Cache Aware Scheduling Shows Nice Wins for AMD Zen 5 on PostgreSQL, Valkey
Recorded: May 29, 2026, 10 a.m.
| Original | Summarized |
Cache Aware Scheduling Shows Nice Wins For AMD Zen 5 On PostgreSQL, Valkey, Network Performance - Phoronix
Articles & Reviews Articles & Reviews News Archive Forums Premium Categories Computers Display Drivers Graphics Cards Linux Gaming Memory Motherboards Processors Software Storage Operating Systems Peripherals Cache Aware Scheduling Shows Nice Wins For AMD Zen 5 On PostgreSQL, Valkey, Network Performance The long-in-development work on Cache Aware Scheduling looks like it will come to a head soon with it looking like Cache Aware Scheduling will land for Linux 7.2. Ahead of the upcoming merge window I ran some fresh benchmarks looking at different areas where this feature is shining. It's been a few months since last trying Cache Aware Scheduling on AMD EPYC Turin as well as Intel Xeon 6 to great success. This round of benchmarking was on an AMD Ryzen Threadripper 9980X within the System76 Thelio Workstation. Cache Aware Scheduling can help improve Linux performance on modern CPUs with multiple cache domains, such as AMD's modern processors from Ryzen to EPYC. The scheduler tries to help ensure that tasks sharing data are colocated to the same last level cache (LLC) domain for ensuring better cache locality and reducing cache misses/bouncing. 6 Comments - Next Page Tweet
Page 1 - IntroductionPage 2 - Cache Aware Scheduling BenchmarksPage 3 - Cache Aware Scheduling BenchmarksPage 4 - Cache Aware Scheduling Benchmarks Page: 1 2 3 4 Next Page Related Articles Latest Linux News Linux 7.2 To Bring Graphics Driver Fix For Old Integrated Graphics On Intel Sandy Bridge Radeon Software For Linux 26.12 Brings Ubuntu 26.04 Support Intel Sends Out Revised Linux Patches For Directed Package Thermal Interrupts Linux 7.2's Open-Source Nouveau Driver To Finally Support The NVIDIA GA100 Arm Announces Metis: Agentic AI Security Framework QEMU Shifting On AI Policy To Allow Some AI/LLM-Generated Contributions Qualcomm Snapdragon C Announced For $300+ Laptops Intel Arc G-Series Processors Announced For Handheld Gaming Devices KDE Plasma 6.7 Beta 2 Released With More Bug Fixes 24 Years After The ATI R300 Launched, Open-Source R300 Driver Continues With Big Rework GTK Introduces Snapping Feature For Better Fractional Scaling Experience Show Your Support, Go Premium Latest Featured Articles Cache Aware Scheduling Shows Nice Wins For AMD Zen 5 On PostgreSQL, Valkey, Network Performance NVIDIA Vera CPU Benchmarks: Olympus Cores Delivering The Best Performance Ever Seen On ARM Linux Provides Better Performance With The AMD Ryzen 9 9950X3D2 Over Windows 11 NVIDIA RTX PRO Blackwell Performance Delivering Excellent Linux Performance Support Phoronix Phoronix Media Contact Phoronix Premium Support Phoronix Share Facebook Legal Disclaimer, Privacy Policy, Cookies | Privacy Manager | Contact |
The work on Cache Aware Scheduling is nearing completion, with expectations that it will be integrated into Linux 7.2. This feature is designed to enhance the performance of Linux systems running on modern Central Processing Units that feature multiple cache domains, such as those found in AMD processors ranging from Ryzen to EPYC. The fundamental goal of Cache Aware Scheduling is to optimize task placement by ensuring that tasks sharing related data are allocated to the same last level cache last level cache domain (LLC). This operational strategy aims to improve cache locality within the system, thereby minimizing cache misses and reducing the performance penalty associated with cache bouncing. These architectural optimizations are particularly relevant for contemporary multi-core and multi-cache designs. As demonstrated in recent benchmarking efforts, implementing Cache Aware Scheduling yields notable performance advantages when running specific workloads on these advanced CPUs. The testing was conducted using an AMD Ryzen Threadripper 9980X processor within a System76 Thelio Workstation environment. The benchmark setup utilized Ubuntu 26.04 and a custom kernel built upon a Linux 7.1-rc2 base. The results from these evaluations highlighted significant performance gains in areas relevant to database operations and networking. Specifically, the scheduling feature demonstrated favorable outcomes in benchmarks focusing on PostgreSQL, Valkey, and overall network performance. These findings suggest that the scheduler effectively leverages the nuanced cache structure of modern CPUs to achieve superior resource utilization and reduced latency for data-intensive applications. The research, documented by Michael Larabel, points toward the practical benefits of fine-grained cache awareness in influencing overall system throughput for demanding software environments. |