Skip to content
Snippets Groups Projects
Select Git revision
  • benchmark-tools
  • postgres-lambda
  • master default
  • REL9_4_25
  • REL9_5_20
  • REL9_6_16
  • REL_10_11
  • REL_11_6
  • REL_12_1
  • REL_12_0
  • REL_12_RC1
  • REL_12_BETA4
  • REL9_4_24
  • REL9_5_19
  • REL9_6_15
  • REL_10_10
  • REL_11_5
  • REL_12_BETA3
  • REL9_4_23
  • REL9_5_18
  • REL9_6_14
  • REL_10_9
  • REL_11_4
23 results

postgres-lambda-diff

  • Clone with SSH
  • Clone with HTTPS
  • user avatar
    Heikki Linnakangas authored
    Instead of palloc'ing each HashJoinTuple individually, allocate 32kB chunks
    and pack the tuples densely in the chunks. This avoids the AllocChunk
    header overhead, and the space wasted by standard allocator's habit of
    rounding sizes up to the nearest power of two.
    
    This doesn't contain any planner changes, because the planner's estimate of
    memory usage ignores the palloc overhead. Now that the overhead is smaller,
    the planner's estimates are in fact more accurate.
    
    Tomas Vondra, reviewed by Robert Haas.
    45f6240a
    History
    Name Last commit Last update