Multithreaded Parallel Writeback: Vivo’s Exploration of Page Cache Write Acceleration

The article examines Linux's page‑cache writeback mechanism, explains why the single‑threaded writeback path becomes a bottleneck under heavy writes, and details Vivo's multithreaded writeback patches—including inode‑to‑context mapping and sysfs‑controlled thread counts—that achieve up to 2.4 GB/s on XFS and a 22 % speedup on F2FS, while also discussing fragmentation trade‑offs and optimal thread‑to‑allocation‑group ratios.

F2FSFilesystemXFS

0 likes · 8 min read

Multithreaded Parallel Writeback: Vivo’s Exploration of Page Cache Write Acceleration

Linux Kernel Journey

Nov 7, 2025 · Fundamentals

Self‑Destructing Page Cache: Huawei’s ModelFS and vivo’s F2FS Uncached Buffer I/O Innovations

The article examines how Huawei’s ModelFS makes prefetch and memory reclamation programmable and how vivo adapts F2FS to support uncached buffer I/O, enabling AI model weights to be loaded without lingering in the page cache and eliminating kswapd overhead.

AI model loadingF2FSModelFS

0 likes · 4 min read

Self‑Destructing Page Cache: Huawei’s ModelFS and vivo’s F2FS Uncached Buffer I/O Innovations

vivo Internet Technology

Oct 30, 2024 · Fundamentals

vivo's Linux Kernel Innovation at the 19th China Linux Kernel Developer Conference

At the 19th China Linux Kernel Developer Conference, vivo unveiled nine open‑source innovations—including DMA‑BUF DIO for AI model loading, ZHP memory compression, EROFS and f2fs filesystem enhancements, and I/O optimizations—contributing significant performance gains and demonstrating its commitment to Linux kernel advancement worldwide.

DMA-BUFEROFSF2FS

0 likes · 6 min read

vivo's Linux Kernel Innovation at the 19th China Linux Kernel Developer Conference

OPPO Kernel Craftsman

Jun 14, 2024 · Fundamentals

In-depth Analysis of F2FS Filesystem Superblock, SIT, NAT, and SSA Structures

The article provides a detailed code-level walkthrough of F2FS’s superblock, Segment Information Table, Node Address Table, Summary Area, and Main Area structures, explaining each field, entry layout, and their roles in managing segments, inodes, and data within the filesystem.

F2FSFilesystemNAT

0 likes · 9 min read

In-depth Analysis of F2FS Filesystem Superblock, SIT, NAT, and SSA Structures

OPPO Kernel Craftsman

Jun 7, 2024 · Fundamentals

Understanding the F2FS File System Structure and Operations

The article walks through the Flash Friendly File System’s on‑disk layout—zones, sections, segments, blocks, SuperBlock, checkpoint, SIT, NAT, and SSA—showing how formatting, mounting, creating, modifying, and deleting files updates these structures, offering a practical guide for kernel and storage engineers.

F2FSFilesystem Analysisfile system

0 likes · 26 min read

Understanding the F2FS File System Structure and Operations

Liangxu Linux

Jan 21, 2024 · Fundamentals

Choosing the Right Linux File System: ext4, Btrfs, XFS, ZFS, F2FS, and OverlayFS

This article reviews the key features, advantages, and command‑line examples of major Linux file systems—including ext4, Btrfs, XFS, ZFS, F2FS, and OverlayFS—to help you select the most suitable one for performance, reliability, and specific workload requirements.

BtrfsF2FSXFS

0 likes · 8 min read

Choosing the Right Linux File System: ext4, Btrfs, XFS, ZFS, F2FS, and OverlayFS

OPPO Kernel Craftsman

Jan 22, 2020 · Fundamentals

Understanding the Flash‑Friendly File System (F2FS): Design, Implementation, and Future Directions

F2FS is a log‑structured, flash‑aware file system that transforms random writes into sequential ones, uses segment‑based layout, NAT indexing, and hot‑cold data segregation with sophisticated garbage‑collection to improve SSD performance, and is now deployed in Android devices with ongoing enhancements such as online resizing and cold‑data compression.

F2FSGarbage CollectionStorage Management

0 likes · 17 min read

Understanding the Flash‑Friendly File System (F2FS): Design, Implementation, and Future Directions