Exclude an external shelf by explicit config, not by path shape

Testing on a second host showed the internal/external split cannot be
inferred: iz-pve1's MD1200 sits behind its own HBA while iz-pve0's
internal drives sit behind a SAS expander, so the previous
"pci-*-scsi-*" glob matched every drive on one host and none on the
other. DISK_EXCLUDE_PATTERN now names the shelf's HBA per host.

Also fixes parse_disk_limit, which used awk's for-in over split fields
and so returned 0 or 70 from "0/70" depending on iteration order.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

monitor.sh

@@ -8,9 +8,17 @@
 
 # ---------------------------------------------------------------- configuration
 
-# Internal drives only. The DAS shelf enumerates behind a SAS expander
-# (*-sas-exp*) and has its own controller - it must not drive server fans.
-DISK_GLOB=${DISK_GLOB:-/dev/disk/by-path/pci-*-scsi-*}
+DISK_GLOB=${DISK_GLOB:-/dev/disk/by-path/*}
+
+# Drives to leave alone, matched against the by-path link. Set this to the PCI
+# address of an external shelf's HBA on any host that has one.
+#
+# There is no reliable way to infer this. An external enclosure looks exactly
+# like an internal backplane from /dev/disk/by-path: iz-pve1's MD1200 sits
+# behind its own HBA at pci-0000:04:00.0, while iz-pve0's *internal* drives sit
+# behind a SAS expander at pci-0000:02:00.0. Guessing from "-sas-exp" picks up
+# the wrong set on one host or the other, so it has to be stated per host.
+DISK_EXCLUDE_PATTERN=${DISK_EXCLUDE_PATTERN:-}
 
 # Each drive's fan ramp is derived from its own maximum operating temperature:
 #   ramp starts at  limit - DISK_RAMP_LOW_OFFSET
@@ -53,6 +61,9 @@ disk_devices() {
   local link dev
   for link in $DISK_GLOB; do
     case "$link" in *-part*) continue ;; esac
+    if [ -n "$DISK_EXCLUDE_PATTERN" ]; then
+      case "$link" in *"$DISK_EXCLUDE_PATTERN"*) continue ;; esac
+    fi
     [ -e "$link" ] || continue
     dev=$(readlink -f "$link")
     [ -b "$dev" ] && echo "$dev"
@@ -73,8 +84,11 @@ parse_disk_temperature() {
 # smartctl -x output on stdin -> the drive's own maximum operating temperature.
 parse_disk_limit() {
   awk '
-    /Min\/Max Temperature Limit/ { split($0, a, /[ \/]+/); for (i in a) if (a[i] ~ /^[0-9]+$/) v = a[i]; print v; exit }
-    /Drive Trip Temperature/     { print $4; exit }'
+    /Min\/Max Temperature Limit/ {
+      if (match($0, /-?[0-9]+\/[0-9]+/)) { split(substr($0, RSTART, RLENGTH), a, "/"); print a[2] }
+      exit
+    }
+    /Drive Trip Temperature/ { print $4; exit }'
 }
 
 # -n standby: skip a sleeping drive rather than spinning it up to measure it.