なぜNGINXを使うのか？¶
幾つかのベンチマークでNGINXが他の軽量webサーバとプロキシに辛勝し、軽量ではないものは踏みつけることを示しました。
Some people say those benchmarks weren’t valid because the competition wasn’t tuned this way or that, etc. I tend to agree that benchmarks only tell part of the story and that there’s little you can do to truly remove bias from them anyway. (誰か、誰もが平等だと同意するベンチマークを見たことがありますか？私はありません。)
Anyway, instead of links to benchmarks for people to argue over (you can use Google to find them yourself if you like), what follows is quotes from people using NGINX in the real world, under real load, serving real applications and websites.
Please feel free to add your own testimonial, but see the Notes at the bottom of this page before you do.
引用¶
Several of the companies we invested in were able to solve significant scaling issues by switching their web platforms to NGINX. NGINXは今日のインターネット上の最も大きなサイトの成長を透過的にそして効果的に可能にします。
– Thomas Gieselmann, BV Capital
My advice to anyone running a web site today who is hitting performance constraints is to investigate whether they can use NGINX. CloudFlare has been able to scale over the last year to handle more than 15 billion monthly page views with a relatively modest infrastructure, in large part because of the scalability of NGINX. Our experience shows that switching to NGINX enables full utilization of the modern operating system and existing hardware resources.
– Matthew Prince, co-founder and CEO of CloudFlare
Both servers [Apache and NGINX] are capable of serving a huge number of requests per second, but Apache’s performance start decreasing as you add more concurrent connections whereas NGINX’s performance almost doesn’t drop! But here comes the best bit: because NGINX is event-based it doesn’t need to spawn new processes or threads for each request, so its memory usage is very low. Throughout my benchmark it just sat at 2.5MB of memory while Apache was using a lot more.
I ran a simple test against NGINX v0.5.22 and Apache v2.2.8 using ab (Apache’s benchmarking tool). During the tests, I monitored the system with vmstat and top. The results indicate that NGINX outperforms Apache when serving static content. Both servers performed best with a concurrency of 100. Apache used four worker processes (threaded mode), 30% CPU and 17MB of memory to serve 6,500 requests per second. NGINX used one worker, 15% CPU and 1MB of memory to serve 11,500 requests per second.
Apache is like Microsoft Word, it has a million options but you only need six. NGINX does those six things, and it does five of them 50 times faster than Apache.
I currently have NGINX doing reverse proxy of over tens of millions of HTTP requests per day (that’s a few hundred per second) on a single server. At peak load it uses about 15MB RAM and 10% CPU on my particular configuration (FreeBSD 6). Under the same kind of load, Apache falls over (after using 1000 or so processes and god knows how much RAM), Pound falls over (too many threads, and using 400MB+ of RAM for all the thread stacks), and Lighty leaks more than 20MB per hour (and uses more CPU, but not significantly more).
– Bob Ippolito in the TurboGears mailing list, 2006-08-24
We are currently using NGINX 0.6.29 with the upstream hash module which gives us the static hashing we need to proxy to Varnish. We are regularly serving about 8-9k requests/second and about 1.2Gbit/sec through a few NGINX instances and have plenty of room to grow!
...we are using NGINX as a primary software for free hosting platforms. I have developed specific modules for banner inserting and stats calculation in NGINX and now our central server can handle about 150-200Mbit/s of highly fragmented http-traffic (all files are small). I think, this is really good result because with any possible tunings of Apache on the same servers we were not able to handle even 60-80Mbit/s.
A while back, we changed our frontend IMAP/POP proxy from perdition to NGINX... [and] we’ve now switched over to using NGINX for our frontend web proxy as well... The net result of all this is that each frontend proxy server currently maintains over 10,000 simultaneous IMAP, POP, Web & SMTP connections (including many SSL ones) using only about 10% of the available CPU.
We recently switched over our static content webserver over to NGINX, easily the most impressive webserver I’ve seen in years. We’re running it on a machine with 8Gb of memory (along with some other stuff), but the NGINX process is only using a ridiculously small 1.4Mb. In other words, it barely registers in any measurable way.
We’ve replaced our Squid (reverse proxy) + Apache setup with NGINX, and load average as well as CPU usage have been reduced by half. In addition to that our benchmarks show that the new setup can handle about two to three times as many requests per second (RPS) as the old setup.
We’ve done some benchmarks for CMS systems such as Wordpress, Drupal, Joomla, TYPO3, etc., and the result is that NGINX delivers pages up to 50% faster than Apache. At the same time NGINX can handle up to 177% as many requests per second (RPS) as Apache.
注意¶
Please feel free to add your own testimonial, but we prefer that it refer to a high traffic site or a site that NGINX somehow provided a unique solution for. Also, if numbers (server utilization, network throughput, simultaneous connections, etc) and/or an actual link to the site being discussed can be provided it makes it much more relevant for people curious about NGINX.