37 Commits (9be95a3e8ccf2a5cd56a1dfce78554676c636ae3)

Author	SHA1	Message	Date
Robert Fratto	9be95a3e8c	chore(dataobj): reduce memory overhead of merging logs stripes (#16833)	2 months ago
benclive	979f7614bc	perf: Optimization pass for reading from dataobjs (#16747)	2 months ago
Robert Fratto	cd11367148	chore(dataobj): Wire dataset.Reader into dataobj.LogsReader and dataobj.StreamsReader (#16701) ... Co-authored-by: Ashwanth Goli <iamashwanth@gmail.com>	2 months ago
Robert Fratto	8c4eb428c3	chore(dataobj): Download pages in 16MB batches (#16689)	2 months ago
Robert Fratto	abf3772366	perf(dataobj): improve parallelized read spead of Zstd (#16632)	3 months ago
Paul Rogers	27431b7e7e	chore: Linting update for new golangci (#16572)	3 months ago
Robert Fratto	7f0dc01e21	chore(dataobj): introduce more efficient dataset reading (#16429) ... This commit introduces a new API, dataset.Reader, which scans through values in datasets more efficiently than dataset.Iter. As a result, dataset.Iter has been removed in favour of the new Reader. dataset.Reader is more efficient than dataset.Iter because: - It avoids using iter.Pull; the number of values flowing through coroutines added a significant amount of CPU overhead. - It supports efficient uses of predicates, where non-predicate columns are only loaded after finding matching rows from predicate columns; this avoids loading unnecessary pages. - It adds initial support for bulk page downloading, so that we need fewer roundtrips to object storage when iterating over a dataset. (This is not fully implemented yet; see below). - Early performance benchmarks see a ~3.4x speed improvement over reading 7GB of uncompressed logs, going from 192 MB/s (with dataset.Iter) to 652 MB/s (with dataset.Reader). This commit is truly massive, and to avoid it getting any larger, I'm leaving some follow up work to additional commits: - Updating dataobj.LogsReader and dataobj.StreamsReader to use the new API. - Adding support for downloading pages in batches; dataset.Reader will request multiple pages at once, but our decoder still unwraps that into several GET requests to object storage. Signed-off-by: Robert Fratto <robertfratto@gmail.com> Co-authored-by: Cyril Tovena <cyril.tovena@gmail.com>	3 months ago
Christian Haudum	f6fcc1194e	chore(dataobj): Decode values in batches (#16418) ... Signed-off-by: Christian Haudum <christian.haudum@gmail.com>	3 months ago
Jackson Coelho	290c14a8cb	chore: fix flush process for dataobj (#16393)	3 months ago
Ashwanth	651d410eea	chore(dataobj): add "uncompressed size" column to streams section (#16322)	3 months ago
Owen Diehl	66889ec51d	feat(dataobj): cardinality estimation (#16233)	3 months ago
Robert Fratto	66b2721cfa	chore(dataobj): do not panic on unrecognized compression type (#16088)	4 months ago
benclive	7f32de6cf2	chore(dataobj): Refactor processor & builder to separate concerns (#16055)	4 months ago
benclive	ca4c025ad0	chore(dataobj): Create initial dataobj builder (#16011) ... Co-authored-by: Cyril Tovena <cyril.tovena@gmail.com> Co-authored-by: Robert Fratto <robertfratto@gmail.com>	4 months ago
Robert Fratto	5ccc6790cb	chore(dataobj): support computation of min/max values in pages and columns (#16015)	4 months ago
Robert Fratto	1adb1e39d3	chore(dataobj): add initial high-level APIs for reading streams and log records (#15974)	4 months ago
Robert Fratto	5929b05a64	chore(dataobj): deduplicate decoder code across bucket and io.ReadSeeker (#15945)	4 months ago
Christian Haudum	ed863fe1be	chore: Fix Loki arm builds (#15936) ... Signed-off-by: Christian Haudum <christian.haudum@gmail.com>	4 months ago
Robert Fratto	93cee63f59	chore(dataobj): add compression ratio and final object size distributions (#15848)	4 months ago
Robert Fratto	948f5c5f3e	chore(dataobj): Reintroduce sorting of the logs section (#15906)	4 months ago
Robert Fratto	64665c4595	chore(dataobj): promote metadata types to hold uint64 instead of uint32 (#15850)	4 months ago
Robert Fratto	2a60011b13	chore(dataobj): reduce total allocations while encoding (#15846)	4 months ago
Robert Fratto	7eb5053d1c	chore(dataobj): improve performance of Streams.EstimatedSize (#15833)	4 months ago
Robert Fratto	093e36af58	chore(dataobj): instrument data objects (#15803)	4 months ago
Robert Fratto	848c31fce9	chore(dataobj): temporarily disable sorting (#15799)	4 months ago
Robert Fratto	127ad5326f	chore(dataobj): support for building and flushing data objects (#15780)	4 months ago
Robert Fratto	83a506954c	chore(dataobj): fix bug where instances of *bytes.Buffer are incorrectly shared (#15776)	4 months ago
Robert Fratto	5980396b76	chore(dataobj): fix bug with partial reads of strings (#15767)	4 months ago
Robert Fratto	11714a71c7	chore(dataobj): add logs tracking and encoding (#15757)	4 months ago
Robert Fratto	aec8e968da	chore(dataobj): track non-NULL values in pages/columns (#15758)	4 months ago
Robert Fratto	d1fd0b9ffc	chore(dataobj): add streams tracking and encoding (#15713)	4 months ago
Robert Fratto	bcec63d9c2	chore(dataobj): logs section metadata and encoding/decoding (#15720)	4 months ago
Robert Fratto	896e138425	chore(dataobj): data object encoding and decoding (#15676)	4 months ago
Robert Fratto	c581218c4f	chore(dataobj): add Dataset with iteration and sorting support (#15652)	5 months ago
Robert Fratto	f2fc0c26c2	chore(dataobj): column building (#15634) ... This commit adds the ability to accumulate sequences of dataset.Value into a column, which is split up across multiple pages. Each page is broken down into two parts: * A bitmap-encoded sequence of booleans, where 1 indicates a row has a value and 0 indicates the row is NULL, and * the encoded sequence of non-NULL values, whose encoding is determined by the column options. The sequence of non-NULL values is then optionally compressed. This commit also includes initial support for reading these columns, starting with internal-only helper utilities for unit tests.	5 months ago
Robert Fratto	6042d0712e	chore(dataobj): add bitmap encoding (#15629)	5 months ago
Robert Fratto	9a21590238	chore(dataobj): initial commit of value encoding (#15606)	5 months ago