Using more than 16g can cause record-pool ptr.i values to overflow
  Fix by splitting memory into 2 zones, lo(16g)/hi(rest)
  When record pools only use zone_lo, and datamemory, buffers etc...can use any


storage/ndb/src/kernel/blocks/lgman.cpp:
  adopt to changed interface for Ndbd_mem_manager
storage/ndb/src/kernel/vm/Pool.cpp:
  Always use ZONE_LO for record pools
    as they use ptr.i == 19 bit page id + 13 bit page index
storage/ndb/src/kernel/vm/ndbd_malloc_impl.cpp:
  Add zones to Ndbd_mem_manager
  ZONE_LO = lower 16g
  ZONE_HI = rest
storage/ndb/src/kernel/vm/ndbd_malloc_impl.hpp:
  Add zones to Ndbd_mem_manager
  ZONE_LO = lower 16g
  ZONE_HI = rest