linux-toradex.git/Documentation/device-mapper, branch v4.4.93

Merge tag 'dm-4.4-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

2015-11-05T05:19:53+00:00

Pull device mapper updates from Mike Snitzer:
 "Smaller set of DM changes for this merge.  I've based these changes on
  Jens' for-4.4/reservations branch because the associated DM changes
  required it.

   - Revert a dm-multipath change that caused a regression for
     unprivledged users (e.g. kvm guests) that issued ioctls when a
     multipath device had no available paths.

   - Include Christoph's refactoring of DM's ioctl handling and add
     support for passing through persistent reservations with DM
     multipath.

   - All other changes are very simple cleanups"

* tag 'dm-4.4-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm switch: simplify conditional in alloc_region_table()
  dm delay: document that offsets are specified in sectors
  dm delay: capitalize the start of an delay_ctr() error message
  dm delay: Use DM_MAPIO macros instead of open-coded equivalents
  dm linear: remove redundant target name from error messages
  dm persistent data: eliminate unnecessary return values
  dm: eliminate unused "bioset" process for each bio-based DM device
  dm: convert ffs to __ffs
  dm: drop NULL test before kmem_cache_destroy() and mempool_destroy()
  dm: add support for passing through persistent reservations
  dm: refactor ioctl handling
  Revert "dm mpath: fix stalls when handling invalid ioctls"
  dm: initialize non-blk-mq queue data before queue is used

dm delay: document that offsets are specified in sectors

2015-10-31T23:06:05+00:00

Only delay params are mentioned in delay.txt.
Mention offsets just like documents for linear and flakey do.

Signed-off-by: Tomohiro Kusumi 
Signed-off-by: Mike Snitzer

dm snapshot: add new persistent store option to support overflow

2015-10-09T20:57:03+00:00

Commit 76c44f6d80 introduced the possibly for "Overflow" to be reported
by the snapshot device's status.  Older userspace (e.g. lvm2) does not
handle the "Overflow" status response.

Fix this incompatibility by requiring newer userspace code, that can
cope with "Overflow", request the persistent store with overflow support
by using "PO" (Persistent with Overflow) for the snapshot store type.

Reported-by: Zdenek Kabelac 
Fixes: 76c44f6d80 ("dm snapshot: don't invalidate on-disk image on snapshot write overflow")
Reviewed-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer

dm raid: document RAID 4/5/6 discard support

2015-08-31T19:05:31+00:00

For RAID 4/5/6 data integrity reasons 'discard_zeroes_data' must work
properly.

Signed-off-by: Heinz Mauelshagen 
Signed-off-by: Mike Snitzer

dm stats: report precise_timestamps and histogram in @stats_list output

2015-08-18T21:20:03+00:00

If the user selected the precise_timestamps or histogram options, report
it in the @stats_list message output.

If the user didn't select these options, no extra tokens are reported,
thus it is backward compatible with old software that doesn't know about
precise timestamps and histogram.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer 
Cc: stable@vger.kernel.org # 4.2

dm cache: display 'needs_check' in status if it is set

2015-07-16T14:23:50+00:00

There is currently no way to see that the needs_check flag has been set
in the metadata.  Display 'needs_check' in the cache status if it is set
in the cache metadata.

Also, update cache documentation.

Signed-off-by: Mike Snitzer

dm thin: display 'needs_check' in status if it is set

2015-07-16T14:23:50+00:00

There is currently no way to see that the needs_check flag has been set
in the metadata.  Display 'needs_check' in the thin-pool status if it is
set in the thinp metadata.

Also, update thinp documentation.

Signed-off-by: Mike Snitzer

dm stats: collect and report histogram of IO latencies

2015-06-17T16:40:40+00:00

Add an option to dm statistics to collect and report a histogram of
IO latencies.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer

dm stats: support precise timestamps

2015-06-17T16:40:40+00:00

Make it possible to use precise timestamps with nanosecond granularity
in dm statistics.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer

dm cache: switch the "default" cache replacement policy from mq to smq

2015-06-17T16:40:38+00:00

The Stochastic multiqueue (SMQ) policy (vs MQ) offers the promise of
less memory utilization, improved performance and increased adaptability
in the face of changing workloads.  SMQ also does not have any
cumbersome tuning knobs.

Users may switch from "mq" to "smq" simply by appropriately reloading a
DM table that is using the cache target.  Doing so will cause all of the
mq policy's hints to be dropped.  Also, performance of the cache may
degrade slightly until smq recalculates the origin device's hotspots
that should be cached.

In the future the "mq" policy will just silently make use of "smq" and
the mq code will be removed.

Signed-off-by: Mike Snitzer 
Acked-by: Joe Thornber