ReferenceInformation-oriented
Reference
Exact, complete technical facts: tools, mount options, procfs, module parameters, limits, the on-disk format, and error meanings.
Reference pages describe what cetrafs is and does, completely and without opinion. Look things up here while you work. For guidance on what to do, see the how-to guides; for why, see Concepts.
All three userspace tools share one exit-code convention:
| Exit | mkfs.cetra | fsck.cetra | defrag.cetra |
|---|---|---|---|
0 | Success | Clean | Done |
1 | Couldn’t create | Problems found | Failed |
2 | Bad invocation | Bad invocation | Bad invocation |
3 | Device inaccessible, or mounted locally or by a live peer | Couldn’t examine the device | n/a |
mkfs.cetra
Create a cetrafs volume: synopsis, every option with its default and bounds, auto-tuning, and exit codes.
fsck.cetra
Check and repair a cetrafs volume offline: synopsis, the four passes, what -r repairs and refuses, and exit codes.
defrag.cetra
Online per-file defragmentation: synopsis, preconditions, refusals and exit codes.
Mount options
The cetrafs mount options, the read-only observer mode, the cluster-wide file-lock mode, and remount rules.
/proc/fs/cetrafs
Every file and field cetrafs publishes under /proc/fs/cetrafs/<dev>/: info, properties, cluster and the writable controls.
Module parameters
cetrafs kernel module parameters: defaults, meaning, and which ones are safe in production.
Limits and unsupported operations
Hard limits of the on-disk format, operations cetrafs deliberately does not support, and the requirements a deployment must meet.
On-disk format
The cetrafs on-disk layout: superblock, Zone and Block Group descriptors, Node Registry, journals, inodes, extents, directory entries and feature flags.
Troubleshooting
Symptoms, error messages and counters, with what each one means and where to go next.
Glossary
Definitions of the terms used in the cetrafs docs, from ATS and COMPARE AND WRITE to extents, fence epochs, Zone Groups and the Node Registry.