Comments on: Twisted.web vs Tornado Performance Test http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/ Make stuff to do things Tue, 31 Aug 2010 03:54:33 -0700 http://wordpress.org/?v=2.8.4 hourly 1 By: air jordan 12 http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-96 air jordan 12 Wed, 09 Jun 2010 01:32:23 +0000 http://www.apparatusproject.org/blog/?p=342#comment-96 Here elaborates the matter not only extensively but also detailly .I support the <br>write's unique point.It is useful and benefit to your daily life.You can go those <br>sits to know more relate things.They are strongly recommended by friends.Personally!<br><a href="http://you-rselfas.com/" rel="nofollow">http://you-rselfas.com/</a> Here elaborates the matter not only extensively but also detailly .I support the
write's unique point.It is useful and benefit to your daily life.You can go those
sits to know more relate things.They are strongly recommended by friends.Personally!
http://you-rselfas.com/

]]> By: air max shoes http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-83 air max shoes Tue, 08 Jun 2010 03:18:02 +0000 http://www.apparatusproject.org/blog/?p=342#comment-83 Well , the view of the passage is totally correct ,your details is really reasonable and you guy give us valuable informative post, I totally agree the standpoint of upstairs. I often surfing on this forum when I m free and I find there are so much good information we can learn in this forum! <br><a href="http://aesthetic-appeal.com" rel="nofollow">aesthetic-appeal</a> Well , the view of the passage is totally correct ,your details is really reasonable and you guy give us valuable informative post, I totally agree the standpoint of upstairs. I often surfing on this forum when I m free and I find there are so much good information we can learn in this forum!
aesthetic-appeal

]]> By: Twisted.web vs Tornado, part deux | Apparatus http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-56 Twisted.web vs Tornado, part deux | Apparatus Thu, 17 Sep 2009 16:18:16 +0000 http://www.apparatusproject.org/blog/?p=342#comment-56 [...] first time I conducted a performance test between Twisted.web and Tornado, the results were not very meaningful in retrospect.  I have three good reasons for redoing the [...] [...] first time I conducted a performance test between Twisted.web and Tornado, the results were not very meaningful in retrospect.  I have three good reasons for redoing the [...]

]]> By: Name http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-55 Name Mon, 14 Sep 2009 11:50:07 +0000 http://www.apparatusproject.org/blog/?p=342#comment-55 If you're running Tornado on Mac OS X and not on Linux, you're using the select() backend and not the epoll backend. Thus your performance numbers are heavily skewed against Tornado's strengths in terms of number of simultaneous connections it can support.<br><br>Yes, it'd be nice if it used libevent so that it could take advantage of kqueue, but it doesn't. If you're running Tornado on Mac OS X and not on Linux, you're using the select() backend and not the epoll backend. Thus your performance numbers are heavily skewed against Tornado's strengths in terms of number of simultaneous connections it can support.

Yes, it'd be nice if it used libevent so that it could take advantage of kqueue, but it doesn't.

]]> By: anonymous http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-54 anonymous Mon, 14 Sep 2009 10:28:06 +0000 http://www.apparatusproject.org/blog/?p=342#comment-54 Apache benchmark is totally unrealistic. As well you should test a web framework when it is loaded up with apps. Apache benchmark is totally unrealistic. As well you should test a web framework when it is loaded up with apps.

]]> By: exarkun http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-53 exarkun Sun, 13 Sep 2009 15:16:54 +0000 http://www.apparatusproject.org/blog/?p=342#comment-53 I've investigated this a bit further and what I found suggests that this behavior may result from the platform's use of syn cookies. When I was initially unable to reproduce this, I was using Ubuntu Hardy, which disables syn cookies by default. After some experimenting on Ubuntu Jaunty, after a tip from Thomas Herve, I was able to reproduce the problem (although only at a much higher concurrency level - around 500). Jaunty enables syn cookies by default. Then, returning to Hardy and enabling syn cookies, I was able to produce the behavior there. I was also able to provoke this behavior from ab running against the Tornado server - which is perfectly sensible if this explanation is correct, since it's primarily do to something the platform TCP stack is doing, not something either Twisted or Tornado is doing.<br><br>I haven't dug into this so deeply that I'm entirely confident that this completely explains the behavior, but I think it's a pretty good start. A direction for further investigation would be to write a client like ab but which reports more identifying information about each connection so that the failing connections can be traced through the entire network.<br><br>One thing I'm not sure about is whether OS X uses syn cookies. Some web pages I've found with Google suggest that it does, but it would be nice to get the information from a more authoritative/reliable source. I've investigated this a bit further and what I found suggests that this behavior may result from the platform's use of syn cookies. When I was initially unable to reproduce this, I was using Ubuntu Hardy, which disables syn cookies by default. After some experimenting on Ubuntu Jaunty, after a tip from Thomas Herve, I was able to reproduce the problem (although only at a much higher concurrency level – around 500). Jaunty enables syn cookies by default. Then, returning to Hardy and enabling syn cookies, I was able to produce the behavior there. I was also able to provoke this behavior from ab running against the Tornado server – which is perfectly sensible if this explanation is correct, since it's primarily do to something the platform TCP stack is doing, not something either Twisted or Tornado is doing.

I haven't dug into this so deeply that I'm entirely confident that this completely explains the behavior, but I think it's a pretty good start. A direction for further investigation would be to write a client like ab but which reports more identifying information about each connection so that the failing connections can be traced through the entire network.

One thing I'm not sure about is whether OS X uses syn cookies. Some web pages I've found with Google suggest that it does, but it would be nice to get the information from a more authoritative/reliable source.

]]> By: Tofu http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-52 Tofu Sun, 13 Sep 2009 12:42:27 +0000 http://www.apparatusproject.org/blog/?p=342#comment-52 I didnt notice anything differnt and I thought that was odd too. I meant to run it again a few more times, but I figured I got the information that I wanted. That performance was not an issue between twisted and tornado. <br><br>BTW, Dustin has started work on tornado with twisted support. <a href="http://github.com/dustin/tornado/tree/master" rel="nofollow">http://github.com/dustin/tornado/tree/master</a> I didnt notice anything differnt and I thought that was odd too. I meant to run it again a few more times, but I figured I got the information that I wanted. That performance was not an issue between twisted and tornado.

BTW, Dustin has started work on tornado with twisted support. http://github.com/dustin/tornado/tree/master

]]> By: Arek http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-51 Arek Sat, 12 Sep 2009 23:42:37 +0000 http://www.apparatusproject.org/blog/?p=342#comment-51 How did your test for 200 concurrent users come out: Twisted ~720 , Tornado ~430 . Then both hover around 700-800 requests per second for 100 and 50 concurrent users.<br><br>That major difference during 200 simultaneous conns seems off . I did not see that happen on my machine. Is there anything you noticed during this test ? How did your test for 200 concurrent users come out: Twisted ~720 , Tornado ~430 . Then both hover around 700-800 requests per second for 100 and 50 concurrent users.

That major difference during 200 simultaneous conns seems off . I did not see that happen on my machine. Is there anything you noticed during this test ?

]]> By: dkoepke http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-50 dkoepke Sat, 12 Sep 2009 17:38:14 +0000 http://www.apparatusproject.org/blog/?p=342#comment-50 There's a fast path for locally-directed packets. Matt's test, like finiteloop's, performed ab on a remote host. This is probably the difference you're seeing. There's a fast path for locally-directed packets. Matt's test, like finiteloop's, performed ab on a remote host. This is probably the difference you're seeing.

]]> By: roder http://www.apparatusproject.org/blog/2009/09/twisted-web-vs-tornado-performance-test/comment-page-1/#comment-49 roder Sat, 12 Sep 2009 13:31:50 +0000 http://www.apparatusproject.org/blog/?p=342#comment-49 I'll try that again with httperf and let you know. Good response btw. I'll try that again with httperf and let you know. Good response btw.

]]>