Re: Clarification needed on memory use behavior when using cache & nbthread

Hello Robin, If there is production traffic on the node, it is possible that there are multiple haproxy instances still handling requests and until they finish serving requests (and the haproxy process finishes execution) the memory cannot be freed. To avoid this problem, I would highly

Re: [ANNOUNCE] haproxy-2.0-dev2

Hi Pavlos! On Wed, Mar 27, 2019 at 09:57:32PM +0100, Pavlos Parissis wrote: > Have you considered enabling SO_INCOMING_CPU socket option in > order to increase data locality and CPU cache hits? No, really for our use case I'm not convinced at all by it, I'm only seeing risks of making things

Re: [ANNOUNCE] haproxy-2.0-dev2

On 26/3/19 6:24 π.μ., Willy Tarreau wrote: > Hi, > > HAProxy 2.0-dev2 was released on 2019/03/26. It added 176 new commits > after version 2.0-dev1. > > This version starts more important changes. One of the most visible > ones is that haproxy will now automatically start with threads enabled >

Clarification needed on memory use behavior when using cache & nbthread

Hi, I've tried using the new haproxy cache with "total-max-size 4095" and "nbthread 4" on a machine with 12GB of RAM and I'm getting hit with "[ALERT] 084/21 (1) : Unable to allocate cache." after a couple of reloads. HAProxy is started by running: /usr/bin/podman run --rm --name haproxy

Re: 1.9.5, SIGABRT

Hi! Thank you very much, I'll test your patch and will write back tomorrow. ср, 27 мар. 2019 г. в 16:50, William Lallemand : > On Wed, Mar 27, 2019 at 02:24:23PM +0100, William Lallemand wrote: > > > > On Wed, Mar 27, 2019 at 01:59:59PM +0300, Максим Куприянов wrote: > > > Hi, everybody! Got a

Re: 1.9.5, SIGABRT

Hi! There were nothing interesting in systemd journal - just general activities and no fault records. Site has a huge config, but its global part looks like this: global daemon uid 117 gid 126 stats socket /tmp/haproxy mode 777 stats socket /var/run/haproxy-admin.sock mode 700 level

Re: Strange "content-length" with http-use-htx

Il 2019-03-27 16:28 Christopher Faulet ha scritto: Your server seems to reject empty POST request when there is no content-length header. Christopher, I will test the fix as soon as it will be released in a 1.9.x. Thank you a lot again for the troubleshooting. .marcoc you have no idea of

Re: [PATCH]: BUILD/MINOR listener

Hi David, On Wed, Mar 27, 2019 at 04:13:28PM +, David CARLIER wrote: > Hi Here a little patch proposal. > > Kind regards. Sounds good ! I pushed it. Thanks a lot ! Olivier

[PATCH]: BUILD/MINOR listener

Hi Here a little patch proposal. Kind regards. From 3ffe96e6a68b5364ecd5364083c9c753e1097d9c Mon Sep 17 00:00:00 2001 From: David Carlier Date: Wed, 27 Mar 2019 16:08:42 + Subject: [PATCH] BUILD/MINOR: listener Silenting couple of warning related to signness. --- src/listener.c | 4 ++-- 1

Re: Strange "content-length" with http-use-htx

Le 27/03/2019 à 07:59, Marco Corte a écrit : Good morning! Christopher helped me fixing the http-use-htx issue "BUG/MEDIUM: proto_htx: Fix data size update if end of the cookie is removed". I am testing haproxy 1.9.5 with the same site real server, with the same configuration: browser

Re: 1.9.5, SIGABRT

On Wed, Mar 27, 2019 at 02:24:23PM +0100, William Lallemand wrote: > > On Wed, Mar 27, 2019 at 01:59:59PM +0300, Максим Куприянов wrote: > > Hi, everybody! Got a core on 1.9.5. > > > > Hello, > > How did it happened? Can you reproduce? > Can you share the systemd log of the service so we can

Re: 1.9.5, SIGABRT

On Wed, Mar 27, 2019 at 01:59:59PM +0300, Максим Куприянов wrote: > Hi, everybody! Got a core on 1.9.5. > Hello, How did it happened? Can you reproduce? Can you share the systemd log of the service so we can see the forking and leaving of the workers. Thanks. > Core was generated by

1.9.5, SIGABRT

Hi, everybody! Got a core on 1.9.5. Core was generated by `/usr/sbin/haproxy -Ws -f /etc/haproxy/haproxy.cfg -p /var/run/haproxy.pid'. Program terminated with signal SIGABRT, Aborted. #0 0x7fe164fd0428 in raise () from /lib/x86_64-linux-gnu/libc.so.6 (gdb) thread apply all bt Thread 1

Re: Strange "content-length" with http-use-htx

Le 27/03/2019 à 07:59, Marco Corte a écrit : Good morning! Christopher helped me fixing the http-use-htx issue "BUG/MEDIUM: proto_htx: Fix data size update if end of the cookie is removed". I am testing haproxy 1.9.5 with the same site real server, with the same configuration: browser

Strange "content-length" with http-use-htx

Good morning! Christopher helped me fixing the http-use-htx issue "BUG/MEDIUM: proto_htx: Fix data size update if end of the cookie is removed". I am testing haproxy 1.9.5 with the same site real server, with the same configuration: browser <--- HTTP/2 ---> haproxy <--- HTTP ---> real