ac49f8c15e
Consolidate persistence and compaction
2017-01-03 16:49:37 +01:00
e7f04d14d5
Lock mmapped files
2017-01-03 10:09:20 +01:00
91b65b55e7
Run persistence in separate goroutine
2017-01-02 22:24:35 +01:00
a648ef5252
Convert persister into function
2017-01-02 16:58:47 +01:00
dbd2b21d2e
Make persistence atomic
2017-01-02 14:41:13 +01:00
62b8ded0a5
Rename iterator value getters to At()
2017-01-02 13:33:06 +01:00
5c45a1cc6f
Remove shardSeriesSet caching
2017-01-02 12:05:52 +01:00
beb842a856
Change block interface
...
This changes the block interface to directly expose index
and series readers rather than the direct querier
2017-01-02 11:12:28 +01:00
5d75a3dc7b
Add basic compaction
...
This adds a basic compactor that will merge two persisted blocks into
one. It simply fully rewrites the index and concatenates the chunk
lists.
It just writes into the current working dir and doesn't properly handle
which blocks to compact for now.
2017-01-02 10:34:55 +01:00
5d7ec06e04
Use ChunkMeta in SeriesWriter
2017-01-01 20:01:17 +01:00
c00d17e691
Modify IndexReader API to accomodate compaction
...
This changes the IndexReader API to expose plain labels
and chunk meta information instead of a Series interface.
Dropping of irrelevant chunks is moved into the querier.
A LabelIndices method is added to query for existing label
value indices.
2016-12-31 16:24:04 +01:00
1e1a37b15b
Remove double-reference in chunk hashmap
2016-12-31 10:19:02 +01:00
675f0886f0
Append to chunks cannot error
2016-12-31 10:10:27 +01:00
7280533c42
Add basic shard metrics
2016-12-31 09:48:49 +01:00
a009247ab7
Add matching of empty label
2016-12-30 19:36:28 +01:00
eb4f366988
Add return error to Appender.Add
2016-12-29 11:03:39 +01:00
3a5468f251
Lock shards during querying and shutdown
2016-12-28 11:41:44 +01:00
286293802b
Add merge postings
2016-12-28 11:02:19 +01:00
ab7fbc05ad
Zero timestamp as base, use binary search list postings
2016-12-28 08:50:20 +01:00
dd72b52098
Add postings intersection
2016-12-27 11:32:10 +01:00
f8111cef0e
Fix chunk series iterator seeking
2016-12-26 16:55:44 +01:00
201d7687b6
Fix uniqueness of new series
2016-12-26 16:55:32 +01:00
5efe1d178e
labels: add Compare and String methods
2016-12-24 13:49:35 +01:00
0d0c5cfaf1
labels: add string constructor, expose matcher
2016-12-24 10:19:46 +01:00
787199a88e
Fix erroneous value assignments
2016-12-22 20:57:00 +01:00
8aba95048a
Rename to OpenHeadBlock
2016-12-22 20:00:24 +01:00
cabd7e4ebc
Add small testdata file
2016-12-22 19:15:37 +01:00
e7edae39b2
Use page buffered writer for WAL
2016-12-22 16:14:34 +01:00
9c6a72aadd
Load head with WALs correctly
2016-12-22 15:54:39 +01:00
1dde3b6d31
Add WAL decoder+loading and benchmarks
2016-12-22 15:18:33 +01:00
0b8c77361e
Add initial WAL writing
2016-12-22 12:05:24 +01:00
2a825f6c28
Consolidate mem index into HeadBlock
2016-12-22 01:12:28 +01:00
869cccf080
Test and fixes for buffered iterator
2016-12-21 16:06:33 +01:00
0a94f58f1a
Fix test import of labels, simplify constructor names
2016-12-21 15:12:26 +01:00
da2beb3e6d
Fix zero division, add buffer series iterator
2016-12-21 13:04:51 +01:00
dbca3453fb
Add label clone benchmark
2016-12-21 10:37:38 +01:00
ede733ab6c
Extract labels package
2016-12-21 09:39:01 +01:00
ee217adc7e
Redfine append interface, remove old Prometheus storage from bench
2016-12-21 00:02:37 +01:00
cddc29fa17
Fix labels comparison, fetch correct labels
2016-12-20 14:54:52 +01:00
ce7f4106c2
Reda correct label number, fix buffered iterator panic
2016-12-20 14:21:50 +01:00
d9ca4b47f5
Fix offset errors, fix persisted postings order
2016-12-20 13:14:55 +01:00
1b23d62e3f
Properly close files before reopening
2016-12-19 22:37:03 +01:00
00a503129b
Use contextualized and traced errors in reader
2016-12-19 22:29:49 +01:00
282d9ae6e2
Implement label value queries in all layers.
2016-12-19 12:26:25 +01:00
aabb21f4b9
Add shard series set test
2016-12-19 11:44:11 +01:00
bad93d8d57
Extract head serialization into Head method
2016-12-18 14:43:27 +01:00
b08f82fa4e
Pre-select relevant chunks on series access.
...
This adds interval metadata to indexed chunks. The queried interval
is used to filter chunks when queried from the index to save
unnecessary accesses of the chunks file.
This is especially relevant for series that come and go often and larger
files.
2016-12-16 12:13:17 +01:00
bd77103a49
Add stats serialization, load querier of all blocks
2016-12-15 16:14:33 +01:00
1a35e54450
Add chained iterator, skipping seek added
2016-12-15 15:23:15 +01:00
205edd2da9
Add byte/string equality check benchmark
2016-12-15 12:15:54 +01:00
Fabian Reinartz