345 Commits (3de55171d326004ed64046594cd9fca5a0b0c4ee)

 

All Branches   

Search

Author	SHA1	Message	Date
Fabian Reinartz	3e569bc964	Optimize memory allocations in writer	8 years ago
Fabian Reinartz	cc0a7c8279	Create alloc and inuse space heap profile	8 years ago
Fabian Reinartz	ffb24a98f4	Add missing unlock, run debug endpoint in benchmark	8 years ago
Fabian Reinartz	21b97d1e04	Fix compaction selection procedure	8 years ago
Fabian Reinartz	327e07e8d0	Properly sync moves and removes in compactor	8 years ago
Fabian Reinartz	92120448c2	Properly cleanup compacted dirs, fixes, docs	8 years ago
Fabian Reinartz	2c3e778d90	Compactor interface	8 years ago
Fabian Reinartz	2c3b56350a	Write meta.json file atomically	8 years ago
Fabian Reinartz	6c4217276f	Periodically trigger compaction ... This addresses an issue where the compaction triggered on cutting a new block doesn't find anything as the writers are still active on the block that should be ready for compaction.	8 years ago
Fabian Reinartz	db5c88ea9a	Misc compaction fixes	8 years ago
Fabian Reinartz	b281e4e39b	Accept prometheus.Registerer in constructor	8 years ago
Fabian Reinartz	306831f151	Add per-block state ULID	8 years ago
Fabian Reinartz	9a5dfadb09	Tweak IndexWriter interface, serialize directly into dir	8 years ago
Fabian Reinartz	78780cd2ba	Segment chunk file ... 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.	8 years ago
Fabian Reinartz	a3b47c4929	Create default logger for DB	8 years ago
Fabian Reinartz	f734773214	Replace per-file locking with single PID lock file ... File locks have a multitude of problems that make them hard to use correctly. As they are just advisory, they are only meaningful to prevent accidents like running the same process twice. A simple PID file lock works reliably in those cases and is simpler.	8 years ago
Fabian Reinartz	c808928b90	SeriesWriter -> ChunkWriter ... This commit simplifies a SeriesWriter into a ChunkWriter and detaches it entirely from the notion of a series and the series index.	8 years ago
Fabian Reinartz	a3d042b54e	Support multiple chunk files in read path	8 years ago
Fabian Reinartz	afa084920c	Use Castagnoli polynomial for CRC32s; cache them	8 years ago
Fabian Reinartz	9c7a88223e	Add full encode/decode WAL cycle test	8 years ago
Fabian Reinartz	2c97428a79	Add basic WAL tests	8 years ago
Fabian Reinartz	84e8027a8e	Close consumed WAL segments, verify checksums on read	8 years ago
Fabian Reinartz	eeb03e97e2	Add headers and format flag for WAL segments	8 years ago
Fabian Reinartz	79944a5912	Break out WAL into segment files	8 years ago
Fabian Reinartz	987a90d149	Don't delete files if retention duration is 0	8 years ago
Fabian Reinartz	9c76624df2	Add initial retention cutoff	8 years ago
Fabian Reinartz	f1435f2e2c	Track appended samples properly in metric	8 years ago
Fabian Reinartz	012cf4ef25	Count writer references on head blocks	8 years ago
Fabian Reinartz	5a1c8eaa0e	Fix missing appends after reference lookups	8 years ago
Fabian Reinartz	f556036037	Close blocks before overwriting with compacted one ... This prevents the meta.json file of a compacted block to be overwritten with data of the old block.	8 years ago
Fabian Reinartz	ac5229e1b4	Correctly write empty blocks and extend appenders by new blocks	8 years ago
Fabian Reinartz	42fa342229	Improve multi-head handling ... This improves handling of multiple head blocks. Configuration is simplified to specify the number of concurrently appendable blocks.	8 years ago
Fabian Reinartz	30efe4a58c	Support writing to multiple head blocks ... This is an initial (and hacky) first pass on allowing appending to multiple blocks simultaniously to avoid dropping samples right after cutting a new head block. It's also required for cases like the PGW, where a scrape may contain varying timestamps.	8 years ago
Fabian Reinartz	a61a31a5d7	compaction: add fast-path for compacting mem blocks	8 years ago
Fabian Reinartz	c20cc44b06	Add docs, write sequence number to meta.json	8 years ago
Fabian Reinartz	30d8866c13	Limit compaction range, make cut and compact concurrent	8 years ago
Fabian Reinartz	67d185ceb9	Compact based on compaction generation	8 years ago
Fabian Reinartz	472c618c39	Drop out-of-bound samples	8 years ago
Fabian Reinartz	d4779b374c	Properly track and write meta file	8 years ago
Fabian Reinartz	9ddbd64d00	Move stats into meta.json file, cleanup, docs	8 years ago
Fabian Reinartz	2f02f86b62	Fix WAL tests	8 years ago
Fabian Reinartz	e006bc6dc6	Improve error messages, create regular dir for block	8 years ago
Fabian Reinartz	d2322f6095	Improve compaction processing	8 years ago
Fabian Reinartz	5ceca3c810	Write to WAL before appending to memory storage	8 years ago
Fabian Reinartz	343dd9d94c	Fix wrong byte size in WAL base ref	8 years ago
Fabian Reinartz	5fb01d41aa	Use new Prometheus text format parser	8 years ago
Fabian Reinartz	dd0b69fe1b	Export ErrNotFound	8 years ago
Fabian Reinartz	9cf49f68e9	wal: use larger buffer	8 years ago
Fabian Reinartz	1c80c33e72	Fix bug of unsorted postings lists being created ... The former approach created unordered postings list by either map iteration of new series being unsorted (fixable) or concurrent writers creating new series interleaved. We switch back to generating ephemeral references for a single batch. Newly created series have to be re-set upon the next insert.	8 years ago
Fabian Reinartz	c7f5590a71	Ensure order of postings when adding new series	8 years ago