riotpiao-poimen/homelab
2
0
Fork 0
Code Issues 23 Pull Requests 2 Actions Packages Projects 1 Releases Wiki Activity

fix(longhorn): retire the failed 2TB PERC disk on talos-cp-2 #62

Merged
rock merged 5 commits from fix/retire-longhorn-disk4 into main 2026-10-13 00:10:02 +00:00
Conversation 0 Commits 5 Files Changed 12
+21 -11
2 changed files with 21 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit d21ee9630f - Show all commits
k8s/infra/longhorn/longhorn-add-disks-job.yaml
+13 -10
View File
@@ -41,13 +41,24 @@ spec:
# - /var/lib/longhorn-disk1 (sdb1, 600GB)
# - /var/lib/longhorn-disk2 (sdc1, 500GB)
# - /var/lib/longhorn-disk3 (sdd1, 160GB)
# - /var/lib/longhorn-disk4 (sde1, 2TB)
#
# /var/lib/longhorn-disk4 (sde1, the 2TB PERC virtual disk) was RETIRED
# on 2026-10-12 and must not be re-added. The device returned SCSI I/O
# errors at ~7,000/minute, the XFS filesystem on it hung, and every
# process that touched it blocked in unkillable D state. Those unkillable
# processes held Longhorn's per-node rebuild slots forever, so no new
# replica could start on talos-cp-2 and every new volume there failed to
# attach. It is removed from the Terraform disk list too, so a re-render
# does not put it back.
echo "Checking talos-cp-2..."
CURRENT_DISKS=$(kubectl -n longhorn-system get nodes.longhorn.io talos-cp-2 -o json | jq -r '.spec.disks | keys | length')
echo " Current disk count: $CURRENT_DISKS"
if [ "$CURRENT_DISKS" -lt 5 ]; then
# 4 = default-disk-080400000000 + disk1..disk3. It was 5 while disk4
# existed; leaving the old threshold would re-apply the patch on every
# run once disk4 is gone.
if [ "$CURRENT_DISKS" -lt 4 ]; then
echo " Adding extra disks to talos-cp-2..."
kubectl -n longhorn-system patch nodes.longhorn.io talos-cp-2 --type merge -p '{
"spec": {
@@ -75,14 +86,6 @@ spec:
"path": "/var/lib/longhorn-disk3",
"storageReserved": 5368709120,
"tags": []
},
"disk4": {
"allowScheduling": true,
"diskType": "filesystem",
"evictionRequested": false,
"path": "/var/lib/longhorn-disk4",
"storageReserved": 21474836480,
"tags": []
}
}
}
terraform/terraform.tfvars.local.bak
+8 -1
View File
@@ -20,6 +20,7 @@ controlplane_configs = {
"talos-cp-1" = {
hostname = "talos-cp-1"
lan_ip = "192.168.1.166"
public_ip = "https://k8s-api.riotpiao.com"
lan_subnet = "192.168.1.0/24"
lan_gateway = "192.168.1.254"
install_disk = "/dev/nvme0n1"
@@ -32,6 +33,7 @@ controlplane_configs = {
"talos-cp-2" = {
hostname = "talos-cp-2"
lan_ip = "192.168.1.214"
public_ip = "https://k8s-api.riotpiao.com"
lan_subnet = "192.168.1.0/24"
lan_gateway = "192.168.1.254"
install_disk = "/dev/disk/by-id/wwn-0x644a842029bd3f002720989b07d7143d"
@@ -39,7 +41,11 @@ controlplane_configs = {
{ device = "/dev/disk/by-id/wwn-0x644a842029bd3f0031b60f4375d97062", mountpoint = "/var/lib/longhorn-disk1" },
{ device = "/dev/disk/by-id/wwn-0x644a842029bd3f0031b5ffeb8bb8b47f", mountpoint = "/var/lib/longhorn-disk2" },
{ device = "/dev/disk/by-id/wwn-0x644a842029bd3f0031b6000c8dabb266", mountpoint = "/var/lib/longhorn-disk3" },
{ device = "/dev/disk/by-id/wwn-0x6b083fe0c5782700321370dc23fd765b", mountpoint = "/var/lib/longhorn-disk4" },
# /var/lib/longhorn-disk4 (wwn-0x6b083fe0c5782700321370dc23fd765b) was
# retired 2026-10-12: the 2TB PERC virtual disk failed with continuous
# SCSI I/O errors, hung its XFS filesystem, and wedged Longhorn replica
# rebuilds on talos-cp-2 with unkillable D-state processes. Do not
# re-add it.
]
zone = "az-b"
allow_scheduling = true
@@ -49,6 +55,7 @@ controlplane_configs = {
"talos-cp-3" = {
hostname = "talos-cp-3"
lan_ip = "192.168.1.162"
public_ip = "https://k8s-api.riotpiao.com"
lan_subnet = "192.168.1.0/24"
lan_gateway = "192.168.1.254"
install_disk = "/dev/nvme0n1"