e7cb9ddb9f
Use a sync.pool for the staging buffer in codec.go.
...
Change-Id: I1aae6847f77b5a7c75582b07c199b1943cf90552
2014-11-25 17:02:01 +01:00
4770cf76a4
Make index package more self-contained.
...
Moved interna from diskPersistence into the indexer.
TotalIndexer now called diskIndexer.
Change-Id: I6c8c62cb171f12bbd8a5474773af7786d71ba388
2014-11-25 17:02:01 +01:00
89f10e8eb2
Move to using the standard library interfaces for encoding/decoding.
...
BinaryMarshaler instead of encodable.
BinaryUnmarshaler instead of decodable.
Left 'codable' in place for lack of a better word.
Change-Id: I8a104be7d6db916e8dbc47ff95e6ff73b845ac22
2014-11-25 17:02:01 +01:00
af77d5ef0b
Added a few missing implementations in index.go.
...
Also, added closing of persistence and mem storage.
Change-Id: Iacf0d22c3520dd2584d9546984c1f8a5ed6cd54e
2014-11-25 17:02:01 +01:00
cca7ebe906
Some more cleanups / obsolete code removals.
...
Change-Id: I584144ceeeedafdb114266d8a6d2513e67b1d010
2014-11-25 17:02:00 +01:00
7e85711df0
Beginnings of a tiered index implementation.
...
This reintroduces a LevelDB-based metrics index.
Change-Id: I4111540301c52255a07b2f570761707a32f72c05
2014-11-25 17:02:00 +01:00
8dfaa5ecd2
Remove use of freelists for chunk bufs.
...
Change-Id: Ib887fdb61e1d96da0cd32545817b925ba88831c1
2014-11-25 17:02:00 +01:00
7b35e0f0b8
Use constants from math package instead of literals.
...
Change-Id: I55427ba32c2cbb32ee42ec1e3153160965ab8b3c
2014-11-25 17:02:00 +01:00
15929eece2
Unpin any already loaded chunks upon preloading error.
...
Change-Id: Ib451136e3ef21bce8b814c21b66eaab727ab341b
2014-11-25 17:02:00 +01:00
fd01d07589
Check that chunk buffer length fits in 16 bit.
...
Change-Id: Id086a54aa8a1990c1979e747c1c02e53bed6d447
2014-11-25 17:02:00 +01:00
1ca7f24137
Remove float diff tolerance altogether.
...
Change-Id: I9ea9683a4665d5800fca75560bb4b8a8b4406d55
2014-11-25 17:02:00 +01:00
d742edfe0d
Fix precision loss.
...
Large delta values often imply a difference between a large base value
and the large delta value, potentially resulting in small numbers with
a huge precision error. Since large delta values need 8 bytes anyway,
we are not even saving memory.
As a solution, always save the absoluto value rather than a delta once
8 bytes would be needed for the delta. Timestamps are then saved as 8
byte integers, while values are always saved as float64 in that case.
Change-Id: I01100d600515e16df58ce508b50982ffd762cc49
2014-11-25 17:02:00 +01:00
dc2e463a97
Improvements after review.
...
Change-Id: I484359282d4c7113518bbbb131f4f18383c08fdb
2014-11-25 17:02:00 +01:00
52c9dc43a3
Improve testing.
...
In particular, create a fuzz test for time series.
Change-Id: I523a17912405a0b6b46bd395c781d201dfe55036
2014-11-25 17:02:00 +01:00
3b25867d61
Add chunk persistence tests, fix storage tests.
...
Change-Id: Id0b8f5382e99efa839cc0f826e92bbda985fe9a9
2014-11-25 17:02:00 +01:00
ecdf5ab14f
Index-persistence switched from gob to a hand-coded solution.
...
Change-Id: Ib4ec42535bd08df16d34d4774bb638e35c5a1841
2014-11-25 17:02:00 +01:00
e7ed39c9a6
Initial experimental snapshot of next-gen storage.
...
Change-Id: Ifb8709960dbedd1d9f5efd88cdd359ee9fa9d26d
2014-11-25 17:02:00 +01:00
Bjoern Rabenstein
Julius Volz