| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | The scheduler now spawns a seperate merge thread | Douglas Rumbaugh | 2023-09-18 | 4 | -58/+221 |
| | | | | | | | | | | | | Merges are now executed from a seperate thread within the scheduler that wakes up via condition variables when new merge tasks are scheduled. In addition, tombstone limits are now enforced by the scheduler, with new merges being scheduled as needed. There are still a few tests failing, notably the zero tombstones in the last run invarient is not holding under tiering with tombstones. Need to look into that yet. | ||||
| * | Moved individual merge task execution into the scheduler | Douglas Rumbaugh | 2023-09-18 | 3 | -35/+98 |
| | | | | | | | | | | | | | | | | | | | | | This change is made in anticipation of scheduling each task using a specific thread, and required some modification to the interface of ExtensionStructure. Namely, 1. ExtensionStructure now supports a get_merge_tasks() interface, which returns a list of the individual level merges that would need to be performed to complete a buffer flush of specified size. 2. merge_levels and merge_buffer have been promoted to the public interface, to allow their use within the scheduler. 3. merge_buffer has been modified to assume that the structure already can support a direct flush of the buffer into L0, it is now the responsibility of the caller to ensure that the necessary merges have already been completed prior to calling this method. Currently, preemptive tombstone compactions are non-functional, so some unit tests are failing. This will be fixed when the thread scheduling system is set up. | ||||
| * | General bugfixes | Douglas Rumbaugh | 2023-09-18 | 2 | -1/+5 |
| | | |||||
| * | Began re-architecting the project for concurrency support | Douglas Rumbaugh | 2023-09-13 | 7 | -308/+645 |
| | | | | | | The project is now in a state where it builds, but it probably has a lot of bugs still. | ||||
| * | Migrated over to using psudb-common utilities/headers | Douglas Rumbaugh | 2023-08-24 | 3 | -12/+12 |
| | | |||||
| * | Expanded query interface | Douglas Rumbaugh | 2023-07-27 | 2 | -8/+43 |
| | | | | | | Query interface now enables skipping of delete processing and stopping query processing when first match is found. | ||||
| * | Alex shard progress | Douglas Rumbaugh | 2023-07-26 | 1 | -0/+7 |
| | | |||||
| * | VPTree: fixed knn query | Douglas Rumbaugh | 2023-07-24 | 1 | -2/+8 |
| | | |||||
| * | Cosine Similarity Type | Douglas Rumbaugh | 2023-07-24 | 1 | -4/+48 |
| | | |||||
| * | Added the parameter argument to query merge routine | Douglas Rumbaugh | 2023-07-17 | 1 | -1/+1 |
| | | | | | | This is necessary for KNN, but it unused for all currently implemented query types. | ||||
| * | PriorityQueue: generalized priority queue comparison operation | Douglas Rumbaugh | 2023-07-17 | 1 | -0/+11 |
| | | | | | | Generalized the comparison used for the priority queue to enable its use within the KNN query code. | ||||
| * | VPTree: changed Point format to a D-dimensional point. | Douglas Rumbaugh | 2023-07-17 | 1 | -6/+24 |
| | | |||||
| * | VPTree: use a secondary hash-table for point lookups | Douglas Rumbaugh | 2023-07-17 | 1 | -0/+9 |
| | | |||||
| * | Initial commit of VPTree-related code | Douglas Rumbaugh | 2023-07-13 | 1 | -11/+36 |
| | | | | | | | Point lookups are currently broken; I suspect that there is something wrong with tree construction, although the quickselect implementation seems to be fine. | ||||
| * | Fixed query errors | Douglas Rumbaugh | 2023-07-03 | 1 | -1/+1 |
| | | |||||
| * | Fixed bug(s) in tagging-based deletes | Douglas B. Rumbaugh | 2023-06-09 | 2 | -1/+2 |
| | | |||||
| * | Build changes and interface cleanup | Douglas B. Rumbaugh | 2023-06-09 | 2 | -6/+6 |
| | | | | | | | | | | | Renamed the get_record_cnt() functions to get_record_count() for consistency, dropped references to SSIs, and added openmp build flags for PGM related targets. Also adjusted dynamic_extension_tests.inc to fail when an erase fails during the static structure testing as part of debugging a delete cancellation problem under leveling. | ||||
| * | General header/file cleanup | Douglas Rumbaugh | 2023-06-07 | 1 | -2/+0 |
| | | |||||
| * | Interface adjustments | Douglas Rumbaugh | 2023-06-07 | 2 | -33/+10 |
| | | | | | | | Layout and Delete Policies are now specified via template parameters, and rejection sampling has been removed as an argument to the mutable buffer constructor. | ||||
| * | Added a pre-query hook for processing states | Douglas Rumbaugh | 2023-06-07 | 1 | -1/+3 |
| | | | | | | This is used for setting up the query alias structure stuff for sampling queries. | ||||
| * | InternalLevel: bugfix when building under tagging | Douglas Rumbaugh | 2023-06-07 | 1 | -1/+1 |
| | | |||||
| * | Fixed uninitialized record header issue | Douglas Rumbaugh | 2023-05-30 | 1 | -0/+1 |
| | | |||||
| * | Framework query bugfixes | Douglas Rumbaugh | 2023-05-29 | 1 | -1/+1 |
| | | |||||
| * | Framework-level query testing + fixes | Douglas Rumbaugh | 2023-05-29 | 1 | -9/+11 |
| | | |||||
| * | WIRS Query tests + fixes | Douglas Rumbaugh | 2023-05-29 | 1 | -0/+4 |
| | | |||||
| * | Fixed InternalLevel memory leak | Douglas Rumbaugh | 2023-05-29 | 2 | -41/+61 |
| | | |||||
| * | Adjusted the way that Wrapping records works to clean up interfaces | Douglas Rumbaugh | 2023-05-29 | 4 | -71/+58 |
| | | |||||
| * | Tests and bugfixes for framework | Douglas Rumbaugh | 2023-05-29 | 5 | -53/+62 |
| | | |||||
| * | More updates/restructuring | Douglas Rumbaugh | 2023-05-22 | 5 | -40/+180 |
| | | |||||
| * | Progress towards generalization of shard interface | Douglas Rumbaugh | 2023-05-22 | 5 | -486/+215 |
| | | |||||
| * | Started implementing shard interface (not finished yet) | Douglas Rumbaugh | 2023-05-17 | 3 | -34/+67 |
| | | |||||
| * | Removed unncessary tagging paramter from shards and levels | Douglas Rumbaugh | 2023-05-17 | 2 | -30/+26 |
| | | |||||
| * | Record format generalization | Douglas Rumbaugh | 2023-05-15 | 3 | -126/+101 |
| | | | | | | Currently, tombstone counting is bugged. But the rest of it appears to be working. | ||||
| * | Ported over IRS with unit tests | Douglas Rumbaugh | 2023-05-09 | 1 | -1/+28 |
| | | |||||
| * | Header update | Douglas Rumbaugh | 2023-05-09 | 1 | -0/+9 |
| | | |||||
| * | Dynamic Extension unit tests + bugfixes | Douglas Rumbaugh | 2023-05-09 | 2 | -87/+89 |
| | | |||||
| * | MutableBuffer tests and bugfixes | Douglas Rumbaugh | 2023-05-09 | 1 | -1/+1 |
| | | |||||
| * | Initial port of DynamicExtension framework | Douglas Rumbaugh | 2023-05-09 | 1 | -0/+633 |
| | | |||||
| * | Initial port of InternalLevel | Douglas Rumbaugh | 2023-05-09 | 2 | -0/+266 |
| | | |||||
| * | Initial port of WIRS structure and mutable buffer | Douglas Rumbaugh | 2023-05-09 | 1 | -0/+236 |