This repository has been archived on 2026-07-30. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
nixos/modules/build-types/ha-server.nix
T
beatzaplentyandClaude Sonnet 4.6 d740064a35
Check NixOS configurations / eval-hosts (pull_request) Successful in 10m37s
fix(ha): all 7 acceptance tests pass — targetctl, fencing, failover, data integrity
Deploy/init fixes:
- iscsi-target.nix: targetctl binary is in rtslib-fb (python3 env), not
  targetcli-fb — fixes ExecStart and ExecStop for the targetctl.service
- deploy.sh: _patch_targetctl() applies runtime dropin to both nodes before
  cluster-init so Pacemaker can manage the iSCSI target from first start
- cluster-init.sh: replace crm configure heredoc with cibadmin --replace XML
  (pacemaker-4.0 schema: globally-unique in meta_attributes, promoted-max/
  promoted-node-max, Promoted role in constraints); force_unmount=true on
  xfs-data; DRBD promote timeout 240s
- cluster-config.nix: add crm-fence-peer.sh/crm-unfence-peer.sh handlers;
  update fencing comment to reflect resource-only + Pacemaker-aware handler
  replacing STONITH during testing phase
- ha-server.nix: add openiscsi to systemPackages for T4 iscsiadm availability

Acceptance test fixes:
- acceptance-tests.sh: fix ((PASS++)) set -e bug → PASS=$((PASS+1));
  detect Active/Standby dynamically via drbdadm role (Pacemaker can promote
  either node); T4 bash TCP probe instead of iscsiadm; T5 timeout 120s;
  T6 echo|sudo tee for root-owned XFS write (bash -c redirect runs as nixos
  not sudo — permission denied); use ns cat / ns rm for root-owned reads

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HaH1cSGvhogRP5ExoF6nD8
2026-07-28 19:03:39 +10:00

49 lines
2.0 KiB
Nix

# HA file server build type: DRBD + XFS + LIO iSCSI + NFS, managed by
# Corosync + Pacemaker. Both ha-server-1 and ha-server-2 use this type.
#
# NFS start/stop:
# services.nfs.server.enable = true configures /etc/exports, wires up
# rpcbind, and loads kernel modules — but nfs-server.service.wantedBy is
# force-cleared so systemd does NOT auto-start it at boot. Pacemaker's
# ha-group resource group (configured by scripts/ha/cluster-init.sh)
# starts and stops nfs-server as part of the failover sequence after the
# XFS mount and iSCSI target are brought up on the new Active node.
#
# Beszel agent:
# Enabled here via enable-agent.nix. The agent KEY (used to pair with
# the Beszel hub) is not set yet — add it to hosts/ha-server-{1,2}/host.nix
# under services.beszel.agent.environment.KEY once the hub accepts the
# new agents, following the pattern in hosts/server/host.nix.
{ lib, pkgs, vars, ... }:
let
# Generates /etc/exports lines for all nfsShares data entries. Shared
# pattern with modules/build-types/server.nix — both export the same
# set of shares, differing only in the storage root they serve from.
mkNfsExports = storageRoot:
lib.concatMapStrings
(share: " ${storageRoot}/${share.subpath} ${vars.lanCidr}${vars.nfsShares.options}\n")
(lib.filter builtins.isAttrs (lib.attrValues vars.nfsShares));
in
{
imports = [
../ha/pacemaker-stack.nix
../ha/iscsi-target.nix
../ha/cluster-config.nix
../beszel/enable-agent.nix
];
# xfsprogs: mkfs.xfs/xfs_info needed by cluster-init.sh.
# openiscsi: iscsiadm needed by acceptance-tests.sh T4 (iSCSI discovery check).
environment.systemPackages = [ pkgs.xfsprogs pkgs.openiscsi ];
services.nfs.server = {
enable = true;
exports = mkNfsExports vars.haStorageRoot;
};
# Pacemaker controls nfs-server — prevent systemd from starting it at boot
# on both nodes (only the Active node should be serving NFS).
systemd.services.nfs-server.wantedBy = lib.mkForce [ ];
}