests per second) can vary a lot. rr

Re: slow https performance compared to http

2016-11-13 Thread gigihc11
I used https://mozilla.github.io/server-side-tls/ssl-config-generator/ in order to configure the ssl part for my nginx: https://mozilla.github.io/server-side-tls/ssl-config-generator/?server=nginx-1.11.3&openssl=1.0.2g&hsts=yes&profile=intermediate but with no OCSP Stapling, ssl_trusted_certificate

Re: slow https performance compared to http

2016-11-13 Thread gigihc11
Oh, I forgot to mention that the setup included also: ssl_session_cache shared:SSL:1m; ssl_session_timeout 5m; Posted at Nginx Forum: https://forum.nginx.org/read.php?2,270898,270900#msg-270900 ___ nginx mailing list nginx@nginx.org http://mailman.ng

Re: slow https performance compared to http

2016-11-13 Thread Lucas Rolff
Because you have the TLS handshake that has to be done which is CPU bound Try change things like ssl_ciphers (to something faster), and use ssl_session_cache/ -- Best Regards, Lucas Rolff gigihc11 wrote: Hi, I have: nginx 1.11.3 Ubuntu 16.04.1 LTS openssl 1.0.2g-1ubuntu4.5 amd64 libssl1.0.0

slow https performance compared to http

2016-11-13 Thread gigihc11
Hi, I have: nginx 1.11.3 Ubuntu 16.04.1 LTS openssl 1.0.2g-1ubuntu4.5 amd64 libssl1.0.0:amd64 1.0.2g-1ubuntu4.5 weak CPU: N3150 16 GB RAM with this test-setup: open_file_cache max=1000 inactive=360s; open_file_cache_valid 30s; I test on running ab command on the same host as nginx is. For a 1.6K