Managing High Temperatures in Intel® Xeon® Processor

Environment

The sample system, a server board S2600ST with a dual-processor Intel® Xeon® Processor configuration, is experiencing temperature discrepancies between the two processors.

CPU0 is operating within normal temperature ranges, around 70°C, while CPU1 is consistently exceeding the threshold temperature, reaching as high as 105°C.

Despite the system allocating the same workload to both processors, CPU1 is clearly experiencing overheating issues.

Upon initial installation, one of the processors was running at an alarming 120 degrees. Notably, both processors are using the same heatsink, suggesting that the issue may not be related to the cooling mechanism.

The system logs have also detected multiple errors, as evidenced by the Sysinfo logs, which may be related to the temperature issues.

Summary: 

• A dual-processor configuration on a server board S2600ST is experiencing temperature discrepancies.
• CPU0 is operating within normal temperature ranges, while CPU1 is exceeding the threshold temperature.
• Both processors are using the same heatsink, and the system is allocating the same workload to both.
• Multiple errors have been detected in the Sysinfo logs, which may be related to the temperature issues.

Error Message on Logs: 

Critical Interrupt PCIe Fatal Error (#0x04)
CRITICAL event: PCIe Fatal Error reports a fatal PCI Express Surprise Link Down error. (BUS:0xAE, DEV:0x00, FUN:0x00)
CRITICAL event: P1 Status reports CATERR has occurred.(Unspecified)
CRITICAL event: P2 Status reports CATERR has occurred.(Unspecified)
CRITICAL event: SPS FW Health reports SPS Health event type FW status. PECI over DMI interface error. Recovery via CPU Host reset or platform reset. DMI timeout of PECI request

If your Intel® Xeon® Processor reports a high temperature, it is crucial to take immediate action to prevent potential damage or throttling, which can impact system performance.

Here are some suggested items to help you identify and resolve the issue:

Monitoring and Initial Steps

1. Monitor the temperature: Use software tools like Intel® Extreme Tuning Utility (for Windows*) or lm-sensors and watch commands (for Linux*) to monitor your CPU temperature in real-time. Validate that the reported temperature is consistently high under certain conditions (for example, during heavy loads).
2. Check the cooling system: Ensure the cooling system (air or liquid) is properly installed and functioning correctly. For air cooling, check that the CPU fan is working and that its vents are not clogged with dust. For liquid cooling, ensure the system is filled correctly, there are no leaks, and the radiator fans are operational.

Maintenance and Adjustments

3. Dust cleaning: Dust buildup can significantly impede the cooling efficiency of your system. Turn off your computer, unplug the power cord, and carefully clean dust from the CPU cooler, RAM, Graphics Card, Power Supply, and case fans using compressed air.
4. Reapply thermal paste: Over time, the thermal paste between the CPU and its cooler can dry out, reducing cooling efficiency. Carefully remove the cooler, clean the surface of the CPU and cooler, apply a new layer of thermal paste, and then reattach the cooler.
5. Adjust fan settings: Use BIOS settings or third-party software to adjust fan speeds. Increase the speed of the CPU fan and case fans, especially during heavy load conditions, to improve airflow and heat dissipation.

Environmental and Software Considerations

6. Environmental factors: Ensure good airflow around the computer case. Don’t operate the system in a sealed or poorly ventilated area. Check the room temperature, as operating the system in a hot environment can increase its internal temperature.
7. Software and load management: If the high temperature is noticed during specific tasks (for example, video editing, 3D modeling, or gaming), consider reducing the load on the CPU or upgrading your cooling solution. Turn off any unnecessary background applications or services that could be contributing to high CPU usage.

Updates and Professional Help

8. BIOS and driver updates: Ensure your system’s BIOS is up to date, as newer versions might include improvements for temperature management or fan control. Keep your operating system, drivers (especially for the motherboard and graphics card), and any software related to your cooling system updated.
9. Thermal throttling considerations: If your CPU is thermally throttling (reducing its speed to protect itself from overheating), it can significantly impact performance. Addressing the cooling issues promptly is essential to prevent this.
10. Professional help: If none of the above steps resolve the issue, or if you're not comfortable with these procedures, consider seeking help from a professional. There could be a fault with the cooling system, the CPU itself, or another component.

Intel Recommendations and Specifications

• Expected behavior: High temperatures may occur due to workload shifts to specific cores under Intel® Turbo Boost Technology (Intel® TBT). This increases CPU core power/thermal density and can trigger the Thermal Control Circuit (TCC) event.
• Thermal specifications: Check the thermal specifications for your processor model, including TCASE_MAX (maximum case temperature) and THROTTLE Target temperature. For example, Intel Xeon processors have specific thermal thresholds, such as TCASE_MAX of 85°C and THROTTLE Target temperatures ranging from 105°C to 108°C, depending on the model.
• Cooling solution: Ensure your cooling solution is adequate for the processor's thermal density and workload. If the heatsink or cooling system is insufficient, it may lead to higher temperatures and thermal spikes.
• Environmental factors: Consider ambient temperature conditions. Extreme environments may require specialized cooling solutions or designs to prevent overheating or freezing issues.
• Thermal analysis tools: Utilize Intel® Power and Thermal Analysis Tool (Intel® PTAT) or similar tools to analyze thermal behavior.
• Processor configuration: Verify the processor's configuration and workload settings. Certain configurations, such as Intel Speed Select Technology (Intel® SST), may impact thermal performance and require adjustments to cooling solutions.

By following these steps and considering Intel's recommendations, you can effectively manage high temperatures in your Intel Xeon processor, ensuring optimal performance and longevity.

Remember, maintaining optimal operating temperatures is vital for your CPU's health and performance. Regular monitoring and preventive measures can help avoid issues related to overheating.

If the issue persists or you need further assistance, consult Intel's technical support or refer to the processor's specific thermal and mechanical design guide for detailed recommendations, available at Resource & Documentation Center.

• 1st Generation Intel® Xeon® Scalable Processors
• 2nd Generation Intel® Xeon® Scalable Processors
• 3rd Generation Intel® Xeon® Scalable Processors
• 4th Generation Intel® Xeon® Scalable Processors
• 5th Generation Intel® Xeon® Scalable Processors
• Intel® Xeon® 6 Processors
• Resource & Documentation Center
• Intel Extreme Tuning Utility
• Intel Speed Select Technology
• Intel Power and Thermal Analysis Tool