Update of /cvsroot/curl/curl-www/libcurl/hiper
In directory labb:/tmp/cvs-serv21943
Modified Files:
_index.html _menu.html _schedule.html
Added Files:
_roadmap.html
Log Message:
add info
Index: _menu.html
===================================================================
RCS file: /cvsroot/curl/curl-www/libcurl/hiper/_menu.html,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -d -r1.1 -r1.2
--- _menu.html 3 Nov 2005 09:49:10 -0000 1.1
+++ _menu.html 3 Nov 2005 10:02:38 -0000 1.2
@@ -41,6 +41,12 @@
VLINK("/libcurl/hiper/schedule.html", schedule)
#endif
+#ifdef HIPER_ROADMAP
+LINK("/libcurl/hiper/roadmap.html", roadmap)
+#else
+VLINK("/libcurl/hiper/roadmap.html", roadmap)
+#endif
+
</div>
<p>
--- NEW FILE: _roadmap.html ---
#include "_doctype.html"
<html>
<head> <title>hiper - roadmap</title>
#include "css.t"
</head>
#define LIBCURL_HIPER
#define HIPER_ROADMAP
#define CURL_URL libcurl/hiper/roadmap.html
#include "_menu.html"
#include "setup.t"
WHERE3(libcurl, "/libcurl/", hiper, "/libcurl/hiper/", hiper roadmap)
<a name=top>
TITLE(Project Hiper Roadmap)
<div class="relatedbox">
<b>Related:</b>
<br><a href="schedule.html">schedule</a>
</div>
<p>
How we intend/hope this project to proceed:
SUBTITLE(1. Measure and Benchmark Existing API)
<p>
<ol>
<li> gather _many_ unique existing URLs (a lot more than 10,000)
<p>
<ul>
<li> mostly to unique hosts, but not necessarily all unique. For the sake of
comparing with a future pipelining version, the test script should be
able to ask for the same document Y times, at least in a later stage.
<li> Write up a curl-using script and use these services:<br>
http://randomurl.com/body.php<br>
http://random.yahoo.com/fast/ryl<br>
http://www.uroulette.com/visit
<li> Store the tens of thousands of random URLs in a text file
</ul>
<li> Write up a multi interface using program that extracts N random URLs from
the list and downloads them simultaneously.
<p>
The random seed and N must be able to be specified to be able to repeat the
exact same set in a subsequent invoke, but in general testing we must vary
the seed in order to not exhaust the same hosts.
<p>
libcurl should most likely be built with c-ares support.
<p>
Use debug builds to be able to generated memory-trace logs to fully track
and check amount of memory used per connection.
<p>
Compare the memory usage measurements with the amount of memory installed
in the development machines so that we remain testing within the amount of
available system RAM.
<li> Measure time from select() returning to it being called again. Run
multiple times - do many measurements.
</ol>
SUBTITLE(Implement the curl_multi_socket API)
<p>
- Port the test program from phase 1 to the new API.
<p>
- Run measurements and benchmarks
SUBTITLE(3. Implement HTTP pipelining support)
<p>
Make sure that:
<ul>
<li> the test program enables pipelining
<li> the test program talks to a fair amount of servers that support pipelining
<li> a fair amount of documents are fetched from the same servers so that
pipelining actually can get activated
</ul>
<p>
To make benchmarks, identify high-latency high-bandwith servers that allow
pipelining to get a feel for "optimal" performance boosts.
#include "_footer.html"
</BODY>
</HTML>
Index: _index.html
===================================================================
RCS file: /cvsroot/curl/curl-www/libcurl/hiper/_index.html,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -d -r1.2 -r1.3
--- _index.html 3 Nov 2005 09:48:56 -0000 1.2
+++ _index.html 3 Nov 2005 10:02:38 -0000 1.3
@@ -15,6 +15,43 @@
<a name=top>
TITLE(High Performance libcurl)
+<p>
+ Hiper is the name of the sub-project that intends to bring high performance
+ adjustments and additions to the libcurl multi interface.
+<p>
+ The aim is to 1) provide a better API for _extremely_ large amounts of
+ simultaneous transfers (the c10k problem) and 2) introduce HTTP pipelining
+ support. By better API, we mean both better suited to deal with the amount
+ of connections (i.e no artificial limits like select() imposes etc), better
+ performance-wise by avoiding expensive looping over all file descriptors to
+ check for actions and to allow users to pick an underlying event system of
+ their own choice.
+<p>
+SUBTITLE(Schedule)
+<p>
+ Daniel intends to work more or less full-time with the Hiper project during
+ December 2005. Leftovers will be done part-time in 2006 with possibly some
+ further full-time periods during spring 2006.
+<p>
+ I'll get back with more specific (release) dates later on.
+
+SUBTITLE(Funding)
+<p>
+ Daniel receives funding from the Swedish foundation IIS for the purpose of
+ implementing this.
+
+SUBTITLE(Project Involvement)
+<p>
+ The plan is to keep the process and progress as open and public as I
+ possibly can, to allow anyone and everyone who feels like contributing or
+ just watching to do so. This is still curl, this is still open source and I
+ still value and appreciate all user feedback and comments.
+
+SUBTITLE(Source Code Repository)
+<p>
+ For the sake of being able to be 100% public and open, I will create a
+ branch in the CVS repository so that the Hiper experiments and developments
+ won't interfere with the "normal" libcurl development.
#include "_footer.html"
Index: _schedule.html
===================================================================
RCS file: /cvsroot/curl/curl-www/libcurl/hiper/_schedule.html,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -d -r1.1 -r1.2
--- _schedule.html 3 Nov 2005 09:48:56 -0000 1.1
+++ _schedule.html 3 Nov 2005 10:02:38 -0000 1.2
@@ -14,7 +14,17 @@
WHERE3(libcurl, "/libcurl/", hiper, "/libcurl/hiper/", hiper schedule)
<a name=top>
-TITLE(Project Hiper Schedule)
+TITLE(Project Hiper Schedule and Dates)
+<div class="relatedbox">
+<b>Related:</b>
+<br><a href="roadmap.html">roadmap</a>
+</div>
+<p>
+ Oct 24, 2005: Daniel visits the "Internetdagarna" conference in Stockholm,
+ Sweden and receives a diploma, a flower and some sturdy handshakes when the
+ <a href="http://www.iis.se/">IIS</a> foundation announced that Daniel will
+ receive 150,000 SEK from their fund. Daniel was notified about their decision
+ roughly one week before this.
#include "_footer.html"
lmpx.com only provides a reader for public news (NNTP) servers. It is not
affiliated with the servers or forums shown here and is not responsible for
the content of articles, which is written by their respective authors.