feat(dr): manual failover/failback scripts + pveelite-down email alert
failover-dr-to-pvemini.sh and failback-dr-to-pveelite.sh promote/demote the rpool/oracle-backups dataset between nodes when pveelite is down. Both refuse to run if the other side is reachable to prevent split-brain. Both patch transfer_backups.ps1 on Oracle Production (10.0.20.36) via SSH to redirect the daily SCP target between 10.0.20.202 and 10.0.20.201. The PowerShell patch uses -EncodedCommand (UTF-16LE base64) so the bash caller does not need to escape PowerShell quoting. End-to-end test including failover -> failback confirmed transfer_backups.ps1 returns to byte-identical state (SHA256 43DD2187...). pveelite-down-alert.sh runs every minute on pvemini and emails an alert with copy-paste failover instructions after 5 consecutive ping failures. The alert body includes the latest oracle-backups and VM 109 replica timestamps so the operator knows the recovery point before deciding. The DR weekly-test script gains a cluster-aware guard at the top that exits silently when /etc/pve/qemu-server/109.conf is not on the local node, allowing the same cron entry to be present on both pveelite and pvemini without double-firing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Agent
132
proxmox/vm109-windows-dr/scripts/failover-dr-to-pvemini.sh
Normal file
132
proxmox/vm109-windows-dr/scripts/failover-dr-to-pvemini.sh
Normal file
@@ -0,0 +1,132 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# Failover the Oracle DR storage from pveelite to pvemini.
|
||||
#
|
||||
# When to run: pveelite is dead long enough that the user has chosen to
|
||||
# take over backup ingestion on pvemini rather than wait. The
|
||||
# pveelite-down email alert points the operator at this script.
|
||||
#
|
||||
# What it does:
|
||||
# 1. Confirms pveelite is actually unreachable (refuses to split-brain).
|
||||
# 2. Flips rpool/oracle-backups on pvemini from readonly replica to
|
||||
# writable primary.
|
||||
# 3. Configures and starts the NFS export on pvemini so VM 109 can
|
||||
# still mount /mnt/pve/oracle-backups when it boots there.
|
||||
# 4. Patches transfer_backups.ps1 on the Oracle Windows production
|
||||
# host (10.0.20.36) to ship to pvemini's IP instead of pveelite's.
|
||||
# 5. Disables the original ZFS replication cron (which would now fail
|
||||
# since the source pveelite is down).
|
||||
# 6. Prints next steps for the operator.
|
||||
#
|
||||
# Idempotent: rerunning is safe — each step checks before acting.
|
||||
#
|
||||
# Reverse: /opt/scripts/failback-dr-to-pveelite.sh once pveelite is back.
|
||||
|
||||
set -euo pipefail
|
||||
export PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||
|
||||
PVEELITE_IP="10.0.20.202"
|
||||
PVEMINI_IP="10.0.20.201"
|
||||
DATASET="rpool/oracle-backups"
|
||||
MOUNTPOINT="/mnt/pve/oracle-backups"
|
||||
NFS_CLIENT="10.0.20.37" # VM 109 NFS client
|
||||
NFS_OPTS="rw,sync,no_subtree_check,no_root_squash"
|
||||
PRIMARY_HOST="10.0.20.36"
|
||||
PRIMARY_USER="dr-failover"
|
||||
PRIMARY_SSH_PORT="22122"
|
||||
TRANSFER_SCRIPT_WIN_PATH='D:\rman_backup\transfer_backups.ps1'
|
||||
LOG="/var/log/oracle-dr/failover.log"
|
||||
SSH_OPTS_PVE="-o UserKnownHostsFile=/etc/pve/priv/known_hosts -o StrictHostKeyChecking=no -o BatchMode=yes"
|
||||
|
||||
mkdir -p "$(dirname "$LOG")"
|
||||
|
||||
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG"; }
|
||||
|
||||
if [ "$(hostname)" != "pvemini" ]; then
|
||||
log "FATAL: this script must run on pvemini (current: $(hostname))"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "============================================================"
|
||||
log "Oracle DR failover: pveelite -> pvemini"
|
||||
log "============================================================"
|
||||
|
||||
# Step 1: confirm pveelite is unreachable
|
||||
log "Step 1: verifying pveelite ($PVEELITE_IP) is unreachable..."
|
||||
if ping -c 3 -W 2 "$PVEELITE_IP" >/dev/null 2>&1; then
|
||||
log "ABORT: pveelite responds to ping. Refusing to split-brain."
|
||||
log " If you really want to force failover anyway:"
|
||||
log " 1. Confirm pveelite NFS service is dead (systemctl status nfs-server)"
|
||||
log " 2. Stop pveelite NFS first: ssh pveelite 'systemctl stop nfs-server'"
|
||||
log " 3. Then re-run this script."
|
||||
exit 2
|
||||
fi
|
||||
log " pveelite unreachable, proceeding."
|
||||
|
||||
# Step 2: flip dataset to writable
|
||||
CURRENT_RO=$(zfs get -H -o value readonly "$DATASET")
|
||||
log "Step 2: dataset readonly status = $CURRENT_RO"
|
||||
if [ "$CURRENT_RO" = "on" ]; then
|
||||
log " setting readonly=off on $DATASET"
|
||||
zfs set readonly=off "$DATASET"
|
||||
else
|
||||
log " already writable, no change"
|
||||
fi
|
||||
|
||||
# Step 3: NFS export
|
||||
log "Step 3: configuring NFS export on pvemini"
|
||||
EXPORT_LINE="$MOUNTPOINT $NFS_CLIENT($NFS_OPTS)"
|
||||
if grep -qF "$EXPORT_LINE" /etc/exports; then
|
||||
log " export already present in /etc/exports"
|
||||
else
|
||||
log " appending export line"
|
||||
echo "$EXPORT_LINE" >> /etc/exports
|
||||
fi
|
||||
systemctl is-enabled --quiet nfs-server || systemctl enable nfs-server
|
||||
systemctl is-active --quiet nfs-server || systemctl start nfs-server
|
||||
exportfs -ra
|
||||
log " active exports:"
|
||||
exportfs -v 2>&1 | sed 's/^/ /' | tee -a "$LOG"
|
||||
|
||||
# Step 4: patch primary Oracle transfer script.
|
||||
# Use literal String.Replace (no regex). Send via PowerShell -EncodedCommand
|
||||
# (UTF-16LE base64) to bypass all bash <-> SSH <-> PowerShell quoting issues.
|
||||
log "Step 4: patching $TRANSFER_SCRIPT_WIN_PATH on $PRIMARY_HOST"
|
||||
PS_SCRIPT="\$path = '$TRANSFER_SCRIPT_WIN_PATH'
|
||||
\$old = '\"$PVEELITE_IP\"'
|
||||
\$new = '\"$PVEMINI_IP\"'
|
||||
\$content = Get-Content \$path -Raw
|
||||
if (\$content.Contains(\$old)) {
|
||||
Set-Content -Path \$path -Value \$content.Replace(\$old, \$new) -NoNewline
|
||||
Write-Output 'PATCHED'
|
||||
} elseif (\$content.Contains(\$new)) {
|
||||
Write-Output 'ALREADY_FAILED_OVER'
|
||||
} else {
|
||||
Write-Output 'UNKNOWN_DRHost_VALUE'
|
||||
}"
|
||||
PS_B64=$(printf '%s' "$PS_SCRIPT" | iconv -t UTF-16LE | base64 -w0)
|
||||
PATCH_RESULT=$(ssh -p "$PRIMARY_SSH_PORT" -o ConnectTimeout=10 -o BatchMode=yes \
|
||||
"$PRIMARY_USER@$PRIMARY_HOST" \
|
||||
"powershell -NoProfile -EncodedCommand $PS_B64" 2>&1 \
|
||||
| grep -vE '^#< CLIXML|<Objs |</Objs>$' | tr -d '\r' | head -1)
|
||||
if [ -n "$PATCH_RESULT" ]; then
|
||||
log " result: $PATCH_RESULT"
|
||||
else
|
||||
log " WARNING: SSH to primary failed — operator must edit $TRANSFER_SCRIPT_WIN_PATH manually"
|
||||
log " Set: \$DRHost = \"$PVEMINI_IP\""
|
||||
fi
|
||||
|
||||
# Step 5: disable original replication cron entry locally too
|
||||
# (it lives on pveelite; nothing to do here, but document)
|
||||
log "Step 5: ZFS replication cron is on pveelite which is down — no action needed"
|
||||
|
||||
# Step 6: print next steps
|
||||
log "============================================================"
|
||||
log "Failover complete on pvemini."
|
||||
log "Next steps for the operator:"
|
||||
log " 1. Verify VM 109 starts here if a DR test is needed:"
|
||||
log " qm start 109 (once HA migrates VM 109 to pvemini, or manually)"
|
||||
log " 2. Watch the next scheduled Oracle backup land on pvemini:"
|
||||
log " tail -f /var/log/syslog | grep nfsd"
|
||||
log " 3. When pveelite returns, run /opt/scripts/failback-dr-to-pveelite.sh"
|
||||
log "============================================================"
|
||||
Reference in New Issue
Block a user