Get the latest tech news

EROFS Being Extended To Handle Massive Amounts Of Data For AI Model Training


The EROFS open-source, read-only Linux file-system is set to be extended with the upcoming Linux 6.15 kernel cycle to support massive amounts of data to support AI model training.

In advance of the Linux 6.15 merge window opening following the v6.14 kernel release, EROFS is seeing 48-bit addressing support added to handle larger file-systems with an emphasis on making the file-system more suitable for AI training purposes and other large-scale data archival needs. However, several new use cases now require larger capacity support: - Massive datasets for model training to boost random sampling performance for each epoch; - Object storage clients using EROFS direct passthrough. In addition, it introduces an mtime field to 32-byte compact inodes for basic timestamp support, as well as expands the superblock root NID to an 8-byte rootnid_8b for out-of-place update incremental builds.

Get the Android app

Or read this on Phoronix

Read more on:

Photo of data

data

Photo of AI model training

AI model training

Photo of massive amounts

massive amounts

Related news:

News photo

Airbyte launches new connectors to help companies better leverage their data

News photo

Attackers swipe data of 500k+ people from Pennsylvania teachers union

News photo

Western Alliance Bank notifies 21,899 customers of data breach