Fujitsu Servers: Autumn Update

    Surely almost every one of you, like us, has encountered an avalanche-like growth in data, and realized that this process should not be expected to stop or slow in the near future. Currently, applications working with data are actively developing, for example, in such areas as business analytics and BigData Mining. Their use requires serious server resources and elimination of bottlenecks in drives and communications.

    Fujitsu, having a large and largely unique experience in developing servers and understanding the needs and tasks of its customers, timely releases solutions that can effectively solve current problems and have a sufficiently large reserve for the future, which is confirmed by repeated world records for performance:

    Moreover, the dual-processor servers of the S8 generation came out just a month ago, but already managed to set new records:

    • PRIMERGY RX300 S8 - a new world record in energy efficiency - 8.097 overall ssj_ops / watt1; 7.46 watts / kilo SAPS2
    • PRIMERGY RX350 S8 - a new record for system performance - SPECfp_base 2006 = 109
    • PRIMERGY RX300 S8 - a new record in the dual-link SAP SD test among dual-processor servers - 10.240 SAP SD Benchmark users

    Many, often not without justification, are skeptical of such “figures on the Internet,” so Fujitsu is ready to demonstrate similar results to the customer on equipment from the demo fund in order to dispel any doubts.

    In the Fujitsu server line, you can find almost everything: from a microserver to a mainframe. Its updating is connected, first of all, with the updating by Intel of its server processors of the Intel Xeon E5-2600 series to version v2, as well as the Intel Xeon E3-1200 series processors to version v3. It affected the following Fujitsu PRIMERGY servers (by family):

    • TX - low-cost floor-standing servers for small infrastructures - the changes affected the single-processor PRIMERGY TX140 generation S2, as well as a sufficiently powerful and flexible dual-processor PRIMERGY TX300 generation S8 generation;
    • RX - universal powerful and energy-efficient rack servers - the single-processor server PRIMERGY RX100 and dual-processor PRIMERGY RX200, RX300 and RX350 (all models of the S8 generation) have been updated;
    • BX - compact scalable blade systems - in this family the dual-processor blade PRIMERGY BX924 was updated to the S4 generation;
    • CX - high-density server infrastructure (several independent computing nodes (nodes) in one server chassis provide more power with the same or less occupied space) - in September this year The new PRIMERGY CX400 chassis and dual-generation S2 CX250 and CX270 computing nodes were introduced.

    Recall that in the Intel Xeon E5-2600 v2 processors, a transition was made from the Sandy Bridge-EP microarchitecture to Ivy Bridge-EP. The latter is well known to all of us on single-processor servers, desktop and mobile PCs, where it has been used for a long time and is being supplanted by Haswell architecture at the moment. The architecture of Ivy Bridge-EP is distinguished, first of all, by a finer manufacturing process (22 nm). In addition, processor models with 12 processing cores appeared, which gave a pretty good performance jump (Sandy Bridge-EP had no more than 8 cores), the maximum volume of the third-level cache increased to 30 MB (there were 20), and support for memory with a frequency of 1866 MHz (it was 1600) and power consumption in idle mode decreased to 10.5 W compared to 15 W in the previous line.

    Another important change was the support of 64 GB memory modules, with which it became possible to use up to 1536 GB of RAM in dual-processor servers! Unfortunately, the cost of each such module is currently comparable to the cost of a whole good server. However, using 32 GB modules, it is quite possible to get a volume of 768 GB for a dual-processor server. Although the price of such modules is still quite high (one 32 GB module costs about 3 modules of 16 GB each), it turns out to be quite lifting if the real task is to provide a large amount of RAM. By the way, if it’s not difficult, please share in the comments what maximum RAM you used in your servers (they are primarily interested in dual-processor, but also the others) and for what tasks.

    Intel Xeon E3-1200 v3 processors are focused on single-processor solutions, they are built on Haswell microarchitecture. This processor architecture differs from the previous one (Ivy Bridge) in some optimizations of the computing cores, in particular, support for the new AVX 2.0 instructions, which made it possible to increase productivity by an average of about 8.5% for processors with the same clock speed characteristics. Comparison of the speed of performing integer operations and floating-point operations of the Intel Xeon Processor E3-1200 processors of all three generations can be seen in the graph below:

    As you can see, there is undoubtedly a performance gain, but in a single-processor server this may not be very noticeable (especially if compare with the previous generation, and not with the very first).

    Updating processors is not the only change in new servers. Another major innovation is the use of Fujitsu Cool-safe Advanced Thermal Design (ATD) technology.. This is Fujitsu's approach to the internal design of servers, expanding their operating temperature range by 5 degrees in both directions. Now the permissible operating ambient temperature for such equipment is from + 5 ° C to + 40 ° C (for servers of previous generations the range was + 10 ° C - + 35 ° C). At the same time, the most important task of Cool-safe ATD is to ensure the continuous operation of servers in the entire operating range without a time limit. Those. you will not need to even change the ambient temperature for a short time or reduce the performance of the server itself to cool it. This factor is, in fact, very important. So, for example, according to Gartner, increasing the temperature in the data center by 5 degrees can save up to 27% on server cooling (data for Europe). And under the conditions of Russian reality, it allows you to install a number of such servers in server rooms with natural air conditioning, or use less powerful cooling systems. The cost of heat dissipation is something you can save on, thanks in large part to Fujitsu. In our opinion, this is an understandable argument for any leader.

    In addition to expanding operating temperatures, the energy efficiency of the servers themselves increases. So, according to the tests java operation per watt (SPECpower_ssj2008), new servers show up to 50% increase in performance per watt, which corresponds to an increase in performance by 35% while maintaining the level of energy consumption. This was achieved through the introduction of new power supplies with 96% efficiency (80Plus Titanium certification), improvements at the system level (BIOS and Firmware components), simplified power management in ServerView (this is the name of our family of software for convenient management of Fujitsu servers throughout life cycle).

    New servers also offer a new level of SSD performance. For this, in some models (RX 300 S8 and RX350 S8), a Fujitsu PRAID EP400i RAID controller with support for the latest 12 Gb / s SAS interface, as well as corresponding SSDs can be installed. In addition, support for PCIe SSD 2.5˝ is expected in the near future. These drives look like a regular 2.5˝ SSD, but have a PCI-Express interface, respectively, they require a basket with a special backplane with direct connection to the PCIe bus. Using only the new 12Gb / s SAS interface can achieve a significant increase in the number of input / output operations per second (IOPS) for SSDs compared to the previous generation, and the gain from the introduction of PCIe drives will be even greater:

    Thus, the response time for the disk subsystem is reduced, which allows for greater performance for solutions with high I / O requirements: databases, business analytics, VDI, etc. Here you can recall the vSAN technology announced by our global partner - the company VMware is in the latest version of the vSphere 5.5 virtualization platform. When using it, such a performance of the local disk subsystem will be very useful.

    The Integrated Remote Access Controller (iRMC), which enables the server to communicate with Fujitsu ServerView, has also been updated.. Its new version S4 has increased up to 256 MB of video memory, it supports monitoring of RAID and disks regardless of the state of the OS (even if the OS is not loaded or “frozen”). Also in it appeared the option of recording video, which works including before loading the OS, and support for CIM (Common Information Model).

    Some new server models also support the nVidia Tesla K20 / K20X and Intel Xeon Phi Compute Accelerators, which are widely distributed in the HPC segment. In general, HPC clusters are one of the areas where Fujitsu's position is traditionally strong. Also in the new lineup there is support for NVIDIA Grid K1 cards certified for use with Citrix XenDesktop, which provide hardware-based virtualization of the GPU and ample opportunities for VDI.

    In conclusion, we give the characteristics of the updated servers. In order not to bore you with a tedious enumeration of characteristics in which it is easy to get confused, we have compiled the corresponding plates (in key they are highlighted in key differences from the previous generation models). In this form, this information seems to us more useful.

    Also popular now: