lib/cache/lvmcache.c | 2 +-
lib/device/dev-md.c | 27 ++++++++++----
lib/device/dev-type.h | 1 +
lib/filters/filter-md.c | 74 +++++++++++++++++++-------------------
lib/label/label.c | 14 ++++++++
test/shell/pvcreate-md-fake-hdr.sh | 3 +-
6 files changed, 75 insertions(+), 46 deletions(-)
diff --git a/lib/cache/lvmcache.c b/lib/cache/lvmcache.c
index 2fba3ff..f55a14c 100644
--- a/lib/cache/lvmcache.c
+++ b/lib/cache/lvmcache.c
@@ -1002,7 +1002,7 @@ int lvmcache_dev_is_unchosen_duplicate(struct device *dev)
* unused_duplicate_devs list, and restrict what we allow done with it.
*
* In the case of md components, we usually filter these out in filter-md,
- * but in the special case of md superblocks <= 1.0 where the superblock
+ * but in the special case of md superblock version 1.0 where the superblock
* is at the end of the device, filter-md doesn't always eliminate them
* first, so we eliminate them here.
*
diff --git a/lib/device/dev-md.c b/lib/device/dev-md.c
index f5a736f..7196dc0 100644
--- a/lib/device/dev-md.c
+++ b/lib/device/dev-md.c
@@ -142,13 +142,6 @@ static int _native_dev_is_md(struct device *dev, uint64_t *offset_found, int ful
* command if it should do a full check (cmd->use_full_md_check),
* and set it for commands that could possibly write to an md dev
* (pvcreate/vgcreate/vgextend).
- *
- * For old md versions with magic numbers at the end of devices,
- * the md dev components won't be filtered out here when full is 0,
- * so they will be scanned, and appear as duplicate PVs in lvmcache.
- * The md device itself will be chosen as the primary duplicate,
- * and the components are dropped from the list of duplicates in,
- * i.e. a kind of post-scan filtering.
*/
if (!full) {
sb_offset = 0;
@@ -414,6 +407,26 @@ unsigned long dev_md_stripe_width(struct dev_types *dt, struct device *dev)
return stripe_width_sectors;
}
+int dev_is_md_with_end_superblock(struct dev_types *dt, struct device *dev)
+{
+ char version_string[MD_MAX_SYSFS_SIZE];
+ const char *attribute = "metadata_version";
+
+ if (MAJOR(dev->dev) != dt->md_major)
+ return 0;
+
+ if (_md_sysfs_attribute_scanf(dt, dev, attribute,
+ "%s", &version_string) != 1)
+ return -1;
+
+ log_very_verbose("Device %s %s is %s.",
+ dev_name(dev), attribute, version_string);
+
+ if (!strcmp(version_string, "1.0"))
+ return 1;
+ return 0;
+}
+
#else
int dev_is_md(struct device *dev __attribute__((unused)),
diff --git a/lib/device/dev-type.h b/lib/device/dev-type.h
index 843e254..f629a02 100644
--- a/lib/device/dev-type.h
+++ b/lib/device/dev-type.h
@@ -76,6 +76,7 @@ int wipe_known_signatures(struct cmd_context *cmd, struct device *dev, const cha
/* Type-specific device properties */
unsigned long dev_md_stripe_width(struct dev_types *dt, struct device *dev);
+int dev_is_md_with_end_superblock(struct dev_types *dt, struct device *dev);
/* Partitioning */
int major_max_partitions(struct dev_types *dt, int major);
diff --git a/lib/filters/filter-md.c b/lib/filters/filter-md.c
index ab97b59..ad5b8e4 100644
--- a/lib/filters/filter-md.c
+++ b/lib/filters/filter-md.c
@@ -29,43 +29,43 @@
*
* (This is assuming lvm.conf md_component_detection=1.)
*
- * If lvm does *not* ignore the components, then lvm will read lvm
- * labels from the md dev and from the component devs, and will see
- * them all as duplicates of each other. LVM duplicate resolution
- * will then kick in and keep the md dev around to use and ignore
- * the components.
- *
- * It is better to exclude the components as early as possible during
- * lvm processing, ideally before lvm even looks for labels on the
- * components, so that duplicate resolution can be avoided. There are
- * a number of ways that md components can be excluded earlier than
- * the duplicate resolution phase:
- *
- * - When external_device_info_source="udev", lvm discovers a device is
- * an md component by asking udev during the initial filtering phase.
- * However, lvm's default is to not use udev for this. The
- * alternative is "native" detection in which lvm tries to detect
- * md components itself.
- *
- * - When using native detection, lvm's md filter looks for the md
- * superblock at the start of devices. It will see the md superblock
- * on the components, exclude them in the md filter, and avoid
- * handling them later in duplicate resolution.
- *
- * - When using native detection, lvm's md filter will not detect
- * components when the md device has an older superblock version that
- * places the superblock at the end of the device. This case will
- * fall back to duplicate resolution to exclude components.
- *
- * A variation of the description above occurs for lvm commands that
- * intend to create new PVs on devices (pvcreate, vgcreate, vgextend).
- * For these commands, the native md filter also reads the end of all
- * devices to check for the odd md superblocks.
- *
- * (The reason that external_device_info_source is not set to udev by
- * default is that there have be issues with udev not being promptly
- * or reliably updated about md state changes, causing the udev info
- * that lvm uses to be occasionally wrong.)
+ * If lvm does *not* ignore the components, then lvm may read lvm
+ * labels from the component devs and potentially the md dev,
+ * which can trigger duplicate detection, and/or cause lvm to display
+ * md components as PVs rather than ignoring them.
+ *
+ * If scanning md componenents causes duplicates to be seen, then
+ * the lvm duplicate resolution will exclude the components.
+ *
+ * The lvm md filter has three modes:
+ *
+ * 1. look for md superblock at the start of the device
+ * 2. look for md superblock at the start and end of the device
+ * 3. use udev to detect components
+ *
+ * mode 1 will not detect and exclude components of md devices
+ * that use superblock version 1.0 which is at the end of the device.
+ *
+ * mode 2 will detect these, but mode 2 doubles the i/o done by label
+ * scan, since there's a read at both the start and end of every device.
+ *
+ * mode 3 is used when external_device_info_source="udev". It does
+ * not require any io from lvm, but this mode is not used by default
+ * because there have been problems getting reliable info from udev.
+ *
+ * lvm uses mode 2 when:
+ *
+ * - the command is pvcreate/vgcreate/vgextend, which format new
+ * devices, and if the user ran these commands on a component
+ * device of an md device 1.0, then it would cause problems.
+ * FIXME: this would only really need to scan the end of the
+ * devices being formatted, not all devices.
+ *
+ * - it sees an md device on the system using version 1.0.
+ * The point of this is just to avoid displaying md components
+ * from the 'pvs' command.
+ * FIXME: the cost (double i/o) may not be worth the benefit
+ * (not showing md components).
*/
/*
diff --git a/lib/label/label.c b/lib/label/label.c
index e7e3997..6fb35ff 100644
--- a/lib/label/label.c
+++ b/lib/label/label.c
@@ -872,6 +872,20 @@ int label_scan(struct cmd_context *cmd)
bcache_invalidate_fd(scan_bcache, dev->bcache_fd);
_scan_dev_close(dev);
}
+
+ /*
+ * When md devices exist that use the old superblock at the
+ * end of the device, then in order to detect and filter out
+ * the component devices of those md devs, we need to enable
+ * the full md filter which scans both the start and the end
+ * of every device. This doubles the amount of scanning i/o,
+ * which we want to avoid. FIXME: it may not be worth the
+ * cost of double i/o just to avoid displaying md component
+ * devs in 'pvs', which is a pretty harmless effect from a
+ * pretty uncommon situation.
+ */
+ if (dev_is_md_with_end_superblock(cmd->dev_types, dev))
+ cmd->use_full_md_check = 1;
};
dev_iter_destroy(iter);
diff --git a/test/shell/pvcreate-md-fake-hdr.sh b/test/shell/pvcreate-md-fake-hdr.sh
index b89fe43..4c9ac7c 100644
--- a/test/shell/pvcreate-md-fake-hdr.sh
+++ b/test/shell/pvcreate-md-fake-hdr.sh
@@ -89,6 +89,7 @@ sleep 1
# (when mdadm supports repair)
if mdadm --action=repair "$mddev" ; then
sleep 1
+ pvscan -vvvv
# should be showing correctly PV3 & PV4
- pvs
+ pvs -vvvv "$dev3" "$dev4"
fi