# No performance improvement on nginx reverse-proxy **URL:** \ **Category:** NGINX\ **Created:** [October 13, 2010, 6:34am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351 "2010-10-13T06:34:29Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![okkezSS](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/o/85f322/32.png) [@okkezSS](https://www.ruby-forum.com/u/okkezSS)\ **Post date:** [October 13, 2010, 6:34am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351/1 "2010-10-13T06:34:29Z")
Hello, This day I did a simpe test with nginx’s reverse-proxy. The environment is on a vmware virtual host. OS: slackware Linux, kernel 2.6.24.5-smp CPU: Intel(R) Celeron(R) CPU 723 @ 1.20GHz MEM: 350M The application environment: nginx version: nginx/0.8.52 apache version: Apache/2.2.15 (Unix) mysql version: 5.1.51 The performance/capability arguments for nginx/apache are: [nginx] worker\_processes 8; events { worker\_connections 1024; } [apache] StartServers 5 MinSpareServers 5 MaxSpareServers 10 MaxClients 150 MaxRequestsPerChild 0 Apache run with two vhosts, one is listening on 8080 port, another is listening on 8081 port. The vhost config shown as below: \ DocumentRoot “/usr/local/apache2.2/vhost/vh1” ScriptAlias /cgi/ “/usr/local/apache2.2/vhost/vh1/cgi/” \ DocumentRoot “/usr/local/apache2.2/vhost/vh2” ScriptAlias /cgi/ “/usr/local/apache2.2/vhost/vh2/cgi/” There are two cgi scripts on the cgi dirs above. one is /usr/local/apache2.2/vhost/vh1/cgi/test.cgi another is /usr/local/apache2.2/vhost/vh2/cgi/test.cgi Their content is do the same. It’s a simple perl script which fetches a record by random from a table which has 150,000 records totally. [the script content is pasted on the last of this message.] Nginx is setup for the reverse-proxy to the two vhosts of apache. The config piece shown as: ``` upstream MyTestServ { server 127.0.0.1:8081; server 127.0.0.1:8080; } server { server_name my.test.com; listen 80; location / { proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_pass http://MyTestServ; } } ``` After all that done, I tested it with http\_load (a tool from [http\_load](http://www.acme.com/software/http_load/)). ./http\_load -parallel 15 -seconds 30 urls This test nginx for rever-proxy, the url is like: [http://192.168.0.77/cgi/test.cgi](http://192.168.0.77/cgi/test.cgi) ./http\_load -parallel 15 -seconds 30 urls1 This test apache directly, the url is like: [http://192.168.0.77:8080/cgi/test.cgi](http://192.168.0.77:8080/cgi/test.cgi) After testing for some times (have been changing the arugments for http\_load), I found nginx with reverse-proxy is not better than the realserver. Even the result is worse for accessing nginx than access apache directly. The result with nginx reverse-proxy: 191 fetches, 15 max parallel, 9782 bytes, in 30 seconds 51.2147 mean bytes/connection 6.36667 fetches/sec, 326.067 bytes/sec msecs/connect: 1.23155 mean, 3.663 max, 0.648 min msecs/first-response: 2250.49 mean, 5026.69 max, 576.448 min 90 bad byte counts HTTP response codes: code 200 – 191 The result with NO reverse-proxy: 196 fetches, 15 max parallel, 10030 bytes, in 30.0005 seconds 51.1735 mean bytes/connection 6.53322 fetches/sec, 334.327 bytes/sec msecs/connect: 1.35084 mean, 6.877 max, 0.797 min msecs/first-response: 2103.1 mean, 4348.94 max, 535.809 min 84 bad byte counts HTTP response codes: code 200 – 196 So how do you think about it? Suggestions are welcome. Thanks. **END** This is the CGI script for testing: #!/usr/bin/perl use strict; use CGI; use DBI; my $q=CGI-\>new; print $q-\>header(“text/plain”); my $dsn = “DBI:mysql:database=pyh;host=127.0.0.1;port=3306”; my $dbh = DBI-\>connect($dsn, ‘root’, ‘’); my $id = 10026 + int(rand(150000)); my $str = “select \* from myt2 where id = $id”; my $sth = $dbh-\>prepare($str); $sth-\>execute; my @array = $sth-\>fetchrow\_array; $sth-\>finish; $dbh-\>disconnect; print “@array\n”; ---
**Author:** ![yung](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/y/edb3f5/32.png) [@yung](https://www.ruby-forum.com/u/yung)\ **Post date:** [October 13, 2010, 8:13am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351/2 "2010-10-13T08:13:07Z")
On Wed, 2010-10-13 at 12:33 +0800, yung wrote: > After testing for some times (have been changing the arugments for > http\_load), I found nginx with reverse-proxy is not better than the > realserver. > Even the result is worse for accessing nginx than access apache directly. > So how do you think about it? > Suggestions are welcome. Thanks. If you use a Ferrari to tow a dump truck, you will find that the dump truck actually goes slightly faster on its own. In short, there are so many bottlenecks in your test setup (Apache, CGI, database) that the speed differences you see are probably not even statistically significant. Further, it’s not clear at all why you think adding additional layers of processing (a proxy) to your stack would somehow magically speed things up. _Of course_ it will be slower. How could you ever expect anything different? The typical use-case of Nginx in front of Apache is to allow Nginx to serve static resources to take the load away from Apache. You could also use some of Nginx’ caching features to take load off Apache. You did none of these things. I think you need to think harder about what you are testing. Regards, Cliff ---
**Author:** ![yung](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/y/edb3f5/32.png) [@yung](https://www.ruby-forum.com/u/yung)\ **Post date:** [October 13, 2010, 8:18am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351/3 "2010-10-13T08:18:44Z")
On Wed, Oct 13, 2010 at 12:33:17PM +0800, yung wrote: > The application environment: > worker\_processes 8; > MaxClients 150 > DocumentRoot “/usr/local/apache2.2/vhost/vh1” > one is /usr/local/apache2.2/vhost/vh1/cgi/test.cgi > > ``` > proxy_set_header Host $host; > > ``` > > 51.2147 mean bytes/connection > 196 fetches, 15 max parallel, 10030 bytes, in 30.0005 seconds > Suggestions are welcome. Thanks. > nginx is not a magic wand, it’s just a reverse proxy. > It can help if a bottleneck is a slow client. > In your case bottlenecks are CGI script launches and database queries, > so nginx adds only an overhead as you have seen: 6.5 req/s vs 6.3 req/s. > print $q-\>header(“text/plain”); > my @array = $sth-\>fetchrow\_array; > $sth-\>finish; > $dbh-\>disconnect; > > print “@array\n”; – Igor S. > **[Igor Sysoev](http://sysoev.ru/en/)** ---
**Author:** ![yung](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/y/edb3f5/32.png) [@yung](https://www.ruby-forum.com/u/yung)\ **Post date:** [October 13, 2010, 8:19am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351/4 "2010-10-13T08:19:22Z")
The only time you will see a performance increase from nginx as a reverse proxy is when you need features that apache does badly like keep alive. ---
**Author:** ![yung](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/y/edb3f5/32.png) [@yung](https://www.ruby-forum.com/u/yung)\ **Post date:** [October 13, 2010, 8:28am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351/5 "2010-10-13T08:28:47Z")
On Wed, Oct 13, 2010 at 05:18:14PM +1100, SplitIce wrote: > The only time you will see a performance increase from nginx as a reverse > proxy is when you need features that apache does badly like keep alive. Not only keep alive - just long enough download, even 1 second: if an Apache process creates response in 50ms, there is no sense to keep the huge process bound to a slow client for 1s, because the process can create resposnes for 20 clients for this second. > > > Suggestions are welcome. Thanks. > > > up. _Of course_ it will be slower. How could you ever expect > > > anything different? The typical use-case of Nginx in front of Apache > > > is to allow Nginx to serve static resources to take the load away from > > > Apache. You could also use some of Nginx’ caching features to take > > > load off Apache. You did none of these things. I think you need to > > > think harder about what you are testing. – Igor S. > **[Igor Sysoev](http://sysoev.ru/en/)** ---
**Author:** ![yung](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/y/edb3f5/32.png) [@yung](https://www.ruby-forum.com/u/yung)\ **Post date:** [March 20, 2012, 4:30am UTC](https://www.ruby-forum.com/t/no-performance-improvement-on-nginx-reverse-proxy/197351/6 "2012-03-20T04:30:21Z")
Vg