Openchallenge 2|2003. Time to deadline: 68 days 22 hrs 52 mins

Home
About
Contact/jury
Winners archive
Support us
Sponsors
News

Challenge 3|2002
Challenges
Implementations
Submit: implementation
Submit: idea/concept
Rules


Nonprofits program

Links


Valid XHTML 1.0!


Analysis of a Slashdot effect /.

by Jussi Kallioniemi - jukal at openchallenge dot org.

From the Jargon Lexicon: slashdot effect n.

1. Also spelled "/. effect"; what is said to have happened when a website being virtually unreachable because too many people are hitting it after the site was mentioned in an interesting article on the popular Slashdot news service. The term is quite widely used by /. readers, including variants like "That site has been slashdotted again!" 2. In a perhaps inevitable generation, the term is being used to describe any similar effect from being listed on a popular site. This would better be described as a flash crowd. Differs from a DoS attack in being unintentional.

Forewords :: about this case

This analysis is based on the data gathered after the story 'Donating Time To Goodwill Projects?' was published at the Slashdot.org site on 24th October 2002 around 13:30 GMT -05:00 (US East coast time). What I wanted to find out is: what is the slashdot effect really like and what are the visitors like.

When reading this "analysis", keep in mind that atleast the following things that may have a significant effect to result: 1) The Openchallenge website has been designed with lightness in mind, there is not many images for example - basically one page is one request + a style sheet 2) Did the story interest people 3) Did the site interest people 4) What other stories were running at Slashdot at the same time 5) How was the openchallenge.org site linked from article 6)...n) many other things. However, I believe that this analysis will give you a hunch about the issue.

Openchallenge.org is absolutely currently not a high-volume site. Typically, there is around 20-30 pagerequests per a five minute period. To know how the server works under higher load, we run a little stress test on the site. The stress test involved executing 100 simultaneous recursive wgets to the site and running them for some minutes. The server survived this without significant change to average page serving time.

The not-so-fancy images shown here are the results of analyzing data with unix shell scripts, Analog and Webalizer. The final charts were crafted using ...Excel! :)

The Analysis

Now, based on this analysis - to avoid the slashdot effect, I should now ask: Do you want to read the rest?

Openchallenge.org, 2002 Feedback