From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: AS33070 50.56.128.0/17 X-Spam-Status: No, score=0.3 required=3.0 tests=AWL,MSGID_FROM_MTA_HEADER, PLING_QUERY,TVD_RCVD_IP shortcircuit=no autolearn=no version=3.3.2 Path: news.gmane.org!not-for-mail From: Ilya Maykov Newsgroups: gmane.comp.lang.ruby.rainbows.general Subject: Re: Rainbows! + EventMachine + Sinatra::Synchrony == pegged CPU when idle? Date: Mon, 23 Jul 2012 16:34:03 -0700 Message-ID: References: <20120619175409.GA27303@dcvr.yhbt.net> NNTP-Posting-Host: plane.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Trace: dough.gmane.org 1343086453 32191 80.91.229.3 (23 Jul 2012 23:34:13 GMT) X-Complaints-To: usenet@dough.gmane.org NNTP-Posting-Date: Mon, 23 Jul 2012 23:34:13 +0000 (UTC) Cc: normalperson-rMlxZR9MS24@public.gmane.org To: "Rainbows! list" Original-X-From: rainbows-talk-bounces-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org Tue Jul 24 01:34:13 2012 Return-path: Envelope-to: gclrrg-rainbows-talk@m.gmane.org X-Original-To: rainbows-talk-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org Delivered-To: rainbows-talk-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=ElOBDZok1V6sedpbuTebKLIegThqHIraZRF2rUfdYmQ=; b=k2tOpckqAmtLjjWUMGGZkYq5OZjbvT6zfUwft5R2EirrqC8r1UXVyMX9vKJFiCWYob ekL3MKiXmAlbamjmONmCFjfkwWDIvxNxaLiVBAy5BTCK8FT2YKTwOLkK4PebobYvJCuw LcL7NPsVcSXzHZrKIADHSYj5tbWG3IxE7BM09FScRuz16apZB4KyUyeo5UHK/fMZgG5K ZuYaQeryOY45zXE2W6qOML1pD3d3mAoCT5FvYSbSDM4C0lEOCpzXAqNHa0VV5Wq0iADC YCo7pi+DLNUtj/+k189IjpyyalsTAljmRvMa7rliJKTSqxsRBEfY/Ybi9x8fz3rIdrcQ J69g== In-Reply-To: <20120619175409.GA27303-yBiyF41qdooeIZ0/mPfg9Q@public.gmane.org> X-BeenThere: rainbows-talk-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Original-Sender: rainbows-talk-bounces-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org Errors-To: rainbows-talk-bounces-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org Xref: news.gmane.org gmane.comp.lang.ruby.rainbows.general:382 Archived-At: Received: from 50-56-192-79.static.cloud-ips.com ([50.56.192.79] helo=rubyforge.org) by plane.gmane.org with esmtp (Exim 4.69) (envelope-from ) id 1StS8i-0001Cn-VQ for gclrrg-rainbows-talk@m.gmane.org; Tue, 24 Jul 2012 01:34:13 +0200 Received: from localhost.localdomain (localhost [127.0.0.1]) by rubyforge.org (Postfix) with ESMTP id 090E12E067; Mon, 23 Jul 2012 23:34:10 +0000 (UTC) Received: from mail-lb0-f178.google.com (mail-lb0-f178.google.com [209.85.217.178]) by rubyforge.org (Postfix) with ESMTP id 7E35F2E063 for ; Mon, 23 Jul 2012 23:34:04 +0000 (UTC) Received: by lbbgj10 with SMTP id gj10so10515991lbb.23 for ; Mon, 23 Jul 2012 16:34:03 -0700 (PDT) Received: by 10.152.102.234 with SMTP id fr10mr19272235lab.32.1343086443622; Mon, 23 Jul 2012 16:34:03 -0700 (PDT) Received: by 10.152.30.140 with HTTP; Mon, 23 Jul 2012 16:34:03 -0700 (PDT) Hi Eric, Sorry for the delayed response. I've added inline answers to your questions. We've since resolved this issue by disabling keepalive in our rainbows config. So, this probably had to do with the keepalive implementation either in Rainbows itself or in the base Unicorn code. Answers to your other questions are inlined below. -- Ilya On Tue, Jun 19, 2012 at 10:54 AM, Eric Wong wrote: > Ilya Maykov wrote: >> Hi all, >> >> We're using Rainbows + EventMachine + Sinatra::Synchrony to run a >> fleet of RESTful web servers backed by a Cassandra cluster. We are >> using the EventMachineTransport to talk to Cassandra with an >> EM::Synchrony::ConnectionPool in each rainbows worker. We have a Storm >> cluster pushing a large stream of real-time data into the Rainbows >> fleet using HTTP PUT requests. We're running into some very strange >> performance issues and need help figuring out what's going on. > > I'm not at all familiar with Storm nor Cassandra. How big are the HTTP > PUT requests Rainbows! is getting? Is Storm pipelining HTTP requests by > any chance? That may not do well with the EM portion of Rainbows! The PUT requests are small - probably about 100 bytes of JSON payload per request (not counting HTTP overhead, headers, etc). Pipelining is disabled on the clients, though keep-alive is not. > >> Basically, when load is low, everything looks good. When we crank up >> the load, all of a sudden the CPU gets pegged, request latencies go >> waaaay up, and requests start timing out. Once this state is reached, >> the high CPU usage (4 rainbows worker processes at ~50% each on a >> 2-core machine = nearly full load) remains even if we completely shut >> off all incoming traffic. > >> Taking a look with strace -p, it looks like >> the rainbows processes are writing ascii NUL characters to file >> descriptor 7 (which is a FIFO) as fast as the kernel will let them. My >> guess is that the worker is trying to communicate with the rainbows >> master process via the FIFO. > > No, rainbows doesn't have code to send "\0" to the master. I > don't think EM does, either, maybe some other library you're > using... > No idea ... I think EventMachine does start up a background thread, not sure if that would affect anything in a bad way. > Which version of Ruby is this? Try adding "-f" to follow threads > for a worker. > This is with Ruby 1.9.2-p290, installed by using rbenv-installer. >> Not sure what is triggering this >> behavior, but would like to know if anyone else has ever seen >> something like this. This thread sounded like it could've been a >> similar issue, but died out without any conclusion: >> http://rubyforge.org/pipermail/rainbows-talk/2012-April/000345.html >> >> Some details about the setup: >> >> 6-node cassandra cluster >> 3 nodes running rainbows web servers >> 4 rainbows workers per node >> max of 50 cassandra connections per rainbows worker >> rainbows.conf has: >> >> Rainbows! do >> use :EventMachine >> worker_connections 50 >> keepalive_requests 1000 >> keepalive_timeout 10 >> end > > Do you have preload_app set to true anywhere? (Try leaving it as false > (the default)) > No, we are not using preload_app. > Can you also try "keepalive_timeout 0" to disable keepalive? (EM > handles it internally, but I'm not sure how well) > This turned out to be the problem. Disabling keepalive got rid of the CPU pegging. Surprisingly, it also made our average latency drop from about 50 ms to about 20 ms per request, even though every request now has to negotiate a connection handshake. So, we're just going to keep it disabled for now. The bug may be inside the keepalive code in Rainbows or Unicorn (not familiar with the codebase so not sure where that code lives). >> So, each rainbows node can handle 4 * 50 = 200 simultaneous connections >> >> 12 Storm worker processes writing to the rainbows web servers >> each Storm worker has max of 10 connections open to each of the 3 rainbows nodes >> >> So, each rainbows node has 12 * 10 = 120 incoming connections from Storm. >> >> Have been playing around with the numbers, the bug (assuming it is a >> bug) seems to be easier to trigger when I increase the number of >> incoming connections (from Storm workers), even if they are a lot less >> than the rainbows servers can take (60-70% of the max connections is >> usually enough). The bug is also easier to trigger when we increase >> the volume of data we're pushing through Storm - hundreds or thousands >> of requests per minute, no bug - hundreds of thousands of requests per >> minute, yes bug. Cassandra is not the issue, it can easily take the >> write load we're generating and is basically idle. >> >> Any help in figuring this out would be greatly appreciated. Thanks, > > Try my suggestions above. > > I would also search your libs/gems for what's writing "\0" since I don't > think it's Rainbows!... > _______________________________________________ > Rainbows! mailing list - rainbows-talk-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org > http://rubyforge.org/mailman/listinfo/rainbows-talk > Do not quote signatures (like this one) or top post when replying _______________________________________________ Rainbows! mailing list - rainbows-talk-GrnCvJ7WPxnNLxjTenLetw@public.gmane.org http://rubyforge.org/mailman/listinfo/rainbows-talk Do not quote signatures (like this one) or top post when replying