Update of /cvsroot/curl/curl-www/libcurl/hiper
In directory labb:/tmp/cvs-serv28793
Modified Files:
_schedule.html
Added Files:
bench.jpg
Log Message:
added more blurb about what I'll do next
--- NEW FILE: bench.jpg ---
(This appears to be a binary file; contents omitted.)
Index: _schedule.html
===================================================================
RCS file: /cvsroot/curl/curl-www/libcurl/hiper/_schedule.html,v
retrieving revision 1.9
retrieving revision 1.10
diff -u -d -r1.9 -r1.10
--- _schedule.html 6 Dec 2005 10:26:34 -0000 1.9
+++ _schedule.html 6 Dec 2005 11:18:28 -0000 1.10
@@ -20,8 +20,7 @@
<br><a href="roadmap.html">Roadmap</a>
</div>
-#define MARKDATE(x) <td nowrap><span class="whodate"> x </span></td><td>
-#define START <tr valign="top">
+#define MARKDATE(x) <tr valign="top"><td nowrap><span class="whodate"> x </span></td><td>
#define STOP </td></tr>
<p>
@@ -33,9 +32,24 @@
<table class="news">
-START
+ MARKDATE(Dec 6 2005) Ok, I think I'll change my measuring approach and I will
+ instead write up my own HTTP server and control that to allow it to either
+ site perfectly quite (just keeping the connection alive) or to send an
+ endless stream of data. By allowing the selection of behaviour be based on
+ the URL, I should be able to modify my test program to run and test a given
+ number of "active" connections with a given number of "existing connections".
+ I guess the real-world URLs are too hard to use to make adequate tests with.
+<p>
+ I found this little benchmark on select() performace compared to other event
+ systems:
+ <br>
+ <a href="http://monkey.org/~provos/libevent/libevent-benchmark.jpg"><img border="0" src="bench.jpg" alt="graph comparing event systems' performances"></a>
+<p>
- MARKDATE(Dec 6 2005) Been struggling to get a test program that can be used
+STOP
+
+ MARKDATE(Dec 6 2005)
+ Been struggling to get a test program that can be used
to measure and show the current overhead/speed in a good way. I've been quite
surprised by the speed of the existing implementation. My test application
easily initiates and transfers 2000 simultaneous transfers (and man does this
@@ -101,8 +115,6 @@
STOP
-START
-
MARKDATE(Dec 2 2005) Made a script that figuered out a few thousand "random"
URLs.<p>Started writing a test application using the existing multi
interface. It fetches N simultaneous URLs and measures how long time is spent
@@ -117,39 +129,32 @@
STOP
-START
MARKDATE(Dec 1 2005) Daniel started working full-time on project Hiper (during
the entire month of December).
STOP
-START
MARKDATE(Nov 29 2005) Mailed the <a href="kvartalsrapport1.pdf">first
quarterly report in Swedish</a> to IIS, about project Hiper. (282KB PDF)
STOP
-START
MARKDATE(Nov 28 2005) Discussing how the "zero copy" interface for
libcurl could work. On the <a href="http://curl.haxx.se/mail/list.cgi?list=curl-library">curl-library</a> mailing list.
STOP
-START
MARKDATE(Nov 9 2005) Discussing possible Windows-adjustments to the hiper
concept on the <a href="http://curl.haxx.se/mail/list.cgi?list=curl-library">curl-library</a> mailing list.
STOP
-START
MARKDATE(Nov 4 2005) Added the <a href="api.html">API</a> and <a
href="app.html">Sample app</a> pages here.
STOP
-START
MARKDATE(Nov 3 2005) announced the 'hiper' project to the world, and added
this hiper section of the curl web site.
STOP
-START
MARKDATE(Oct 24 2005) Daniel visited 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
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.