In today's business environment, IT organizations face increasing pressure to ensure that systems are available to employees and customers 24/7. However, management errors or unforeseen events can happen from time to time - such as unplugging the wrong server during a maintenance window or failing to switch to an uninterruptible power supply during a lightning storm.
As data volumes increase, booting up servers and loading terabyte-scale databases into traditional memory after such events can take hours or longer. Booting up terabyte-scale in-memory database management systems like the SAP HANA® platform is even longer and more challenging due to the volatile nature of a server’s main memory. If power is lost, all data stored in main memory or dynamic random access memory must be reloaded. Even in high-availability configurations where a secondary system takes over the workload from the primary, extended boot times can increase risk because the primary system must still load all data back into main memory before redundancy can be restored.
Intel® Optane™ DC persistent memory combines the features of dynamic random access memory and traditional persistent memory, bringing a major change to the startup time of in-memory databases. SAP HANA 2.0 SPS 03 supports Intel® Optane™ DC persistent memory. Intel and SAP are leading the next generation of memory technology.
SAP HANA Business Data Platform: Preparing for the Persistent Memory Revolution
Over the past six years, Intel and SAP have worked together to enable the SAP HANA platform to support Intel® Optane™ DC persistent memory. This combination helps minimize system downtime compared to traditional memory.
The SAP HANA platform achieves its performance by storing data in the server’s main memory, which consists of fast dynamic random access memory. However, this speed comes at a cost: Although dynamic random access memory is the fastest memory available, it is also volatile, which means that the memory contents are not retained when the power is turned off, the server is restarted, or the SAP HANA platform is restarted. Any data stored in the dynamic random access memory is lost and must be reloaded from slower storage based on solid-state drives (SSDs) or hard disk drives (HDDs). For large, complex SAP HANA databases, this can result in extended downtime. Such failures are very costly, distracting database administrators (DBAs) and other IT operations staff from other important tasks, and it can also mean that customers or company employees do not have access to critical data in a timely manner.
SAP HANA 2.0 SPS 03 runs on servers that combine Intel® Optane™ DC persistent memory with DRAM, which changes the in-memory database landscape. Intel® Optane™ DC persistent memory provides nearly the same performance as DRAM, but the memory contents are preserved when power is turned off, the server is restarted, or SAP HANA is restarted. For the SAP HANA platform, it is no longer necessary to reload in-memory data from other persistent storage, minimizing downtime and reducing operational costs. When combined with other disaster recovery mechanisms in SAP HANA 2.0 SPS 03, organizations can better protect data, which helps database administrators focus on critical projects and potentially reduces total cost of ownership (TCO).
Intel and SAP engineers demonstrated how servers equipped with Intel® Optane™ DC persistent memory, traditional DRAM, and the SAP HANA 2.0 SPS 03 platform can significantly reduce system downtime. On a server equipped with DRAM only, the boot time of the SAP HANA 2.0 platform with 6 TB of data was 50 minutes. The combination of servers equipped with DRAM and Intel® Optane™ DC persistent memory reduced the boot time of the SAP HANA 2.0 SPS 03 platform by 12.5 times to just 4 minutes.
Intel® Optane™ DC persistent memory: a game changer for in-memory computing
IT organizations with big data requirements often use a tiered storage approach for in-memory databases and analytical systems such as the SAP HANA platform. These tiers include:
DRAM-based “hot” tier: This is the fastest available memory, but also the most expensive and volatile. Data in this tier is accessed frequently, but is not retained if power is lost or the server is rebooted. DRAM capacity does not scale as quickly as technologies in other storage tiers, which limits the size of in-memory databases and the amount of memory available in each processor.
• Flash-based “warm” tier: Flash-based storage is based on NAND memory and is relatively cheap, but much slower than DRAM. Unlike DRAM, data in flash-based storage is retained even after a power outage. Data in this tier is accessed more frequently, but not as frequently as data in the hot tier.
• Disk-based “cold” tier: This tier uses common hard disk drives, which have high capacity but are slower than flash and DRAM. Data in this tier is typically used for sensor and Internet of Things (IoT) data, which is considered archival data and is accessed infrequently.
Intel® Optane™ DC persistent memory merges the performance of DRAM with flash and disk-based storage, changing the data tiering landscape. Unlike DRAM, if a server loses power or the server is restarted, the data in Intel® Optane™ DC persistent memory is retained and still provides near-DRAM performance. Intel® Optane™ DC persistent memory blurs the line between volatile DRAM and persistent storage, driving a new revolution in how data is stored.
SAP HANA® 2.0 SPS 03 Features and Enhancements
In addition to support for Intel® Optane™ DC persistent memory, SAP HANA 2.0 SPS 03 delivers innovations and enhancements in the following key areas:
• Artificial intelligence (AI) enhancements help improve performance and productivity, helping data scientists gain insights. SAP HANA Spatial Service enables developers to easily add additional advanced spatial capabilities to applications.
• Database improvements enhance data and privacy protection by adding real-time data anonymization, improving high availability and disaster recovery, and enhancing multi-tenancy capabilities, dynamic tiering, and workload/performance management in innovative ways.
• Data management enhancements include new data integrations, support for federated sources of additional data types, and simplification capabilities to help improve data quality.
• Application development and tool enhancements help improve performance, simplify development, and enable new levels of security.
These improvements and support for Intel® Optane™ DC persistent memory open up new innovation possibilities and expand memory and storage configuration options.
DRAM is expensive and limited in size compared to flash and disk-based storage. The combination of Intel® Optane™ DC persistent memory and DRAM enables more memory configurations at a lower cost per GB than DRAM-only configurations. In addition, Intel® Optane™ DC persistent memory is available as persistent memory modules (PMMs). These modules use the same dual in-line memory module (DIMM) form factor as DRAM, but provide greater memory density than DRAM in the same physical server space. As a result, in-memory databases and analytics systems, such as SAP HANA 2.0 SPS 03, have a larger memory footprint, higher performance, and lower cost than using traditional DRAM alone.
Intel and SAP: Enabling the Next Generation of In-Memory Computing
Intel® Optane™ DC persistent memory combined with SAP HANA 2.0 SPS 03 blurs the line between DRAM and persistent storage for in-memory computing, changing the data tiering landscape. SAP HANA platforms experience significantly less system downtime, reducing operating costs and increasing data availability for customers and employees. SAP HANA platforms can also benefit from combined configurations of DRAM and Intel® Optane™ DC persistent memory that far exceed the performance of traditional DRAM.
Previous article:Huawei will set off a NAND buying spree
Next article:NAND Flash and DRAM prices are expected to continue to decline
- Popular Resources
- Popular amplifiers
- Huawei's Strategic Department Director Gai Gang: The cumulative installed base of open source Euler operating system exceeds 10 million sets
- Analysis of the application of several common contact parts in high-voltage connectors of new energy vehicles
- Wiring harness durability test and contact voltage drop test method
- Sn-doped CuO nanostructure-based ethanol gas sensor for real-time drunk driving detection in vehicles
- Design considerations for automotive battery wiring harness
- Do you know all the various motors commonly used in automotive electronics?
- What are the functions of the Internet of Vehicles? What are the uses and benefits of the Internet of Vehicles?
- Power Inverter - A critical safety system for electric vehicles
- Analysis of the information security mechanism of AUTOSAR, the automotive embedded software framework
Professor at Beihang University, dedicated to promoting microcontrollers and embedded systems for over 20 years.
- Innolux's intelligent steer-by-wire solution makes cars smarter and safer
- 8051 MCU - Parity Check
- How to efficiently balance the sensitivity of tactile sensing interfaces
- What should I do if the servo motor shakes? What causes the servo motor to shake quickly?
- 【Brushless Motor】Analysis of three-phase BLDC motor and sharing of two popular development boards
- Midea Industrial Technology's subsidiaries Clou Electronics and Hekang New Energy jointly appeared at the Munich Battery Energy Storage Exhibition and Solar Energy Exhibition
- Guoxin Sichen | Application of ferroelectric memory PB85RS2MC in power battery management, with a capacity of 2M
- Analysis of common faults of frequency converter
- In a head-on competition with Qualcomm, what kind of cockpit products has Intel come up with?
- Dalian Rongke's all-vanadium liquid flow battery energy storage equipment industrialization project has entered the sprint stage before production
- New breakthrough! Ultra-fast memory accelerates Intel Xeon 6-core processors
- New breakthrough! Ultra-fast memory accelerates Intel Xeon 6-core processors
- Consolidating vRAN sites onto a single server helps operators reduce total cost of ownership
- Consolidating vRAN sites onto a single server helps operators reduce total cost of ownership
- Allegro MicroSystems Introduces Advanced Magnetic and Inductive Position Sensing Solutions at Electronica 2024
- Car key in the left hand, liveness detection radar in the right hand, UWB is imperative for cars!
- After a decade of rapid development, domestic CIS has entered the market
- Aegis Dagger Battery + Thor EM-i Super Hybrid, Geely New Energy has thrown out two "king bombs"
- A brief discussion on functional safety - fault, error, and failure
- In the smart car 2.0 cycle, these core industry chains are facing major opportunities!
- [Analog Electronics Course Selection Test] + Assessment
- Configuration of heat dissipation holes in DC-DC layout
- [Raspberry Pi Pico Review] 5. Pico drives LCD1602
- DIY Extended WiFi Antenna
- Characteristics and Applications of Voltage Monitoring Chip TPS383X
- [RVB2601 Creative Application Development] Introduction and use of RVB2601 WiFi networking to obtain weather information
- Renesas Electronics RL78/G11 target board free application, participate in the application can also win a JD card!
- Usage of pragma in dsp
- FPGA Learning Notes-----FPGA Competition Adventure
- PIC series microcontroller programming basics II