Sep 30, 2025 · Fundamentals

How Merging cfs_rq and sched_entity Boosts Linux Scheduler Cache Hits by 31%

Google engineer Zecheng Li’s patch series merges the CFS scheduler’s cfs_rq and sched_entity structures and switches to a per‑CPU allocator, cutting LLC miss rates by up to 31% and raising kernel IPC by up to 25% on AMD and Intel platforms, with negligible regression.

CFSLinuxScheduler

0 likes · 8 min read

How Merging cfs_rq and sched_entity Boosts Linux Scheduler Cache Hits by 31%

Liangxu Linux

Sep 2, 2020 · Fundamentals

Why System Calls Are So Expensive: From INT 0x80 to vDSO

This article explains how Linux system calls work, compares their overhead to regular function calls, and details the three implementation methods—software interrupts, fast syscall instructions, and the virtual dynamic shared object (vDSO)—including their performance trade‑offs and practical usage.

INT 0x80Linuxkernel performance

0 likes · 16 min read

Why System Calls Are So Expensive: From INT 0x80 to vDSO

How Merging cfs_rq and sched_entity Boosts Linux Scheduler Cache Hits by 31%

Why System Calls Are So Expensive: From INT 0x80 to vDSO

Why System Calls Are So Expensive: From INT 0x80 to vDSO