ceph/stack.yaml at main · agentic-stacks/ceph · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
name: ceph
namespace: agentic-stacks
version: 0.1.0
description: >
  Complete operational knowledge for deploying, managing, and operating
  production Ceph storage clusters using cephadm on bare metal. Covers
  RBD, CephFS, and RGW services across Ceph Reef (18.2.x) and Squid (19.2.x).

repository: https://github.com/agentic-stacks/ceph

target:
  software: ceph
  versions:
    - "18.2.x"
    - "19.2.x"

skills:
  - name: training
    entry: skills/training/
    description: Interactive training — teaches this stack's domain to new users

  - name: concepts
    entry: skills/foundation/concepts
    description: Ceph architecture, CRUSH maps, placement groups, pools, BlueStore
  - name: hardware-planning
    entry: skills/foundation/hardware-planning
    description: Disk sizing, CPU/RAM ratios, network bandwidth, node role planning
  - name: host-preparation
    entry: skills/foundation/host-preparation
    description: OS prerequisites, NTP, firewall ports, container runtime, cephadm install
  - name: bootstrap
    entry: skills/deploy/bootstrap
    description: cephadm bootstrap, initial MON/MGR/OSD deployment, dashboard setup
  - name: networking
    entry: skills/deploy/networking
    description: Public vs cluster network design, VLAN, bonding, MTU configuration
  - name: services
    entry: skills/deploy/services
    description: RBD pool creation, CephFS/MDS deployment, RGW S3 gateway setup
  - name: health-check
    entry: skills/operations/health-check
    description: Cluster health interpretation, OSD states, PG states, alert triage
  - name: scaling
    entry: skills/operations/scaling
    description: Add/remove OSDs and hosts, expand services, rebalance
  - name: upgrades
    entry: skills/operations/upgrades
    description: Rolling upgrades within and across Reef/Squid versions
  - name: backup-restore
    entry: skills/operations/backup-restore
    description: Pool snapshots, RBD mirroring, RGW multisite, disaster recovery
  - name: pool-management
    entry: skills/operations/pool-management
    description: CRUSH rules, erasure coding profiles, tiering, quotas
  - name: certificate-mgmt
    entry: skills/operations/certificate-mgmt
    description: Dashboard TLS, RGW TLS, internal messenger encryption
  - name: troubleshooting
    entry: skills/diagnose/troubleshooting
    description: Symptom-based diagnostic trees for common Ceph failure modes
  - name: performance
    entry: skills/diagnose/performance
    description: Benchmarking with rados bench/fio, slow OSD diagnosis, bottleneck ID
  - name: known-issues
    entry: skills/reference/known-issues
    description: Version-specific bugs and workarounds for Reef and Squid
  - name: compatibility
    entry: skills/reference/compatibility
    description: Ceph version × kernel × container image × client compatibility
  - name: decision-guides
    entry: skills/reference/decision-guides
    description: Replicated vs erasure coding, BlueStore tuning, network topology

project:
  structure:
    - cluster-spec.yaml
    - cluster-spec.yaml.orig
    - service-specs/
    - ceph.conf
    - scripts/
    - docs/

requires:
  tools:
    - name: cephadm
      description: Ceph orchestrator for container-based deployment and lifecycle
    - name: ceph
      description: Ceph CLI for cluster operations and status
    - name: podman
      description: Container runtime (default for cephadm on modern distros)

depends_on: []