Platform Settings for Dell PowerEdge Servers

Operating System Tuning Parameters

tuned-adm

This command line utility allows you to switch between user definable tuning profiles. Several predefined profiles are already included. You can even create your own profile, either based on one of the existing ones by copying it or make a completely new one. The distribution provided profiles are stored in subdirectories below /usr/lib/tuned and the user defined profiles in subdirectories below /etc/tuned. If there are profiles with the same name in both places, user defined profiles have precedence.

Profile used:
- throughput-performance - Broadly applicable tuning that provides excellent performance across a variety of common server workloads

Firmware / BIOS / Microcode Settings

ADDDC Setting

Default: Enabled

Adaptive Double DRAM Device Correction
When enabled, failing DRAMs are dynamically mapped out. This action can have some impact on system performance under certain workloads. This feature only applies to x4 DIMMs and when Fault Resilient Mode (FRM) is disabled.

HBM Mode

Default: Flat

Settings:

• Flat: HBM and DDR are exposed as separate regions.
• Cache: DDR is cached (symmetric DDR population is required). Intel SGX and MKTIME are not supported.

This field selects the High Bandwidth Memory (HBM) mode.

DIMM Self Healing on Uncorrectable Memory Error

Default: Enabled

Post Package Repair (PPR) on Uncorrectable Memory Error
Disabling this feature may improve memory performance for some workloads.

Logical Processor

Default: Enabled

Each processor core supports up to two logical processors. When set to Enabled, the BIOS reports all logical processors. When set to Disabled, the BIOS only reports one logical processor per core. Generally, higher processor count results in increased performance for most multi-threaded workloads and the recommendation is to keep this enabled. However, there are some floating point/scientific workloads, including HPC workloads, where disabling this feature may result in higher performance.

Virtualization Technology

Default: Enabled

When set to Enabled, the BIOS will enable processor Virtualization features and provide the virtualization support to the Operating System (OS) through the DMAR table. In general, only virtualized environments such as VMware(r) ESX (tm), Microsoft Hyper-V(r) , Red Hat(r) KVM, and other virtualized operating systems will take advantage of these features. Disabling this feature is not known to significantly alter the performance or power characteristics of the system, so leaving this option Enabled is advised for most cases.

DCU Streamer Prefetcher

Default: Enabled

Data Cache Unit (DCU) - this setting can affect performance depending on the application running on the server. Recommended for High Performance Computing applications.

Sub NUMA Cluster

Default: Disabled

When set to Enabled / 2-way Clustering / 4-way Clustering:
Sub NUMA Clustering (SNC) is a feature for breaking up the LLC into disjoint clusters based on address range, with each cluster bound to a subset of the memory controllers in the system. It improves average latency to the LLC.

UMA Based Clustering Status

Default: Quadrant

Quadrant is the default mode when Sub NUMA cluster is disabled. If Sub NUMA Clustering is not disabled, this setting is disabled.

x2APIC Mode

Default: Enabled

Compared to traditional xAPIC architecture, x2APIC extends the processor addressbility and enhances interrupt delivery performance. Virtualization Technology must be enabled to allow enabling and disabling of this option. This option is forced to Disabled when Virtualization Technology is disabled.

MADT Core Enumeration

Default: Round Robin

• Linear - processor cores are enumerated across all Dies within a Socket before enumerating additional Sockets for a linear distribution of interrupt controllers for the OS.
• Round Robin - processor cores are enumerated across all Dies within a Socket before enumerating additional Sockets for a linear distribution of interrupt controllers for the OS.

This field determines how BIOS enumerates processor cores in the ACPI MADT table.

LLC Prefetch

Default: Enabled

Disable LLC (Last Level Cache) Prefetch on all threads.

Dead Line LLC Alloc

Default: Enabled
Enabled - opportunistically fill dead lines in the LLC (Last Level Cache).
Disabled - never fill dead lines in LLC.

Optimizer Mode

Default: Auto

Settings:

• Auto: enabled when CPU Power Management is set to Max Performance
• Enabled: enabled regardless of the CPU Power Management setting
• Disabled: Turns off the feature

Tunes for CPU Performance. Startng with GEN 4 Intel Scalable processors, this option may not available on server configurations where the CPUs are air cooled.

Opportunistic Snoop Broadcast

Default: Auto

Opportunistic Snoop Broadcast (OSB) is a feature within the PCIe protocol that enhances system performance by reducing latency and improving data transfer efficiency. Auto is controlled by SI compatibility and Directory Mode Enable/Disable

UPI Prefetch

Default: Enabled

Mechanism to get the memory read started early on DDR bus. The UPI Rx path will spawn a MemSpecRd to iMC directly.

System Profile

Default: Performance Per Watt (DAPC)

When set to Custom, other settings can changed for Memory Patrol Scrub, CPU Power Management, CIE, C States, Energy Efficiency Policy.

CPU Power Management

Default: System DBPM (DAPC)

Allows selection of CPU power management methodology.

• Maximum Performance: typically selected for performance-centric workloads where it is acceptable to consume additional power to achieve the highest possible performance for the computing environment. This mode drives processor frequency to the maximum across all cores (although idled cores can still be frequency reduced by C-state enforcement through BIOS or OS mechanisms if enabled). This mode also offers the lowest latency of the CPU Power Management Mode options, so is always preferred for latency-sensitive environments. OS DBPM is another performance-per-watt option that relies on
• OS DBPM: performance-per-watt option that relies on the operating system to dynamically control individual cores in order to save power.

Energy Efficient Turbo

Default: Enabled

Energy Efficient Turbo (EET) is a mode of operation where a processor's core frequency is adjusted within the turbo range based on workload.

C1E

Default: Enabled

When set to Enabled, the processor is allowed to switch to minimum performance state when idle.

C States

Default: Enabled

C States allow the processor to enter lower power states when idle. When set to Enabled (OS controlled) or when set to Autonomous (if Hardware controlled is supported), the processor can operate in all available Power States to save power, but may increase memory latency and frequency jitter.

Memory Patrol Scrub

Default: Standard

Patrol Scrubbing searches the memory for errors and repairs correctable errors to prevent the accumulation of memory errors. When set to Disabled, no patrol scrubbing will occur. When set to Standard Mode, the entire memory array will be scrubbed once in a 24 hour period. When set to Extended Mode, the entire memory array will be scrubbed more frequently to further increase system reliability.

Energy Efficiency Policy

Default: Balanced Performance

The CPU uses the setting to manipulate the internal behavior of the processor.

• Balanced Performance: targets better power savings at the expnse of performance.
• Performance: targets better performance at the expense of power savings.

CPU Interconnect Bus Link Power Management

Default: Enabled

When Enabled, CPU interconnect bus link power management can reduce overall system power a bit while slightly reducing system performance.

PCI ASPM L1 Link Power Management

Default: Enabled

When Enabled, PCIe Advanced State Power Management (ASPM) can reduce overall system power a bit while slightly reducing system performance.

Fan Speed Offset

Default: Off

Configuring this option allows additional cooling to the server. In case hardware is added (example, new PCIe cards), it may require additional cooling. A fan speed offset causes fan speeds to increase (by the offset % value) over baseline fan speeds calculated by the Thermal Control algorithm.