611017f4ed
Add comments
2015-12-18 10:00:07 -07:00
930174bf4d
Handle calling WriteBlock with no data gracefully
2015-12-18 09:57:16 -07:00
6bc7765b88
Handle calling write with no values to TSMWriter gracefully
2015-12-18 09:52:53 -07:00
421a127f11
Add indirectIndex.UnmarshalBinary benchmark
2015-12-17 15:38:51 -07:00
8c7e11f4cf
Aggressively clean up KeyCursor resources
2015-12-17 12:51:51 -07:00
fd2a409ea3
Skip decoding blocks that are already full
2015-12-17 12:47:05 -07:00
825296ddd8
Add comments
2015-12-16 11:30:06 -07:00
88324bf61c
Optimize indirectIndex.UnmarshalBinary further
2015-12-16 11:28:13 -07:00
70d1f45058
Load TSM files concurrently
2015-12-16 11:28:12 -07:00
737871268b
Speed up indirectIndex.UnmarshalBinary
...
Remove a bunch of unnecessary allocations to improve startup times.
2015-12-16 11:16:17 -07:00
3893bc60e1
Speed up TSM compactor
...
Just keep the current block for each iterator in the buffers.
2015-12-16 11:16:17 -07:00
00f570441b
Convert TSMKeyIterator to return blocks
2015-12-16 11:16:17 -07:00
59a57d8f73
Convert CacheKeyIterator to return encoded blocks
2015-12-16 11:16:17 -07:00
0623648140
Add chunking support back to TSMKeyIterator
...
Was removed when MergeIterator was deleted.
2015-12-16 11:16:17 -07:00
31b97c3fe0
Add max points per block back for CacheKeyIterator
...
Was removed when MergeIterator was removeed.
2015-12-16 11:16:16 -07:00
45e87cdfe4
Strip checksum when returning block from ReadBytes
2015-12-16 11:16:16 -07:00
97435b9124
Return minTime/maxTime from BlockIterator.Read
2015-12-16 11:16:16 -07:00
ce6de9728e
Add test for BlockIterator with multiple blocks for a key
2015-12-16 11:16:16 -07:00
4a3037814f
Add WriteBlock to TSMWriter
2015-12-16 11:16:16 -07:00
d99c1f944e
Add BlockIterator for reading TSM blocks without decoding
2015-12-16 11:16:16 -07:00
928aef04cd
Split data_file.go into reader.go and writer.go
2015-12-16 11:16:16 -07:00
47317d73b4
Merge pull request #5131 from influxdb/site-fixes
...
Default data logging to on
2015-12-16 10:03:25 -08:00
ad1044dde9
typo: unkown -> unknown
2015-12-15 18:10:47 -05:00
d45048455a
Default data logging to on
2015-12-15 13:15:38 -08:00
0e4bc275d8
Merge pull request #5115 from influxdb/site-fixes
...
Log TSM initialization
2015-12-15 13:13:17 -08:00
01ac0b3f23
Tweak compaction log messages
2015-12-15 10:33:13 -08:00
d89e233567
Merge pull request #5100 from influxdb/dgn-fix-4303
...
fix #4303 : don't drop from multiple databases
2015-12-15 07:27:05 -05:00
a6cdb5229d
Log tsm initialization
2015-12-14 15:50:56 -08:00
3014fb90e4
fix #4303 : don't drop from multiple databases
2015-12-12 13:54:23 -05:00
75764517f6
Merge pull request #5082 from li-ang/fix_x
...
Fix wrong value of countCompacting in WAL
2015-12-11 10:07:56 -08:00
03f8cd3956
Add comment explaining magic number
2015-12-10 11:46:40 -08:00
631ecc23de
Fix growing destination buffer during WAL entry encoding
...
The test to see if the destination buffer for encoding and decoding a WAL
entry was broken and would cause a panic if there were large batches that
would overflow the buffer size.
Fixes #5075
2015-12-10 11:46:40 -08:00
34bdffdb00
Fix wrong value of countCompacting in wal
2015-12-10 17:47:20 +08:00
b7000c80dd
count with fill(none) will drop 0 valued intervals
2015-12-09 15:20:47 -07:00
da08304780
Merge pull request #4940 from li-ang/fix_aggregative_query_err
...
Fix distributed aggregative query error
2015-12-09 11:04:40 -08:00
992aea7bd3
Merge pull request #5060 from influxdb/jw-drop-db
...
Cancel writing TSM files when engine closes
2015-12-08 16:16:07 -07:00
b192136887
Merge pull request #5058 from influxdb/pd-update-compaction-logic
...
Update TSM compaction logic
2015-12-08 18:14:15 -05:00
27cc2ea0cc
Update compact.Plan
2015-12-08 18:01:31 -05:00
d7cff651d1
Cancel writing TSM files when engine closes
...
If the engine is closed while a compaction is going on, the close call
blocks until the goroutine exits. This could be several minutes because
the control does not return back up to the channel selector while there is
still data to write.
2015-12-08 15:41:53 -07:00
96445a53a7
Update TSM compaction logic
...
* Update compaction to look at newest files of the smallest step first
* Update compaction to look at older files in larger steps if newer files don't have enough small steps to compact
* Changed the TestDefaultCompactionPlanner_CombineSequence test to reflect what's possible now. We'd only have multiple files in the same generation if the all files but one were over the max allowable size.
* Clean up the logic on when full compactions are run and when planning can be skipped
2015-12-08 17:33:38 -05:00
62cb3a1e9b
Merge pull request #5057 from influxdb/jw-5046
...
Fix leaking TSM files when compacting
2015-12-08 13:11:46 -07:00
3543917a74
Avoid allocating strings during search
2015-12-08 13:02:17 -07:00
99c313ddae
Fix leaking TSM files when compacting
...
The files being read were not closed after the compaction ran causing
them to leak.
Fixes #5046
2015-12-08 12:55:30 -07:00
9d82e24ca0
Fix performance of dropping large number of keys
2015-12-08 10:47:06 -07:00
f245b44afa
Set full compaction duration option on planner
...
Was set on engine and not planner so it was always 0.
2015-12-08 09:56:36 -07:00
d32aeb2535
Merge pull request #5031 from influxdb/jw-mintime
...
Dedupe points at query time if there are overlapping blocks
2015-12-07 21:28:29 -07:00
87892d79da
Dedupe points at query time if there are overlapping blocks
2015-12-07 21:10:10 -07:00
bb386219f4
ran go fmt on mmap_solaris.go #4787
2015-12-07 17:41:26 -08:00
0f889a77d1
fix tsm1 for Solaris #4787 , passes unit tests now
2015-12-07 17:14:26 -08:00
c13f8e9128
Fix wrong results of distributed aggregative query
2015-12-08 07:08:46 +08:00
Jason Wilder
Philip O'Toole
Alexandre Viau
Philip O'Toole
dgnorton
liang@qiniu.com
Nathaniel Cook
Jason Wilder
Paul Dix
Fazal Majid