What is VDS?

ISPmanager control panel

Documentation

Software packages for VDS

FAQ

>> How to choose a package to meet your needs

Taking the time to select the best software package for your company does take some effort. Nevertheless, it takes even more effort to recover from the wasted time and energy resulting from hastily picking the wrong package. During your evaluation process, always ask yourself, "How does this package benefit me and help achieve my objectives?" Choose the right package for your business—the package that does indeed meet all of your needs and provides you with the greatest benefits.

We tested our servers performance and compared different VPS accounts to one another and against a baseline for completing this guideline. The information provided in this page detail the features available and thus guides our customers in selecting a VPS plan most suitable to them.

The utilities sysbench and ab were used to test, measure and evaluate the performance of MySQL database server and Apache web-server.

The maximum number of requests Apache and MySQL processed per sec is displayed in the Table 1.

Table 1

All tests were run using the utilities SysBench and Ab. SysBench measures execution times for all processed requests (SELECT and INSERT lines, check simple.html and simple.php files content) to display the folowing statistical information:

The Table 2 shows VPS prformance by processor CPU speed.

Table 2 (RAM 96 MB)

Processor speed	300Mhz	400Mhz	500Mhz	600Mhz	700Mhz
MySQL	754	983	1568	1880	2516
simple.html	403,06	663,57	899,28	1116,07	1388,89
simple.php	126,92	188,36	309,5	202	398,25
Nginx. Processing of simple.html	1182	1818	2036	2506	2777

It's not enough to write the fastest Web applications imaginable and develop the most efficient architecture to host them. In a real-world situation, a Web site also should be tested to see just how fast those applications perform. It's also nice to know just where the architecture might break down under heavy load. A good start to performance testing comes from simply acknowledging that performance is a factor that can be measured and compared against real-world situations. After this idea is firmly in place, it's possible to design a series of repeatable tests that produce results that can be used to predict the future performance of the site under any condition.

Let's take a web-site where a PHP script uses 20 database queries, displays 10 static pictures. The page is generated within 10 seconds, the site maintains 10 user-sessions simultaneously.

The below formula was used in our tests for calculating an average web server response time

VDS-Racoon plan (see Table 1)
MySQL query execution time = 0,00103 sec (963 queries per sec).
Web-server query execution time =0,00178 sec (561 queries per sec).
PHP script execution time = 0,00729 sec (137 queries per sec).

Let's take another example. A web page written in php with 20 static pictures submits 15 SQL queries.

To estimate the execution time, totalize time consumption of MySQL and Apache services

0,00729 + 20*0,00178 + 15*0,00103 = 0,05834 sec

VDS-Mustang
MySQL query execution time = 0.00046 (2128 queries per sec)
Web-server query execution time = 0.00069 (1445 queries per sec)
PHP script execution time = 0.00318 (314 queries per sec)

0.00318 + 20*0.00069 + 15*0.00103 = 0.03243 sec

You should note that the above data can only be obtained under ideal conditions. The data contains the most statistically significant results, but such factors as TCP connection to the server, response generated and sent to the requesting web browser were disregarded. The goal of this performance testing was to show the web applications performance on diferent hosting plans.

table of contents | on top