Version 2.2 of Intel® Rack Scale Design Released—Supports Purley Advanced Telemetry and TPM
Intel® Rack Scale Design (Intel® RSD) 2.2 supports the Intel® Xeon® Scalable Family platform with out-of-band (OOB) discovery of features such as Trusted Platform Module (TPM), advanced telemetry and FPGA accelerator cards. In addition, OOB telemetry support provides detailed information about the health and status of infrastructure components to aid in provisioning and for capacity, performance, power, and thermal management.
The agentless OOB implementation continuously gathers telemetry data without impacting the performance of running applications, and also improves security by isolating management controls for the data network. Version 2.2 auto-discovers PCIe add-in FPGA accelerator cards to allow composition of nodes with FPGAs, and enabling orchestration software to assign FPGA resources to specific workloads. TPM support includes the ability to discover, enable, disable and clear TPMs. The latest reference documents are available on the Intel® RSD web site and the reference code is on Intel® RSD GitHub.
Intel® RSD Telemetry Helps Reduce DC Energy Costs
Customers are already using the new telemetry capabilities of Intel® RSD 2.2 to enable advanced data center solutions. For example, cloud service provider (CSP) SafeDX* is using Intel® RSD to implement improved temperature controls to reduce energy consumption.
With cooling equipment consuming 40% of the total data center power budget, cloud service providers (CSPs) and enterprises are looking to reduce cost by improving power usage efficiency (PUE). A growing trend is to save power by operating data centers at higher ambient temperatures. Employing this technique successfully requires precise monitoring of equipment to keep local temperatures within safe maximums.
The SafeDX solution uses:
- Telemetry capabilities built into the Foxconn R-5211* server based on the Intel® Xeon® Scalable processor platform.
- Intel® RSD with its support for OOB telemetry gathering and communication via open APIs.
- Intel® Intelligent Data Center Management (Intel® IDCM) software.
Together, these technologies provide precise, local thermal and power monitoring of racks and individual servers, enabling an eﬀective feedback and control loop to improve data center cooling efficiency. SafeDX* has been able to demonstrate a 17% cooling energy reduction using this closed loop approach, and is on track to deliver a PUE of 1.5 in the next deployment.
The SafeDX* energy efficiency architecture shown above employs temperature sensing at the device level, Intel® RSD software components and APIs at the control level to access and relay the sensor data, and IDCM software at the management layer. Working together, Intel® RSD software components (PSME, RMM and PODM) collect telemetry data such as fan speed, airﬂow, CPU thermal margin, DIMM thermal margin, inlet and outlet temperatures, CPU/memory/ system utilization, and power consumption data from each rack and server node.
PODM relays all this information to IDCM, which maintains overall control of the cooling system. IDCM provides backend services including a sampler service, Thermal Control Strategy (TCS) service, and a database. The sampler service leverages PODM APIs to gather thermal and power telemetry data (servers and rack infrastructure) and stores it in the IDCM database. The TCS service analyzes the data and calculates efficiency metrics such as return temperature index (RTI) and rack cooling index (RCI). Based on its analysis, IDCM sends commands to the air conditioning units to adjust thermal settings. Real-time data and metrics are also presented to operators through a GUI dashboard.
We expect to see much more data center innovation in the future based on the new hyperscale monitoring and control capabilities provided by Intel® RSD via open, modern RESTful APIs. Read mode about the Foxconn/SafeDX energy efficiency solution here. Also check out the related video.
More on Intel® Rack Scale Design
To learn more about Intel® RSD or get more involved in the Intel® RSD ecosystem, check out the Intel® RSD website. Or contact your OEM or Intel sales representative now for an evaluation of Intel® RSD based systems. If you are planning to attend the OCP Summit*, please visit Intel and our partners to see Intel® RSD for yourself.