July 29, 2015 at 14:16Fujitsu PRIMEQUEST: a standard platform with mainframe reliability
Critical applications place very high demands on the server platform. It should provide constant availability, minimal downtime, have high performance and scalability. Traditionally, proprietary RISC / UNIX platforms and mainframes have been used for these purposes. Servers of standard architecture did not possess such qualities.
Now the situation has changed: by RAS indicators(Reliability, Availability, Serviceability - reliability), some x86 server models have reached a whole new level, and in the advanced developments of leading vendors, RAS tools implemented in next-generation Intel Xeon E7 processors are complemented by RAS characteristics inherent in UNIX hardware architectures -systems and mainframes. However, only a few players in the global server market simultaneously have experience in developing RISC architecture servers and mainframes, which allows them to create systems with the highest level of reliability and performance.
Fujitsu Offers New PRIMEQUEST 2000 Server SeriesThe second-generation Xeon E7 V3 processor, based on the most powerful processors, provides an exceptionally reliable platform for data center infrastructures. PRIMEQUEST systems are already widely known for their record performance and fault tolerance. Features of the new generation of PRIMEQUEST servers are advanced RAS components with advanced self-healing features, including dynamic configuration changes and extended partitions, DDR4 memory fault tolerance, as well as a new Intel processor family.
The models introduced in May 2015 include the four-processor PRIMEQUEST 2400E2 system, the eight-processor PRIMEQUEST 2800E2, and the eight-processor model PRIMEQUEST 2800B2. The transition from Xeon E7 v2 to Xeon E7 v3 processors allowed Fujitsu to significantly increase the performance / dollar ratio for PRIMEQUEST servers:
PRIMEQUEST platform is distinguished from the business-critical x86 systems of other leading vendors by the unique Fujitsu experience embodied in technologies, which has been developing mainframes and powerful RISC / UNIX servers for decades. Therefore, the Fujitsu PRIMEQUEST 2000 Series servers offer high UNIX class availability and the cost-effectiveness of a standard architecture. They are even called x86 mainframes.
By the way, this company has already 50 years of experience in creating business-critical systems.
The first PRIMEQUEST system on the Intel x86 platform appeared in 2005. The latest Fujitsu PRIMEQUEST server line uses a highly reliable server architecture, many of which are inherited from Fujitsu PRIMEPOWER UNIX servers and Fujitsu mainframes.
E2 models are designed to solve critical tasks in cases where downtime is unacceptable. These systems will be a good option for companies that wish to upgrade to a standard architecture platform without losing the reliability inherent in modern UNIX systems and mainframes.
The PRIMEQUEST 2800B2 is a server for even more memory intensive applications such as in-memory computing and SAP HANA. It provides cost-effectiveness and guaranteed support for business-critical security levels.
Today, customers have a real alternative to expensive proprietary systems. A powerful argument in favor of x86 servers was the vast ecosystem and attractive product prices. It is no coincidence that companies and organizations around the world are increasingly choosing economical x86 servers for Linux and Windows for critical tasks, replacing them with proprietary UNIX platforms: according to IDC, over the past five years, the number of such servers in the world has grown by 25% -30%. The emergence of new classes of tasks, including support for mobility, cloud computing, Big Data analytics, further increase the need for cost-effective business critical servers.
As a server of standard architecture, PRIMEQUEST gives customers access to the entire vast x86 ecosystem, allowing you to use a large number of applications created for this architecture. Such a platform can be used for the most demanding and resource-intensive workloads, including decision support systems, SAP DBMSs and Oracle. Finally, a very important factor in modern conditions is price. PRIMEQUEST servers are characterized by the lowest price among enterprise-class systems with a level of reliability comparable to such UNIX platforms as IBM Power and HP Superdome 2.
PRIMEQUEST implements automated recovery of “motherboards” - server modules containing processors and random access memory, flexible I / O redirection, non-shutdown service, backup of the control processor and system clock, mirroring of RAM, detection and correction of CPU errors, redundancy and hot replacement of components.
High requirements of applications to the level of availability of the hardware platform determine its features. It should ensure data integrity, the ability to recover from failures in a minimum of time, and proactive management / monitoring to prevent downtime. At the same time, its architecture should be well balanced and scalable, without “bottlenecks”.
The first PRIMEQUEST server, released in 2005, became the most powerful IA-64 server for critical computing at that time. In 2012, the PRIMEQUEST 1000 line was introduced; in 2014, deliveries of the new series of servers, PRIMEQUEST 2000, began. The last update dates back to May 2015, when the E2 / B2 models were introduced.
The servers of this series were originally created as an x86 platform for executing mission-critical enterprise applications, but at the same time reducing the high costs traditionally inherent in the UNIX world, not inferior to UNIX systems in terms of availability, scalability and performance. Fujitsu PRIMEQUEST servers allow you to solve the problems of consolidation, standardization of the server fleet, and ensure the smooth operation of business-critical applications.
Servers support standard OS - RedHat and SuSE Linux or Windows Server. They can be used for large databases, in-memory databases such as SAP HANA, as well as for working with Big Data and as a platform for business-critical applications.
Since the requirements for high availability and cost-effectiveness differ from one customer to another, Fujitsu offers three PRIMEQUEST models: 2800 / 2400E2 (Enterprise Model) with the highest level of availability and 2000B2 (Business Model), “tailored” to achieve the best cost-effectiveness. Due to high energy efficiency and reduced administration costs, these servers are one of the most economical systems of this class.
Fujitsu PRIMEQUEST 2400 / 2800E2 (number 2 means the second generation of servers) - a 4- / 8-socket system in a 10U package - is positioned as a dynamic platform for a modern data center, which combines the efficiency and flexibility of x86 servers with high availability and reliability of platforms SPARC.
Older PRIMEQUEST models support up to 8 Intel Xeon processors - up to 144 processing cores. Management Board Management (MMB) controls fully control the server, collecting data and statistics from its components, monitor the temperature inside the system, and help identify and troubleshoot problems. For drives, processors and memory, potential problems are identified in advance, even before a possible failure.
MMB also controls the process of starting and stopping the server, activating and deactivating system resources. In addition, the PRIMEQUEST MMB utilizes the number of modules that is required in accordance with the current power consumption, which makes a significant contribution to the energy efficiency of the system. The fan speed is also adjustable according to current cooling needs. Thus, the MMB improves the reliability and energy efficiency of the system. Hardware management MMB duplicated. For ease of administration, they are integrated with the ServerView Suite management software.
PRIMEQUEST adjusts the number of active power supply modules (PSUs) according to the power consumption of the server. Take, for example, the redundant configuration of N + 1 power modules. If four PSUs operate at a load of 40% of the maximum value, the server reduces the number of active PSUs to three with a load of 53%. As a result, one PSU becomes inactive.
All major components support hot swapping: power modules, fans, disk drives, PCI cards, service processors. Almost all components are duplicated.
Thanks to the hardware partitions, the PRIMEQUEST system provides much higher reliability than platforms with exclusively software virtualization. It uses physical partitions (hardware partitions) and active backup of the so-called "system boards" (System Board, SB) - replaceable server modules.
The physical partitions are actually several independent systems with common I / O, operating on the same platform - an excellent opportunity for server consolidation.
Physical partitions can be reconfigured without rebooting the system. Dynamically reconfigurable partitions are a unique feature for x86 systems. For example, if the resources of one hardware partition are not enough to cope with the current load, you can allocate additional memory / processor power from another partition to it. Something like this:
Partition configuration can be changed without shutting down the system and restarting it, adding resources to a particular partition or deleting them. This significantly increases the flexibility and reliability of the system.
You can reserve a System Board in the event of a failure or to expand a working partition.
When the load increases, you can install another module (System Board) into a working system and add its resources to the corresponding section. In the same way, you can change equipment on a “live” system in the event of a failure of one “system board”.
Fujitsu offers a graphical interface for reconfiguring partitions. Working with him is not particularly difficult. It is quite intuitive.
However, fans of the command line can use it. In this example, System Board 3 is added to Section 0 “live”.
If the operation is successful, the green indicator on the front panel of the server will light up, indicating the operating status of the corresponding “motherboard”. Another example is removing System Board 2 from section 0:
The hardware partitions (PPAR) with dynamic reconfiguration at the level of “motherboards" are not limited to. Fujitsu engineers also provided for the so-called extended sections.
Advanced Partitions (EPAR) allow you to manipulate resources with greater granularity - not at the level of the entire System Board module, but at the level of computing cores and memory blocks, which helps optimize the use of system resources - memory and CPU, or isolate failures. In addition, choosing the required number of cores can significantly save on software licensing. For example, Oracle DBMS licenses are very expensive.
The differences in sections of different types are shown in the following table.
Thus, PRIMEQUEST servers support several types of partitions - physical, advanced and software (virtual machines) - with different levels of isolation of hardware and software errors and consolidation capabilities.
To summarize:
Partitions:
PRIMEQUEST supports up to 8 electrically isolated partitions - hardware-level partitions, as well as extended partitions with functionality similar to virtual machines, but not requiring a license for a hypervisor.
Flexible I / O:
In PRIMEQUEST, the entire I / O subsystem is available to all CPUs through PCIe switches. It supports up to 56 PCI slots and the ability to install a large number of PCI SSD drives without sacrificing I / O performance.
System board in hot standby:
In PRIMEQUEST, it can be used to recover from a motherboard failure, and dynamic reconfiguration is supported. Also, the backup motherboard can be added live to the partition. This is implemented for Windows and Linux.
Parallel maintenance:
In PRIMEQUEST, individual partitions can be stopped for maintenance, while other partitions work. The control module is redundant.
As a result, PRIMEQUEST combines the qualities of standard x86 servers and PRIMEPOWER platform technologies for high performance and availability.
According to Intel , thanks to the Xeon E7 v3 processors, Fujitsu PRIMEQUEST servers increase the consolidation of IT infrastructure by 26% due to increased throughput when running applications and support 40% more virtual machines. The specifications of the PRIMEQUEST 2800E2 and Xeon E7 8800 series processors can be found here .
With the transition to the new generation of Xeon v3, the performance of PRIMEQUEST has grown by about 20%.
In May, the PRIMEQUEST 2800E2 servers with 8 Xeon E7-8890 v3 processors set a record among eight-processor systems when performing the SPECint_rate_base2006 benchmark test, and the PRIMEQUEST 2800E2 server with 2 Xeon E7-8890 v3 processors became the leader in the SPECfp_rate_base2006 test among dual processors. The results of these and other tests can be found here .
When performing the SAP SD test, the Fujitsu PRIMEQUEST 2800E2 server served more than 56 thousand users simultaneously.
The 2800E2 model scales to 8 Intel Xeon processors, E7-8800 v3 processors, and 12 TB of RAM (with Linux). It is typical that with an increase in the number of motherboards / processors, server performance when working with the DBMS grows almost linearly, which indicates a balanced architecture of the system and its competent design. Especially high performance can be achieved using an external flash array.
Why can you use such server platforms? They best reveal their qualities in use cases such as mission-critical applications and scalable databases, real-time analytics, and server capacity consolidation. Such a platform actually combines up to eight physically independent servers, helping to significantly reduce operating costs.
PRIMEQUEST is aimed at customers who migrate applications from mainfames and RISC / UNIX systems , implementing large-scale projects for scaling, virtualization and deployment of resource-intensive Linux / Windows applications, DBMS.
PRIMEQUEST helps minimize planned and unplanned downtime, since almost all system components are completely redundant and support hot-swap. In addition, central processors and RAM are fault tolerant thanks to multi-level data protection mechanisms. And the performance of the PRIMEQUEST server scales very well to its maximum value.
Unique functionality and fault tolerance make this server a unique offer on the market, and the use of the latest components, such as Intel Xeon V3 and DDR4 memory, allows you to actively compete with servers that use 16 processors or more, but are based on less efficient components.
A complete set of error detection and correction tools, as well as a system architecture that provides high availability, guarantee the maximum uptime of the PRIMEQUEST server. Such a server can significantly reduce downtime due to maintenance operations, such as replacing failed components and updating firmware. In addition, due to its simple design, where most of the components are connected using the backplane with almost no cables, the components can be replaced through the front or rear panel without removing the equipment from the rack.
PRIMEQUEST servers are aimed at companies that need a highly reliable system based on Linux or Windows Server, organizations that have "outgrown" typical x86 servers, and those who would like to reduce the cost of operation and license fees.
Now the situation has changed: by RAS indicators(Reliability, Availability, Serviceability - reliability), some x86 server models have reached a whole new level, and in the advanced developments of leading vendors, RAS tools implemented in next-generation Intel Xeon E7 processors are complemented by RAS characteristics inherent in UNIX hardware architectures -systems and mainframes. However, only a few players in the global server market simultaneously have experience in developing RISC architecture servers and mainframes, which allows them to create systems with the highest level of reliability and performance.
Fujitsu Offers New PRIMEQUEST 2000 Server SeriesThe second-generation Xeon E7 V3 processor, based on the most powerful processors, provides an exceptionally reliable platform for data center infrastructures. PRIMEQUEST systems are already widely known for their record performance and fault tolerance. Features of the new generation of PRIMEQUEST servers are advanced RAS components with advanced self-healing features, including dynamic configuration changes and extended partitions, DDR4 memory fault tolerance, as well as a new Intel processor family.
The models introduced in May 2015 include the four-processor PRIMEQUEST 2400E2 system, the eight-processor PRIMEQUEST 2800E2, and the eight-processor model PRIMEQUEST 2800B2. The transition from Xeon E7 v2 to Xeon E7 v3 processors allowed Fujitsu to significantly increase the performance / dollar ratio for PRIMEQUEST servers:
PRIMEQUEST platform is distinguished from the business-critical x86 systems of other leading vendors by the unique Fujitsu experience embodied in technologies, which has been developing mainframes and powerful RISC / UNIX servers for decades. Therefore, the Fujitsu PRIMEQUEST 2000 Series servers offer high UNIX class availability and the cost-effectiveness of a standard architecture. They are even called x86 mainframes.
By the way, this company has already 50 years of experience in creating business-critical systems.
The first PRIMEQUEST system on the Intel x86 platform appeared in 2005. The latest Fujitsu PRIMEQUEST server line uses a highly reliable server architecture, many of which are inherited from Fujitsu PRIMEPOWER UNIX servers and Fujitsu mainframes.
E2 models are designed to solve critical tasks in cases where downtime is unacceptable. These systems will be a good option for companies that wish to upgrade to a standard architecture platform without losing the reliability inherent in modern UNIX systems and mainframes.
The PRIMEQUEST 2800B2 is a server for even more memory intensive applications such as in-memory computing and SAP HANA. It provides cost-effectiveness and guaranteed support for business-critical security levels.
Why x86?
Today, customers have a real alternative to expensive proprietary systems. A powerful argument in favor of x86 servers was the vast ecosystem and attractive product prices. It is no coincidence that companies and organizations around the world are increasingly choosing economical x86 servers for Linux and Windows for critical tasks, replacing them with proprietary UNIX platforms: according to IDC, over the past five years, the number of such servers in the world has grown by 25% -30%. The emergence of new classes of tasks, including support for mobility, cloud computing, Big Data analytics, further increase the need for cost-effective business critical servers.
As a server of standard architecture, PRIMEQUEST gives customers access to the entire vast x86 ecosystem, allowing you to use a large number of applications created for this architecture. Such a platform can be used for the most demanding and resource-intensive workloads, including decision support systems, SAP DBMSs and Oracle. Finally, a very important factor in modern conditions is price. PRIMEQUEST servers are characterized by the lowest price among enterprise-class systems with a level of reliability comparable to such UNIX platforms as IBM Power and HP Superdome 2.
PRIMEQUEST implements automated recovery of “motherboards” - server modules containing processors and random access memory, flexible I / O redirection, non-shutdown service, backup of the control processor and system clock, mirroring of RAM, detection and correction of CPU errors, redundancy and hot replacement of components.
High requirements of applications to the level of availability of the hardware platform determine its features. It should ensure data integrity, the ability to recover from failures in a minimum of time, and proactive management / monitoring to prevent downtime. At the same time, its architecture should be well balanced and scalable, without “bottlenecks”.
PRIMEQUEST Architecture
The first PRIMEQUEST server, released in 2005, became the most powerful IA-64 server for critical computing at that time. In 2012, the PRIMEQUEST 1000 line was introduced; in 2014, deliveries of the new series of servers, PRIMEQUEST 2000, began. The last update dates back to May 2015, when the E2 / B2 models were introduced.
The servers of this series were originally created as an x86 platform for executing mission-critical enterprise applications, but at the same time reducing the high costs traditionally inherent in the UNIX world, not inferior to UNIX systems in terms of availability, scalability and performance. Fujitsu PRIMEQUEST servers allow you to solve the problems of consolidation, standardization of the server fleet, and ensure the smooth operation of business-critical applications.
Servers support standard OS - RedHat and SuSE Linux or Windows Server. They can be used for large databases, in-memory databases such as SAP HANA, as well as for working with Big Data and as a platform for business-critical applications.
Since the requirements for high availability and cost-effectiveness differ from one customer to another, Fujitsu offers three PRIMEQUEST models: 2800 / 2400E2 (Enterprise Model) with the highest level of availability and 2000B2 (Business Model), “tailored” to achieve the best cost-effectiveness. Due to high energy efficiency and reduced administration costs, these servers are one of the most economical systems of this class.
Fujitsu PRIMEQUEST 2400 / 2800E2 (number 2 means the second generation of servers) - a 4- / 8-socket system in a 10U package - is positioned as a dynamic platform for a modern data center, which combines the efficiency and flexibility of x86 servers with high availability and reliability of platforms SPARC.
Older PRIMEQUEST models support up to 8 Intel Xeon processors - up to 144 processing cores. Management Board Management (MMB) controls fully control the server, collecting data and statistics from its components, monitor the temperature inside the system, and help identify and troubleshoot problems. For drives, processors and memory, potential problems are identified in advance, even before a possible failure.
MMB also controls the process of starting and stopping the server, activating and deactivating system resources. In addition, the PRIMEQUEST MMB utilizes the number of modules that is required in accordance with the current power consumption, which makes a significant contribution to the energy efficiency of the system. The fan speed is also adjustable according to current cooling needs. Thus, the MMB improves the reliability and energy efficiency of the system. Hardware management MMB duplicated. For ease of administration, they are integrated with the ServerView Suite management software.
PRIMEQUEST adjusts the number of active power supply modules (PSUs) according to the power consumption of the server. Take, for example, the redundant configuration of N + 1 power modules. If four PSUs operate at a load of 40% of the maximum value, the server reduces the number of active PSUs to three with a load of 53%. As a result, one PSU becomes inactive.
All major components support hot swapping: power modules, fans, disk drives, PCI cards, service processors. Almost all components are duplicated.
Sections and dynamic reconfiguration
Thanks to the hardware partitions, the PRIMEQUEST system provides much higher reliability than platforms with exclusively software virtualization. It uses physical partitions (hardware partitions) and active backup of the so-called "system boards" (System Board, SB) - replaceable server modules.
The physical partitions are actually several independent systems with common I / O, operating on the same platform - an excellent opportunity for server consolidation.
Physical partitions can be reconfigured without rebooting the system. Dynamically reconfigurable partitions are a unique feature for x86 systems. For example, if the resources of one hardware partition are not enough to cope with the current load, you can allocate additional memory / processor power from another partition to it. Something like this:
Partition configuration can be changed without shutting down the system and restarting it, adding resources to a particular partition or deleting them. This significantly increases the flexibility and reliability of the system.
You can reserve a System Board in the event of a failure or to expand a working partition.
When the load increases, you can install another module (System Board) into a working system and add its resources to the corresponding section. In the same way, you can change equipment on a “live” system in the event of a failure of one “system board”.
Fujitsu offers a graphical interface for reconfiguring partitions. Working with him is not particularly difficult. It is quite intuitive.
However, fans of the command line can use it. In this example, System Board 3 is added to Section 0 “live”.
If the operation is successful, the green indicator on the front panel of the server will light up, indicating the operating status of the corresponding “motherboard”. Another example is removing System Board 2 from section 0:
The hardware partitions (PPAR) with dynamic reconfiguration at the level of “motherboards" are not limited to. Fujitsu engineers also provided for the so-called extended sections.
Advanced Partitions (EPAR) allow you to manipulate resources with greater granularity - not at the level of the entire System Board module, but at the level of computing cores and memory blocks, which helps optimize the use of system resources - memory and CPU, or isolate failures. In addition, choosing the required number of cores can significantly save on software licensing. For example, Oracle DBMS licenses are very expensive.
The differences in sections of different types are shown in the following table.
Thus, PRIMEQUEST servers support several types of partitions - physical, advanced and software (virtual machines) - with different levels of isolation of hardware and software errors and consolidation capabilities.
To summarize:
Partitions:
PRIMEQUEST supports up to 8 electrically isolated partitions - hardware-level partitions, as well as extended partitions with functionality similar to virtual machines, but not requiring a license for a hypervisor.
Flexible I / O:
In PRIMEQUEST, the entire I / O subsystem is available to all CPUs through PCIe switches. It supports up to 56 PCI slots and the ability to install a large number of PCI SSD drives without sacrificing I / O performance.
System board in hot standby:
In PRIMEQUEST, it can be used to recover from a motherboard failure, and dynamic reconfiguration is supported. Also, the backup motherboard can be added live to the partition. This is implemented for Windows and Linux.
Parallel maintenance:
In PRIMEQUEST, individual partitions can be stopped for maintenance, while other partitions work. The control module is redundant.
As a result, PRIMEQUEST combines the qualities of standard x86 servers and PRIMEPOWER platform technologies for high performance and availability.
Performance
According to Intel , thanks to the Xeon E7 v3 processors, Fujitsu PRIMEQUEST servers increase the consolidation of IT infrastructure by 26% due to increased throughput when running applications and support 40% more virtual machines. The specifications of the PRIMEQUEST 2800E2 and Xeon E7 8800 series processors can be found here .
With the transition to the new generation of Xeon v3, the performance of PRIMEQUEST has grown by about 20%.
In May, the PRIMEQUEST 2800E2 servers with 8 Xeon E7-8890 v3 processors set a record among eight-processor systems when performing the SPECint_rate_base2006 benchmark test, and the PRIMEQUEST 2800E2 server with 2 Xeon E7-8890 v3 processors became the leader in the SPECfp_rate_base2006 test among dual processors. The results of these and other tests can be found here .
When performing the SAP SD test, the Fujitsu PRIMEQUEST 2800E2 server served more than 56 thousand users simultaneously.
The 2800E2 model scales to 8 Intel Xeon processors, E7-8800 v3 processors, and 12 TB of RAM (with Linux). It is typical that with an increase in the number of motherboards / processors, server performance when working with the DBMS grows almost linearly, which indicates a balanced architecture of the system and its competent design. Especially high performance can be achieved using an external flash array.
Summary
Why can you use such server platforms? They best reveal their qualities in use cases such as mission-critical applications and scalable databases, real-time analytics, and server capacity consolidation. Such a platform actually combines up to eight physically independent servers, helping to significantly reduce operating costs.
PRIMEQUEST is aimed at customers who migrate applications from mainfames and RISC / UNIX systems , implementing large-scale projects for scaling, virtualization and deployment of resource-intensive Linux / Windows applications, DBMS.
PRIMEQUEST helps minimize planned and unplanned downtime, since almost all system components are completely redundant and support hot-swap. In addition, central processors and RAM are fault tolerant thanks to multi-level data protection mechanisms. And the performance of the PRIMEQUEST server scales very well to its maximum value.
Unique functionality and fault tolerance make this server a unique offer on the market, and the use of the latest components, such as Intel Xeon V3 and DDR4 memory, allows you to actively compete with servers that use 16 processors or more, but are based on less efficient components.
A complete set of error detection and correction tools, as well as a system architecture that provides high availability, guarantee the maximum uptime of the PRIMEQUEST server. Such a server can significantly reduce downtime due to maintenance operations, such as replacing failed components and updating firmware. In addition, due to its simple design, where most of the components are connected using the backplane with almost no cables, the components can be replaced through the front or rear panel without removing the equipment from the rack.
PRIMEQUEST servers are aimed at companies that need a highly reliable system based on Linux or Windows Server, organizations that have "outgrown" typical x86 servers, and those who would like to reduce the cost of operation and license fees.