I see that Brian McCallister did some benchmarks recently, showing Apache, Mongrel, Jetty and TwisteWeb: http://kasparov.skife.org/blog/src/ruby/silly-micro-benchmarks.html Regards, Dan This communication is the property of Qwest and may contain confidential or privileged information. Unauthorized use of this communication is strictly prohibited and may be unlawful. If you have received this communication in error, please immediately notify the sender by reply e-mail and destroy all copies of the communication and any attachments.
On 8.2.2007, at 23.22, Zed A. Shaw wrote:> What do I get from Brian? Whining and complaining that there''s no > keep-alives or pipelining and the only "proof" he offers for their > requirement is a single sentence at the bottom of a page full of > randomness.At least he self admits the benchmarks were useless :-/ //jarkko -- Jarkko Laine http://jlaine.net http://dotherightthing.com http://www.railsecommerce.com http://odesign.fi -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2417 bytes Desc: not available Url : http://rubyforge.org/pipermail/mongrel-users/attachments/20070208/bf958814/attachment.bin
On Thu, 8 Feb 2007 10:56:14 -0600 "Berger, Daniel" <Daniel.Berger at qwest.com> wrote:> I see that Brian McCallister did some benchmarks recently, showing > Apache, Mongrel, Jetty and TwisteWeb: > > http://kasparov.skife.org/blog/src/ruby/silly-micro-benchmarks.html*Sigh*, yeah those are really informative. Why do people do crap like this? You don''t see me over on the stomp list bitching about it''s dumbass requirement that it be accessible via telnet. You don''t see me whining about stomp using a shit framing mechanism or copying all the worst parts of HTTP over. In fact, I wrote a damn parser for Stomp with Ragel and gave it to Brian. Twice. What do I get from Brian? Whining and complaining that there''s no keep-alives or pipelining and the only "proof" he offers for their requirement is a single sentence at the bottom of a page full of randomness. -- Zed A. Shaw, MUDCRAP-CE Master Black Belt Sifu http://www.zedshaw.com/ http://www.awprofessional.com/title/0321483502 -- The Mongrel Book http://mongrel.rubyforge.org/ http://www.lingr.com/room/3yXhqKbfPy8 -- Come get help.
On 2/8/07, Jarkko Laine <jarkko at jlaine.net> wrote:> > On 8.2.2007, at 23.22, Zed A. Shaw wrote: > > What do I get from Brian? Whining and complaining that there''s no > > keep-alives or pipelining and the only "proof" he offers for their > > requirement is a single sentence at the bottom of a page full of > > randomness. > > At least he self admits the benchmarks were useless :-/ > > //jarkkoYeah, I also understand Zed''s frustration. These are the kind of things that get picked up on /. or digg on a slow day and, well...you know what happens then. Pat -------------- next part -------------- An HTML attachment was scrubbed... URL: http://rubyforge.org/pipermail/mongrel-users/attachments/20070208/b203fe5e/attachment.html
Op 8-feb-2007, om 22:22 heeft Zed A. Shaw het volgende geschreven:> Why do people do crap like this? You don''t see me over on the stomp > list bitching about it''s dumbass requirement that it be accessible via > telnet. You don''t see me whining about stomp using a shit framing > mechanism or copying all the worst parts of HTTP over.Well some people just like to hear themselves talk. The actual words really don''t matter, it''s more the sound their lips make. It''s soothing I guess. The voices inside, yes? It makes them stop. J. -- www.gomagazine.nl +31643904460 pobox 51059 nl-1007eb amsterdam -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2423 bytes Desc: not available Url : http://rubyforge.org/pipermail/mongrel-users/attachments/20070208/0dbaab3a/attachment-0001.bin
On 2/8/07, Jarkko Laine <jarkko at jlaine.net> wrote: <snip>>Yeah, I also understand Zed''s frustration. These are the kind ofthings that get picked up on /. or digg on a slow day >and, well...you know what happens then. Yes. You have to suffer through the following comments: * In Soviet Russia, Mongrel benchmarks run YOU! * Imagine a Beowulf cluster running Mongrel! * Yes, but does Mongrel run Linux? * Random goats.ex links * Netcraft confirms, Mongrel is dying. * All your Mongrel are belong to us! * In Korea, only old people run Mongrel. * I, for one, welcome our new Mongrelian Overlords. And, last but not least: 1) Install Mongrel 2) Run hundreds of Mongrel instances 3) ??? 4) Profit!!! Regards, Dan This communication is the property of Qwest and may contain confidential or privileged information. Unauthorized use of this communication is strictly prohibited and may be unlawful. If you have received this communication in error, please immediately notify the sender by reply e-mail and destroy all copies of the communication and any attachments.
You forgot one: the form response. Other than that: LOL! You are advocating a [ ] multi threaded webserver [ ] multiprocess webserver [ ] event driven webserver [ ] single-process webserver [ ] combination of the above It won''t scale because [ ] there is not enough ram [ ] you will run out of file descriptors [ ] it cannot access a shared memory store [ ] it''s too slow [ ] people won''t use it [ ] it''s too expensive [ ] you are not teh leet etc... Op 8-feb-2007, om 23:39 heeft Berger, Daniel het volgende geschreven:> On 2/8/07, Jarkko Laine <jarkko at jlaine.net> wrote: > > <snip> > >> Yeah, I also understand Zed''s frustration. These are the kind of > things that get picked up on /. or digg on a slow day >and, well...you > know what happens then. > > Yes. You have to suffer through the following comments: > > * In Soviet Russia, Mongrel benchmarks run YOU! > * Imagine a Beowulf cluster running Mongrel! > * Yes, but does Mongrel run Linux? > * Random goats.ex links > * Netcraft confirms, Mongrel is dying. > * All your Mongrel are belong to us! > * In Korea, only old people run Mongrel. > * I, for one, welcome our new Mongrelian Overlords. > > And, last but not least: > > 1) Install Mongrel > 2) Run hundreds of Mongrel instances > 3) ??? > 4) Profit!!! > > Regards, > > Dan > > > This communication is the property of Qwest and may contain > confidential or > privileged information. Unauthorized use of this communication is > strictly > prohibited and may be unlawful. If you have received this > communication > in error, please immediately notify the sender by reply e-mail and > destroy > all copies of the communication and any attachments. > _______________________________________________ > Mongrel-users mailing list > Mongrel-users at rubyforge.org > http://rubyforge.org/mailman/listinfo/mongrel-users-- www.gomagazine.nl +31643904460 pobox 51059 nl-1007eb amsterdam -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2423 bytes Desc: not available Url : http://rubyforge.org/pipermail/mongrel-users/attachments/20070208/d9c65731/attachment.bin
Philip Hallstrom
2007-Feb-08 23:17 UTC
[Mongrel] Informal benchmarks - apache, mongrel, etc
>> Yeah, I also understand Zed''s frustration. These are the kind of > things that get picked up on /. or digg on a slow day >and, well...you > know what happens then. > > Yes. You have to suffer through the following comments: > > * In Soviet Russia, Mongrel benchmarks run YOU! > * Imagine a Beowulf cluster running Mongrel! > * Yes, but does Mongrel run Linux? > * Random goats.ex links > * Netcraft confirms, Mongrel is dying. > * All your Mongrel are belong to us! > * In Korea, only old people run Mongrel. > * I, for one, welcome our new Mongrelian Overlords. > > And, last but not least: > > 1) Install Mongrel > 2) Run hundreds of Mongrel instances > 3) ??? > 4) Profit!!!I only wish you had a typo or other error in your message so we could round out the selection of posts with a thourough grammatical lashing! Followed by several more posts pointing out every error in this post. Followed by several more telling all of us to get a life. Otherwise I think you just about nailed it :)