There's been discussion in the open source world about a decline in the popularity of the dominant Apache web server. These concerned are fueled largely by the Netcraft survey of the internet, which shows a 20% decline in Apache's market share over the last three years, from a high near 70% to the 50% or so it enjoys today. But bearing in mind the old saw about lies and statistics, it's worth digging a bit more to see what these numbers mean.
Looking at Netcraft's figures more closely, it becomes apparent that this is more than an "Apache vs. IIS" battle. One significant change for the Apache numbers happened in mid-2007, when the 8 million or so Google-served sites started reporting themselves as "GFE" rather than Apache - even though GFE may well be a private fork of the Apache codebase. That's a significan chunk of the 158 million sites that Netcraft surveyed right there.
Although most of the rest of the Apache decline appears to correspond exactly to a rise in IIS, it's not clear how significant this is for the average personal or corporate site. For example, Microsoft picked up 5% of the market in one fell swoop in early 2006 when Go Daddy moved all of their millions of parked (i.e., not active by any sensible definition) domains from Apache servers to IIS. A win for Microsoft, to be sure, but not an indicator of any particular trend.
Web monitoring company Pingdom has recently looked at this issue from another angle: they asked which web servers run the most important sites, rather than just counting noses. By checking headers from the 100 most popular web sites (according to Alexa), they came up with a different set of numbers: 49% Apache, 20% IIS, 4% lighttpd, and 27% other/unknown. By that measure, Apache is still over twice as popular as IIS, despite Microsoft's relationships with the sort of enterprises that generally own the most popular sites.
There's another thing evident from the Pingdom statistics as well: the choice of web server software carries with it a good deal of inertia. Out of the 49 Apache sites, for example, there are still more announcing themselves as Apache 1.3 than Apache 2.0. On the IIS side of the house, IIS 6.0, and even 5.0, far outnumber the recently-released IIS 7.0.
I'd love to see Pingdom's numbers extended in two ways: covering a few more orders of magnitude (say, the top 10,000 sites) and resampled over time (the way that Netcraft works). I suspect that would tell us more about server use that really matters. Meanwhile, it doesn't look like Apache is in any danger of losing its dominance among the top dog sites any time soon.
Do you think Apache's dominance holds up across the top 10,000 sites?
Comments
Add CommentBy on Mar. 18, 2008
Well, whoever has the most market share of anything has the greatest potential to lose market share to someone else. They're whom you take share *from*. Apache with, by conservative estimates, half of the Web and a firm 1st place position seems pretty dominant to me.
I agree with you; I think we need more numbers. And that "other/unknown" category right now is beating IIS. ;) So what's in there, I wonder?
The other issue aside from market share is how happy people are with Apache. And the answer has been pretty overwhelmingly positive, I think, on the majority of the major sites.
By on Mar. 18, 2008
Whoops, didn't log in. Okay, I hearby take ownership of the previous comment. ;)
By on Mar. 18, 2008
I think that if you were able to get access to the data, Apache would still be the web server of choice for the top 10,000 sites. It can't be beat, esp. not by IIS, and will continue to dominate this space for the foreseeable future.
By on Mar. 19, 2008
you know, in some countries, like Vietnam for example, since most of the software are pirated, they only know of Windows, MS-Office, IIS and their number of web servers keep increasing.
Since the total number of web server increases (IIS), the percentage of Apache goes down.
By on Mar. 19, 2008
My Apache servers reports it's self as IIS 9.54 and not as Apache. My IIS server headers also mis-report the real server type. Sure I only have 30+ web servers in the farm, still it shows how the reporting by Netcraft or any such service can be less then accurate if they rely on http headers.
By on Mar. 19, 2008
Speaking from personal experience, Apache/IIS are just way too difficult to setup/maintain. I prefer lighttpd, for most applications. Easy to setup, easy to maintain, and (most importantly) easy to configure as a reverse proxy for my "real" application.
By on Mar. 19, 2008
Netcraft stats are totally unreliable and can be screwed easily:
http://blog.wpkg.org/2007/09/20/just-how-unreliable-is-netcraft/
By on Mar. 20, 2008
I run a couple dozen websites ranging from my personal site to medium sized eCommerce sites and almost all of them run on Apache because of it's price, stability, power, flexibility, and ease of use.
I have a couple that run on IIS because they required proprietary software that would only run on IIS. These give me more trouble than all my other websites combined.
I use lighttpd for a couple lightweight caching servers. I'd probably use more if I could find a hosting provider that offered lighttpd reverse proxy servers cheap and had really fast pipes. Would like to replace a LAMP-based cache server through 1&1. Mainly because 1&1's support staff is retarded but also because I think lighttpd would be a lil faster than Apache+PHP.
Share Your Comments
Trackback URL
http://ostatic.com/trackback/158627