21 messages in org.apache.httpd.devRe: Is async the answer
FromSent OnAttachments
Akins, BrianJan 18, 2008 10:51 am 
Justin ErenkrantzJan 18, 2008 11:16 am 
Colm MacCarthaighJan 18, 2008 11:20 am 
Akins, BrianJan 18, 2008 11:26 am 
Akins, BrianJan 18, 2008 11:30 am 
Colm MacCarthaighJan 18, 2008 12:07 pm 
Akins, BrianJan 18, 2008 1:16 pm 
Colm MacCarthaighJan 18, 2008 1:28 pm 
Ruediger PluemJan 18, 2008 2:30 pm 
Justin ErenkrantzJan 18, 2008 4:33 pm 
Niklas EdmundssonJan 19, 2008 3:53 am 
Graham LeggettJan 19, 2008 4:45 am 
Davi ArnautJan 19, 2008 6:57 am 
Jim JagielskiJan 19, 2008 7:04 am 
Graham LeggettJan 19, 2008 8:01 am 
Henrik NordströmJan 19, 2008 1:14 pm 
Henrik NordströmJan 19, 2008 1:19 pm 
Davi ArnautJan 19, 2008 3:29 pm 
Graham LeggettJan 20, 2008 7:44 am 
Akins, BrianJan 22, 2008 10:03 am 
Akins, BrianJan 22, 2008 10:07 am 
Actions with this message:
Paste this link in email or IM:
Paste this link in email or IM:
Atom feed for this thread
Paste this URL into your reader:
Subject:Re: Is async the answerActions...
From:Davi Arnaut (da@apache.org)
Date:Jan 19, 2008 3:29:05 pm
List:org.apache.httpd.dev

Graham Leggett wrote:

Davi Arnaut wrote:

The proxy that the LiveJournal folks wrote, I think, copies all the data from the origin server into a file and then uses sendfile to send to the client...

Doesn't this limit the network bandwidth to the bandwidth of the disk and/or file system?

Yes, and the effective bandwidth of the disk can be significantly higher than both the cache backend (which is often expensive) and the network frontend (which has slow potential slow clients typing up your resources).

Don't forget that your cache disk is most often RAM backed, meaning effectively your cache disk is a ramdisk, with all the speed advantages that go with it.

This is true for expensive hardware and very well designed operating systems and file systems.. and the space is not infinite.

But... OK. Back to the topic I thought that one of the key points of async/event based servers were that we use software to scale and not hardware (so that hardware is not the bottleneck)... like serving thousands of slow clients from commodity hardware.