1. 04 9月, 2017 1 次提交
  2. 27 8月, 2017 1 次提交
  3. 07 8月, 2017 1 次提交
  4. 06 8月, 2017 1 次提交
    • F
      Persist series without allocating the full set · 96d7f540
      Fabian Reinartz 提交于
      Change index persistence for series to not be accumulated in memory
      before being written as one large batch. `Labels` and `ChunkMeta`
      objects are reused.
      This cuts down memory spikes during compaction of multiple blocks
      significantly.
      
      As part of the the Index{Reader,Writer} now have an explicit notion of
      symbols and series must be inserted in order.
      96d7f540
  5. 06 6月, 2017 1 次提交
  6. 17 5月, 2017 1 次提交
  7. 16 5月, 2017 1 次提交
  8. 14 5月, 2017 1 次提交
  9. 02 5月, 2017 1 次提交
  10. 30 4月, 2017 11 次提交
  11. 28 4月, 2017 1 次提交
  12. 11 4月, 2017 1 次提交
  13. 05 4月, 2017 1 次提交
  14. 04 4月, 2017 1 次提交
  15. 30 3月, 2017 1 次提交
  16. 27 3月, 2017 2 次提交
  17. 20 3月, 2017 1 次提交
  18. 14 3月, 2017 1 次提交
    • F
      Use ChunkMeta references for clarity · a8e89033
      Fabian Reinartz 提交于
      This has been a common source of hard to debug issues. Its a premature
      and unbenchmarked optimization and semantically, we want ChunkMetas to
      be references in all changed cases.
      a8e89033
  19. 07 3月, 2017 1 次提交
  20. 03 3月, 2017 1 次提交
  21. 25 2月, 2017 1 次提交
  22. 23 2月, 2017 1 次提交
    • F
      Segment chunk file · 78780cd2
      Fabian Reinartz 提交于
      This adds write path support for segmented chunk data files.
      Files of 512MB are pre-allocated and written to. If the file size
      is exceeded, the next file is started. On completion, files
      are truncated to their final size.
      78780cd2
  23. 19 2月, 2017 2 次提交
  24. 16 2月, 2017 1 次提交
  25. 02 2月, 2017 1 次提交
  26. 20 1月, 2017 1 次提交
  27. 19 1月, 2017 2 次提交