Commit bccab6a0 ("dm cache: switch the "default" cache replacement
policy from mq to smq") should've incremented the "default" policy's
version number to 1.4.0 rather than reverting to version 1.0.0.
Reported-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

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: NMike Snitzer <snitzer@redhat.com>
Acked-by: NJoe Thornber <ejt@redhat.com>

The policy tick() method is normally called from interrupt context.
Both the mq and smq policies do some bottom half work for the tick
method in their map functions.  However if no IO is going through the
cache, then that bottom half work doesn't occur.  With these policies
this means recently hit entries do not age and do not get written
back as early as we'd like.

Fix this by introducing a new 'can_block' parameter to the tick()
method.  When this is set the bottom half work occurs immediately.
'can_block' is set when the tick method is called every second by the
core target (not in interrupt context).
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

The stochastic-multi-queue (smq) policy addresses some of the problems
with the current multiqueue (mq) policy.

Memory usage
------------

The mq policy uses a lot of memory; 88 bytes per cache block on a 64
bit machine.

SMQ uses 28bit indexes to implement it's data structures rather than
pointers.  It avoids storing an explicit hit count for each block.  It
has a 'hotspot' queue rather than a pre cache which uses a quarter of
the entries (each hotspot block covers a larger area than a single
cache block).

All these mean smq uses ~25bytes per cache block.  Still a lot of
memory, but a substantial improvement nontheless.

Level balancing
---------------

MQ places entries in different levels of the multiqueue structures
based on their hit count (~ln(hit count)).  This means the bottom
levels generally have the most entries, and the top ones have very
few.  Having unbalanced levels like this reduces the efficacy of the
multiqueue.

SMQ does not maintain a hit count, instead it swaps hit entries with
the least recently used entry from the level above.  The over all
ordering being a side effect of this stochastic process.  With this
scheme we can decide how many entries occupy each multiqueue level,
resulting in better promotion/demotion decisions.

Adaptability
------------

The MQ policy maintains a hit count for each cache block.  For a
different block to get promoted to the cache it's hit count has to
exceed the lowest currently in the cache.  This means it can take a
long time for the cache to adapt between varying IO patterns.
Periodically degrading the hit counts could help with this, but I
haven't found a nice general solution.

SMQ doesn't maintain hit counts, so a lot of this problem just goes
away.  In addition it tracks performance of the hotspot queue, which
is used to decide which blocks to promote.  If the hotspot queue is
performing badly then it starts moving entries more quickly between
levels.  This lets it adapt to new IO patterns very quickly.

Performance
-----------

In my tests SMQ shows substantially better performance than MQ.  Once
this matures a bit more I'm sure it'll become the default policy.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>