VPS performance: how much to hang in grams?

    The hosting market has gradually moved from leasing virtual sites to fully sane virtual servers, when there is guaranteed capacity and full access to the system and hardware. This strongly segmented the market: you can find both tariff plans for 200-300 rubles, and more than 2000 rubles a month. At the same time, all hosting providers offer more or less the same equipment indicators (processor, memory, disk) and the reasonable question arises: what, in fact, is the difference?

    To understand the issue with all the necessary depth, we tested the performance of more or less the same tariff plans from the most popular Russian providers on one of the most popular commercial platform in Russia for creating sites - 1C-Bitrix. Why on her? There are many reasons: the standard installation of the base site, the availability of “specially selected” tariff plans, and simply the existence of a certain set of Bitrix Environment packages that guarantee the relatively equal participation of various sites in testing (when we can compare performance without taking into account the specifics of the operating system or server environment).

    Measurement procedure


    For the methodology, we used three main performance parameters, partially related to each other:
    • performance assessment of 1C-Bitrix (the Small Business edition was used everywhere with the same site template and the same settings for installing the online store out of the box), the best of the three values ​​of sequential measurements was taken;
    • the average server response time for several characteristic pages (for example, the main or product card, the same for all sites) without taking into account network costs (only the response time for a request without taking into account the request transmission time), the average time per day was taken (or more );
    • and the full loading time of the same pages (it is already essential here that the same site template was used for all sites), the average time per day (or more) was taken.

    The choice of each parameter is understandable: it reflects the actual performance of the site with one of the most important for business components (either it is an assessment of the site manufacturer’s internal characteristics of the server, or a real assessment of server performance on real requests is fault tolerance, or a real assessment of client performance is download speed).

    All indicators were normalized to “medium-good” value (for example, for the 1C-Bitrix rating it was a reference value of 30), then they were multiplied and normalized to the price of the tariff plan. The latter is also quite obvious: we do not just find the most productive site of all, but choose the most practical one for solving specific business problems (ensuring fault tolerance and the speed of the site).

    Tariff Plans


    For the study, the following VPS tariff plans were selected. The table also shows the performance assessment of 1C-Bitrix (measured without any load on the site).
    Provider / TariffCPU (MHz)Memory (Mb)Disk (GB)Price, rub / monthBitrix
    Agava Optimal Bitrix100051212124973.05
    Rusonyx VPS Plus 2012200010241049966.13
    Reg.Ru VPS-320001024fifteen59564.56
    Selectel Bitrix-M10241024fifty75058.82
    HC ProVPS-32000102410140058.37
    Masterhost "Practical: 1C-Bitrix"800102410170055.69
    FirstVDS VDS Acceleration6007681624938.05
    FastVPS OVZ-5240020001467129.01
    TimeWeb VPS-Ultra15001024fifteen250014.63
    Infobox VPS-1024 Linux1000102460110011.48
    IHC Earth20001024fifty8505.55

    results


    Evaluation of WEBO Software, as was already noted above, was formed as an integral value of the ratio between four factors: 1C-Bitrix performance rating, server response time (for different pages, the same between the tested sites), time of full loading of the same pages and at the price.
    Provider / TariffBitrixResponse Time (ms)Download Time (ms)Price, rub / monthEvaluation of WEBO Software
    123123
    Rusonyx VPS Plus 201266.1382786010891208855499536.87
    Reg.Ru VPS-364.56706753175012751121595390.88
    Agava Optimal 1C-Bitrix73.055557371602128910481249288.01
    FirstVDS VDS Acceleration38.0514714493160016621840249220.91
    Selectel Bitrix-M58.82144154116159414311395750117.81
    HC ProVPS-358.37739772240218521511140085.22
    FastVPS OVZ-529.0120315017019162285142367141.86
    Masterhost "Practical: 1C-Bitrix"55.69158103148241021201837170035.62
    Infobox VPS-1024 Linux11.4857048138818761978188911003,5
    TimeWeb VPS-Ultra14.6327824520528182717181525003.12
    IHC Earth5.557366374025040331728588501

    conclusions


    The leaders in terms of performance / price ratio (more performance for the same money) stood out well from the total number of hosting providers: these are Rusonyx, Reg.Ru, Agave and FirstVDS. At the same time, if Agave got into the lead thanks to a very powerful virtual hardware (it’s not very clear for what reason: the declared characteristics are inferior to the majority of competitors), then FirstVDS broke out only because of the low price for a fairly good performance.

    At the same time, Reg.Ru and Rusonyx are very detached from other providers, providing very good performance for a low price - in the region of 500-600 rubles per month. However, Rusonyx outperforms Reg.Ru due to its good client performance (the virtual server was initially tuned for high performance and the configurations of Apache, nginx, PHP and MySQL are optimized for this), somewhat inferior in server response time.

    In general, there is only one advice - to go from top to bottom on this list and consistently choose a hosting provider that will appeal to you by the ratio of other factors.

    And as it turned out, 1C-Bitrix performance assessment is a good enough tool to measure the real performance of the site, but this assessment does not always give a result corresponding to real performance. Therefore, when choosing between several sites, in addition to this indicator, you also need to focus on real performance (server response time), which can be quickly measured using a large number of well-known tools.

    Also popular now: