Do I need a four-socket server?

Randall Lundin

Sunday 1 November 2015

Today, 80 percent of the worldwide x86 rack-server revenue comes from one- or two-socket servers. So why do you need a four-socket server? Let’s take a look.

Consolidating multiple, smaller servers to fewer, four-socket servers — such as Lenovo x3850 X6 — provides added server capabilities and application benefits, as well as real cost savings.

The advantages of four-socket, scale-up servers can be summed up in three categories: server capabilities, enterprise applications and consolidation benefits.

Server capabilities

  • Memory: The Lenovo x3850 X6 has 4X the memory capabilities of two-socket servers. The x3850 X6 provides the memory required for large virtual machines and in-memory databases.
  • Performance: The x3850 X6 provides greater than 2X the compute performance of two-socket servers.
  • Agility: The x3850 X6 provides agility not found in two-socket servers. You can add, modify or upgrade easily with selectable modular X6 “book” components for storage, compute and I/O.
  • Increased I/O: The x3850 X6 provides up to 11 PCIe expansions slots compared to most two-socket systems that provide seven-to-eight PCIe expansion slots.
  • Advanced RAS: The x3850 X6 has advanced reliability, availability and serviceability (RAS) capabilities not available on two-socket servers. Mission-critical applications require the highest level of RAS available.

Enterprise applications

Several application and workloads lend themselves particularly well to scale-up, four-socket servers rather than scale-out deployments with smaller servers. Factors contributing to a decision to scale up rather than scale out include processing and memory requirements, number of end users, scalability cost and administrative cost.

Here are some examples:

  • Oracle Database: While Oracle Database software products support both scale-out and scale-up computing, deploying Oracle Databases on scale-up servers brings a number of benefits, including simplified server management, reduced server licensing costs and reduced operating costs related to IT staff time and management.
  • SAP HANA: SAP HANA is an integrated solution combining software and hardware, frequently referred to as the HANA appliance. It consists of the SAP HANA database and adds components needed to work with, administer and operate the database. SAP HANA, almost by definition, is a scale-up deployment.
  • SAP Applications: SAP is typically deployed in a three-tier architecture, and the database layer cannot be scaled merely by adding servers. Properly scaling to handle larger database loads requires deploying them on hardware that is suited to house both the SAP applications and their associated databases. A scale-up deployment can also be used to consolidate multiple instances of SAP scattered around the organization onto fewer four- or eight-socket servers.
  • Microsoft SQL Server: Microsoft designed SQL Server to scale up rather than to scale out in a single-instance scenario. While it supports many high-availability features such as clustering, a single SQL Server database is not designed to be deployed across multiple server platforms as a single virtual instance. This means that scaling is best achieved by upgrading the underlying hardware on which the database runs rather than by adding instances on separate servers.
  • Microsoft Exchange: Historically, many customers added servers to grow capacity. This approach led to server sprawl and to time-consuming, inefficient Microsoft Exchange systems management. Today, multirole deployments combine Mailbox, Hub Transport and Client Access Server (CAS) roles onto a single server in a particular service delivery location.
  • Enterprise Custom Applications: Custom applications, many of which are legacy applications running on aging centralized hardware, drive many mission-critical workloads in enterprises today. And as demands on these applications grow, the underlying hardware is not always able to keep pace. Scale-up advantages include the opportunity to add workloads on standardized four-socket servers running Microsoft Windows or Linux — in place of operating systems that have reached their end of life.

Consolidation benefits

By consolidating to fewer and more powerful X6 servers, you can achieve real business benefits of reduced operating costs, reduced power and cooling costs and reduced software licensing costs. You can improve utilization, improve application performance and extend data centre life.

By consolidating workloads from scale-out x86 servers to scale-up X6 servers, you can experience savings in a number of categories. Without consolidation, these costs will increase because larger numbers of physically separate servers are needed to support the workloads and to support all of the end users accessing the servers. The categories of consolidation savings are listed below.

  • Reduced software licensing costs: A major factor to consolidating onto scale-up systems includes the reduction in the number of instances of supporting software — such as operating system licenses and third party licenses. Since many major software packages are licensed on a per-processor or per-core basis, reducing the number of systems can significantly lower annual software supports cost.
  • Improved IT staff productivity: Using scale-up servers reduces the total number of processors and servers under management. With fewer physical servers to maintain, server administrators are freed up to focus on higher-value-added tasks and expand process automation applications without adding overhead.
  • Reduced energy consumption: With a focus on global warming and fluctuating energy cost, many of you now have an objective to reduce energy consumption in your data centres. Reducing the server footprint onto fewer, more modern systems can dramatically lower the energy requirements and the power bill for an organization.
  • Increased resource utilization (CPU, memory, and network): Combining workloads on scale-up servers rather than having them on dedicated hardware improves utilization of valuable compute resources.
  • Reduced server hardware cost: In many cases, by replacing multiple two-socket servers with much more powerful four- and eight-socket X6 servers, you can reduce your initial hardware purchase price. That gives you the immediate benefit of reducing server hardware today, but also the cost savings associated with deferred future hardware purchases.
  • Reduced end-user productivity losses: X6 scale-up servers with mission-critical RAS capabilities can incur less unplanned downtime than scale-out. Less downtime translates to better user productivity with less lost time and fewer IT help desk and support recovery time (IT productivity).
  • Improved performance: X6 scale-up server products are best suited for highly demanding workloads because they have faster and more cores, giving them the ability to run workloads faster and more efficiently than before.
  • Accelerated application deployment: With virtualized, scale-up X6 servers, you can accelerate the deployment of new applications initiatives. Projects that previously took weeks to size, purchase, install and configure new server resources can now be ready in hours. By decoupling specific application requirements from physical servers, clients can set up and reconfigure application environments much more rapidly and make much better use of computing resources.
  • Extended data centre life: Reducing the number of physical servers alleviates pressure on data centre capacity, enabling you to defer expensive new build outs.

As workload performance demands increase, memory requirements and scalability needs increase, the need for scale-up, four-socket servers increases. At the same time, the need to reduce cost, drives the consolidation towards four-socket servers. Handling high-performing, scale-up consolidation of mission-critical workloads is where the Lenovo x3850 X6 shines.

For more information, view System x3850 X6 and System x3950 X6.

This post first appeared on


Building the next-gen data centre

Where traditional and web-scale apps co-exist