bf65e967aa
Add test for compacting multiple TSM files
2015-12-03 10:36:17 -05:00
67ea0b757b
Merge pull request #4848 from influxdb/cluster-integration
...
Added framework for cluster integration testing
2015-12-03 08:56:51 -06:00
edf8e31ee6
update changelog
2015-12-03 08:09:18 -06:00
0c2588ed43
cluster retention auto create test
2015-12-03 08:08:57 -06:00
52da1c76d6
cluster retention policy tests
2015-12-03 08:08:56 -06:00
96c230d968
allow for configurable cluster creation
2015-12-03 08:08:56 -06:00
ab57bde115
more tests, some refactoring
2015-12-03 08:08:56 -06:00
23435299ca
disable test parallelism
2015-12-03 08:08:56 -06:00
91da96eb34
fix race in test harness
2015-12-03 08:08:56 -06:00
6e845839c8
fix flakey test harness
2015-12-03 08:08:56 -06:00
967a53cabd
start sharing integration tests for cluster tests
2015-12-03 08:08:56 -06:00
cf4e901078
silence registration logging for testing
2015-12-03 08:04:10 -06:00
35b438f8fa
silence meta/rpc logging for testing
2015-12-03 08:04:10 -06:00
3208564192
fix RP not found error messages
2015-12-03 08:04:09 -06:00
657877dd94
make not found err messages more consistent
2015-12-03 08:04:09 -06:00
343f00d1f2
fix go vet errors
2015-12-03 08:04:09 -06:00
76d291e88e
beginning of cluster test harness
2015-12-03 08:04:09 -06:00
b0fb8a0a27
Update TSM cache, compact, wal, encoding
...
* Update cache to have a single slice of values for a key (removed checkpoints)
* Changed compact.Plan to only worry about TSM files.
* Updated Plan to not return an error since there was no case in which it would.
* Update WAL to not keep stats since they're no longer needed.
* Update engine to flush the Cache/WAL to a new TSM file when the min threshold is hit.
* Split compact logic between TSM compacts and WAL/Cache writes.
* Remove unnecessary merge iterator, wal segment iterator, and other no longer necessary stuff.
* Remove the asending bool from the Dedupe method. Values should always be in ascending order. It's up to the cursor to iterate through values based on the direction. Giving the cursor responsibility makes it so we don't need to sort, dedupe or reallocate anything for different query orders.
* Updated engine to use its locks to ensure writes and cache flushes don't cause a race.
* Update all tests with new signatures. Removed a bunch of tests around TSM rewrites and WAL segment iteration that are no longer necessary.
2015-12-03 08:11:50 -05:00
f9fa366861
Add querying across cluster
...
Add support for precision
2015-12-02 14:49:23 -08:00
d85f3c3dc7
Merge pull request #4955 from influxdb/ga-config-tweaks
...
Clarify engine comment about tsm1 in the sample config
2015-12-02 13:51:45 -08:00
28b9fdc08d
Merge pull request #4959 from influxdb/jw-tsm-query
...
TSM dev engine startup
2015-12-02 14:37:16 -07:00
83ccaaa656
Reload cache at startup
2015-12-02 14:16:36 -07:00
94604ccc07
Merge pull request #4956 from influxdb/jw-mmap
...
TSM File Compaction
2015-12-02 14:01:40 -07:00
ba99dece0c
Wire up tsm1dev engine cursor
2015-12-02 14:01:10 -07:00
3a8a19a99d
Implement LoadMetaDataIndex for tsm1dev engine
2015-12-02 13:38:06 -07:00
3014d7e391
Return errors for func not implemented in tsm1dev engine
2015-12-02 11:06:01 -07:00
a7e21c2975
Don't set a cache memory limit by default
...
100mb is easy it hit even with basic stress test config. Don't set
a limit by default so that an operator can size it appropriately based
on their hardware.
2015-12-02 11:01:13 -07:00
da8c56049b
FormatDuration uses "u" for microsecond units
...
Previously, it was formatting microsecond durations without any units.
Currently, all durations must have units explicitly specified.
2015-12-02 09:00:58 -08:00
6847a6ba0c
Fix rebase
2015-12-02 09:47:16 -07:00
751d1dd467
Don't rewrite TSM files while WAL segments exist
...
This approach is not working and needs to be reworked.
2015-12-02 09:45:24 -07:00
5744f5ba02
Add ability to filter values by time when writing TSM files
2015-12-02 09:45:24 -07:00
708266da69
Cache related compaction fixes
2015-12-02 09:45:24 -07:00
231c052003
Don't limit WAL segments during compaction
...
Since they are already loaded in the cache, this limit is not really
needed anymore.
2015-12-02 09:45:24 -07:00
7e249e0555
Use CacheKeyIterator instead of WALKeyIterator during compactions
2015-12-02 09:45:24 -07:00
4a03469662
Integrate TSM compaction into dev engine
2015-12-02 09:45:23 -07:00
78fda2b89b
Implement WAL SegmentStats for compactions
2015-12-02 09:45:23 -07:00
1485ea7e41
Implement Size on TSMReader
2015-12-02 09:45:23 -07:00
d4b1c25f8e
Add CompactionPlanner type
...
CompactionPlanner is used to determine which files (WAL Segments, TSM
Files) to include in a given compaction run.
2015-12-02 09:45:23 -07:00
5291fbcf39
Add TSM support to MergeIterator
...
Enables the ability to combine multiple TSM files into one as well
as merge existing TSM files with newer WAL segment values.
2015-12-02 09:45:23 -07:00
acdb6bcdf6
Add TSMKeyIterator
...
Allows iterating of multiple TSM files in sort key and values order.
2015-12-02 09:45:23 -07:00
4b6767bf01
Add MMAP based file reader
2015-12-02 09:45:23 -07:00
b5200ad472
Update CHANGELOG.md
2015-12-02 11:38:43 -05:00
6e1d0f47d4
Merge pull request #4921 from pires/3170-db_not_found
...
Handler errors should be formatted as JSON.
2015-12-02 11:36:53 -05:00
5958f31130
Update CHANGELOG.md
2015-12-02 11:35:00 -05:00
218ef13ac1
Merge pull request #4866 from pires/2676-createdb_with_retention
...
Added support for configurable default retention policy on database creation
2015-12-02 11:32:52 -05:00
e5b9ac944b
Update changelog for #4876
...
changelog entry for #4876
2015-12-02 08:58:38 -06:00
3cd8056664
Merge pull request #4876 from e-dard/lint
...
Lint
2015-12-02 08:55:47 -06:00
8384ba3e84
Update comments.
2015-12-02 12:35:58 +00:00
fccd6a9399
Clarify engine comment about tsm1
2015-12-02 00:09:50 -08:00
d8715ee3dd
Order the MapItems by timestamp
2015-12-02 10:47:12 +08:00
Paul Dix
Cory LaNou
David Norton
Michael Desa
Gunnar
Jason Wilder
Jason Wilder
Mark Rushakoff
Edd Robinson
gunnaraasen
liang@qiniu.com