Re: Shared Metrics Between Workers

2015-11-13 Thread Michael Fischer
On Fri, Nov 13, 2015 at 8:51 AM, Jeff Utter wrote: > I was wondering if anyone can offer any advice in handling stats > collections between worker processes in forking servers (like unicorn). > Specifically, I am attempting to work on a solution for the Prometheus ruby

Re: nginx reverse proxy getting ECONNRESET

2015-03-25 Thread Michael Fischer
On Tue, Mar 24, 2015 at 11:55 PM, Eric Wong e...@80x24.org wrote: Actually, are you getting 502 errors returned from nginx in this case? That would not be harmless. I suggest ensuring rack.input is fully-drained if that is the case (perhaps using PrereadInput). No, they're all 200 responses

nginx reverse proxy getting ECONNRESET

2015-03-24 Thread Michael Fischer
We have an nginx 1.6.2 proxy in front of a Unicorn 4.8.3 server that is frequently reporting the following error: 2015/03/24 01:46:01 [error] 11217#0: *872231 readv() failed (104: Connection reset by peer) while reading upstream The interesting things are: 1) The upstream is a Unix domain

Re: nginx reverse proxy getting ECONNRESET

2015-03-24 Thread Michael Fischer
On Tue, Mar 24, 2015 at 11:23 PM, Eric Wong e...@80x24.org wrote: So there might be data sitting on the socket if your application processing returns a response before it parsed the POST request. When this occurs, the nginx access logs show an HTTP 200 (OK) response with a 0 byte response

Re: Request Queueing after deploy + USR2 restart

2015-03-03 Thread Michael Fischer
If the response times are falling a minute or so after the reload, I'd chalk it up to a cold CPU cache. You will probably want to stagger your reloads across backends to minimize the impact. --Michael On Tue, Mar 3, 2015 at 2:24 PM, Sarkis Varozian svaroz...@gmail.com wrote: We have a rails

Re: Reserved workers not as webservers

2014-10-09 Thread Michael Fischer
On Thu, Oct 9, 2014 at 10:43 AM, Bráulio Bhavamitra brau...@eita.org.br wrote: As being forked process, I never saw a worker problem crashing master or other workers. Process isolation is one thing, but that's not the same thing as system isolation. Imagine your worker process has a memory

Re: Weird Unicorn Timeout Issues (Hibernation problem?)

2014-08-04 Thread Michael Fischer
On Mon, Aug 4, 2014 at 12:45 PM, Eric Wong e...@80x24.org wrote: [1] Perhaps persistent connections will be an option in the future if the support/documentation overhead is worth it, as nginx supports persistent connections to backends nowadays. I don't believe the added complexity is