Merge pull request #173 from truenas/truenas/zfs-2.1.13

Merge zfs-2.1.13

.github/workflows/checkstyle.yaml

@@ -4,7 +4,7 @@ on: [push, pull_request]
 
 jobs:
   skip-checkstyle:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     outputs:
       should_skip: ${{ steps.skip_check.outputs.should_skip }}
     steps:
@@ -17,20 +17,27 @@ jobs:
   checkstyle:
     needs: skip-checkstyle
     if: ${{ needs.skip-checkstyle.outputs.should_skip != 'true' }}
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v3
       with:
         ref: ${{ github.event.pull_request.head.sha }}
     - name: Install dependencies
       run: |
-        sudo apt-get update
-        sudo apt-get install --yes -qq build-essential autoconf libtool gawk alien fakeroot linux-headers-$(uname -r)
-        sudo apt-get install --yes -qq zlib1g-dev uuid-dev libattr1-dev libblkid-dev libselinux-dev libudev-dev libssl-dev libbsd-dev python-dev python-setuptools python-cffi python3 python3-dev python3-setuptools python3-cffi
-        # packages for tests
-        sudo apt-get install --yes -qq parted lsscsi ksh attr acl nfs-kernel-server fio
-        sudo apt-get install --yes -qq mandoc cppcheck pax-utils devscripts
-        sudo -E pip --quiet install flake8
+        # https://github.com/orgs/community/discussions/47863
+        sudo apt-mark hold grub-efi-amd64-signed
+        sudo apt-get update --fix-missing
+        sudo apt-get upgrade
+        sudo xargs --arg-file=${{ github.workspace }}/.github/workflows/build-dependencies.txt apt-get install -qq
+        sudo xargs --arg-file=${{ github.workspace }}/.github/workflows/checkstyle-dependencies.txt apt-get install -qq
+        sudo python3 -m pip install --quiet flake8
+        sudo apt-get clean
+
+        # confirm that the tools are installed
+        # the build system doesn't fail when they are not
+        flake8 --version
+        scanelf --version
+        shellcheck --version
     - name: Prepare
       run: |
         sh ./autogen.sh

.github/workflows/zloop.yml

@@ -15,7 +15,7 @@ jobs:
           concurrent_skipping: 'same_content_newer'
 
   tests:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     env:
       TEST_DIR: /var/tmp/zloop
     steps:
@@ -24,15 +24,12 @@ jobs:
         ref: ${{ github.event.pull_request.head.sha }}
     - name: Install dependencies
       run: |
-        sudo apt-get update
-        sudo apt-get install --yes -qq build-essential autoconf libtool gdb \
-          git alien fakeroot \
-          zlib1g-dev uuid-dev libblkid-dev libselinux-dev \
-          xfslibs-dev libattr1-dev libacl1-dev libudev-dev libdevmapper-dev \
-          libssl-dev libffi-dev libaio-dev libelf-dev libmount-dev \
-          libpam0g-dev libbsd-dev \
-          python-dev python-setuptools python-cffi python-packaging \
-          python3 python3-dev python3-setuptools python3-cffi python3-packaging
+        # https://github.com/orgs/community/discussions/47863
+        sudo apt-mark hold grub-efi-amd64-signed
+        sudo apt-get update --fix-missing
+        sudo apt-get upgrade
+        sudo xargs --arg-file=${{ github.workspace }}/.github/workflows/build-dependencies.txt apt-get install -qq
+        sudo apt-get clean
     - name: Autogen.sh
       run: |
         sh autogen.sh
@@ -53,8 +50,9 @@ jobs:
     - name: Tests
       run: |
         sudo mkdir -p $TEST_DIR
-        # run for 20 minutes to have a total runner time of 30 minutes
-        sudo /usr/share/zfs/zloop.sh -t 1200 -l -m1 -- -T 120 -P 60
+        # run for 10 minutes or at most 2 iterations for a maximum runner
+        #   time of 20 minutes.
+        sudo /usr/share/zfs/zloop.sh -t 600 -I 2 -l -m1 -- -T 120 -P 60
     - name: Prepare artifacts
       if: failure()
       run: |

META

@@ -1,10 +1,10 @@
 Meta:          1
 Name:          zfs
 Branch:        1.0
-Version:       2.1.12
+Version:       2.1.13
 Release:       1
 Release-Tags:  relext
 License:       CDDL
 Author:        OpenZFS
-Linux-Maximum: 6.3
+Linux-Maximum: 6.5
 Linux-Minimum: 3.10

cmd/zed/agents/zfs_mod.c

@@ -599,8 +599,6 @@ zfs_iter_vdev(zpool_handle_t *zhp, nvlist_t *nvl, void *data)
 		 */
 		if (nvlist_lookup_string(nvl, dp->dd_prop, &path) != 0 ||
 		    strcmp(dp->dd_compare, path) != 0) {
-			zed_log_msg(LOG_INFO, "  %s: no match (%s != vdev %s)",
-			    __func__, dp->dd_compare, path);
 			return;
 		}
 		if (dp->dd_new_vdev_guid != 0 && dp->dd_new_vdev_guid != guid) {

cmd/zed/agents/zfs_retire.c

@@ -415,6 +415,11 @@ zfs_retire_recv(fmd_hdl_t *hdl, fmd_event_t *ep, nvlist_t *nvl,
 		    FM_EREPORT_PAYLOAD_ZFS_VDEV_GUID, &vdev_guid) != 0)
 			return;
 
+		if (vdev_guid == 0) {
+			fmd_hdl_debug(hdl, "Got a zero GUID");
+			return;
+		}
+
 		if (spare) {
 			int nspares = find_and_remove_spares(zhdl, vdev_guid);
 			fmd_hdl_debug(hdl, "%d spares removed", nspares);

cmd/zed/zed.d/Makefile.am

@@ -21,6 +21,7 @@ dist_zedexec_SCRIPTS = \
 	scrub_finish-notify.sh \
 	statechange-led.sh \
 	statechange-notify.sh \
+	statechange-slot_off.sh \
 	vdev_clear-led.sh \
 	vdev_attach-led.sh \
 	pool_import-led.sh \
@@ -39,6 +40,7 @@ zedconfdefaults = \
 	scrub_finish-notify.sh \
 	statechange-led.sh \
 	statechange-notify.sh \
+	statechange-slot_off.sh \
 	vdev_clear-led.sh \
 	vdev_attach-led.sh \
 	pool_import-led.sh \

cmd/zed/zed.d/statechange-slot_off.sh

@@ -0,0 +1,64 @@
+#!/bin/sh
+# shellcheck disable=SC3014,SC2154,SC2086,SC2034
+#
+# Turn off disk's enclosure slot if it becomes FAULTED.
+#
+# Bad SCSI disks can often "disappear and reappear" causing all sorts of chaos
+# as they flip between FAULTED and ONLINE.  If
+# ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT is set in zed.rc, and the disk gets
+# FAULTED, then power down the slot via sysfs:
+#
+# /sys/class/enclosure/<enclosure>/<slot>/power_status
+#
+# We assume the user will be responsible for turning the slot back on again.
+#
+# Note that this script requires that your enclosure be supported by the
+# Linux SCSI Enclosure services (SES) driver.  The script will do nothing
+# if you have no enclosure, or if your enclosure isn't supported.
+#
+# Exit codes:
+#   0: slot successfully powered off
+#   1: enclosure not available
+#   2: ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT disabled
+#   3: vdev was not FAULTED
+#   4: The enclosure sysfs path passed from ZFS does not exist
+#   5: Enclosure slot didn't actually turn off after we told it to
+
+[ -f "${ZED_ZEDLET_DIR}/zed.rc" ] && . "${ZED_ZEDLET_DIR}/zed.rc"
+. "${ZED_ZEDLET_DIR}/zed-functions.sh"
+
+if [ ! -d /sys/class/enclosure ] ; then
+	# No JBOD enclosure or NVMe slots
+	exit 1
+fi
+
+if [ "${ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT}" != "1" ] ; then
+	exit 2
+fi
+
+if [ "$ZEVENT_VDEV_STATE_STR" != "FAULTED" ] ; then
+	exit 3
+fi
+
+if [ ! -f "$ZEVENT_VDEV_ENC_SYSFS_PATH/power_status" ] ; then
+	exit 4
+fi
+
+# Turn off the slot and wait for sysfs to report that the slot is off.
+# It can take ~400ms on some enclosures and multiple retries may be needed.
+for i in $(seq 1 20) ; do
+	echo "off" | tee "$ZEVENT_VDEV_ENC_SYSFS_PATH/power_status"
+
+	for j in $(seq 1 5) ; do
+		if [ "$(cat $ZEVENT_VDEV_ENC_SYSFS_PATH/power_status)" == "off" ] ; then
+			break 2
+		fi
+		sleep 0.1
+	done
+done
+
+if [ "$(cat $ZEVENT_VDEV_ENC_SYSFS_PATH/power_status)" != "off" ] ; then
+	exit 5
+fi
+
+zed_log_msg "powered down slot $ZEVENT_VDEV_ENC_SYSFS_PATH for $ZEVENT_VDEV_PATH"

cmd/zed/zed.d/zed.rc

@@ -143,3 +143,8 @@ ZED_SYSLOG_SUBCLASS_EXCLUDE="history_event"
 # Disabled by default, 1 to enable and 0 to disable.
 #ZED_SYSLOG_DISPLAY_GUIDS=1
 
+##
+# Power off the drive's slot in the enclosure if it becomes FAULTED.  This can
+# help silence misbehaving drives.  This assumes your drive enclosure fully
+# supports slot power control via sysfs.
+#ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT=1