| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Improved statistics calculation | Douglas Rumbaugh | 2025-04-25 | 3 | -83/+116 |
| | | |||||
| * | Scheduler statistics tracking update | Douglas Rumbaugh | 2025-04-25 | 6 | -38/+130 |
| | | | | | | | | | | The current scheme is really inefficient in terms of retreival of the results, but keeps the critical path mostly clear. It's probably worth it to do a more organized tracking of the data as it comes in, to avoid an n^2 statistics generation step at the end. | ||||
| * | switched k to a double | Douglas Rumbaugh | 2025-04-17 | 5 | -16/+18 |
| | | |||||
| * | DynamicExtension.h: Updated function docstrings | Douglas Rumbaugh | 2025-04-10 | 1 | -23/+26 |
| | | |||||
| * | DynamicExtension.h: Added the insertion rate limiter | Douglas Rumbaugh | 2025-04-10 | 1 | -52/+98 |
| | | | | | | | The exact determination of *how* to use this mechanism will be contigent on some of the math I'm working on at the moment. | ||||
| * | Missed cmakelists in last commit | Douglas Rumbaugh | 2025-04-09 | 1 | -0/+11 |
| | | |||||
| * | New benchmarks | Douglas Rumbaugh | 2025-04-09 | 2 | -0/+337 |
| | | |||||
| * | Disabled early abort for point lookups | Douglas Rumbaugh | 2025-04-09 | 3 | -9/+36 |
| | | | | | | | | I'm having some trouble getting "bad" query performance, so I'm going to try using PLs w/o early abort as a worst-case scenario. This should get the best per-shard performance scaling | ||||
| * | BSM bugfixes | Douglas Rumbaugh | 2025-04-08 | 3 | -16/+12 |
| | | |||||
| * | Implemented the legacy policies and fixed a few bugs | Douglas Rumbaugh | 2025-04-07 | 10 | -163/+195 |
| | | |||||
| * | working commit (temporary progress, doesn't build) | Douglas Rumbaugh | 2025-04-05 | 12 | -118/+148 |
| | | |||||
| * | LockManager.h: adjusted unlock procedure | Douglas Rumbaugh | 2025-03-03 | 1 | -1/+2 |
| | | | | | | There was a race condition. Now there isn't... or at least there's one less. | ||||
| * | Fixed a few concurrency bugs | Douglas Rumbaugh | 2025-03-03 | 21 | -253/+370 |
| | | |||||
| * | Query Preemption: still has one or two bugs, but mostly works | Douglas Rumbaugh | 2025-02-24 | 8 | -17/+246 |
| | | |||||
| * | Added uniform data generator as file option | Douglas Rumbaugh | 2025-02-20 | 1 | -215/+240 |
| | | |||||
| * | Average version of mixed-workload bench | Douglas Rumbaugh | 2025-02-17 | 3 | -8/+192 |
| | | |||||
| * | Thread count sweep | Douglas Rumbaugh | 2025-02-17 | 1 | -7/+14 |
| | | |||||
| * | Fixed a few benchmark bugs | Douglas Rumbaugh | 2025-02-17 | 2 | -1/+10 |
| | | |||||
| * | Multi-threaded mixed workload benchmark | Douglas Rumbaugh | 2025-02-17 | 3 | -10/+157 |
| | | |||||
| * | Fixed legacy tiering policy | Douglas Rumbaugh | 2025-02-17 | 4 | -13/+19 |
| | | |||||
| * | BTree insertion latency benchmarks | Douglas Rumbaugh | 2025-02-17 | 2 | -0/+82 |
| | | |||||
| * | Retooled dist benchmark to actually print dist info | Douglas Rumbaugh | 2025-02-14 | 1 | -8/+7 |
| | | |||||
| * | Parallel background reconstructions appear to be working! | Douglas Rumbaugh | 2025-02-14 | 7 | -98/+49 |
| | | |||||
| * | progress towards resolving asynch structure merges | Douglas Rumbaugh | 2025-02-13 | 6 | -138/+131 |
| | | |||||
| * | more updates | Douglas Rumbaugh | 2025-02-11 | 3 | -16/+29 |
| | | |||||
| * | Progress: began adding parallel merging and locking of levels | Douglas Rumbaugh | 2025-02-11 | 16 | -87/+180 |
| | | |||||
| * | Migrated remaining tail latency benchmarks to new interface | Douglas Rumbaugh | 2025-02-10 | 3 | -19/+19 |
| | | |||||
| * | Tiering: adjusted layout policy to properly handle L0 | Douglas Rumbaugh | 2025-02-06 | 1 | -1/+1 |
| | | |||||
| * | CMakeLists update | Douglas Rumbaugh | 2025-02-06 | 1 | -0/+1 |
| | | |||||
| * | Background compaction stuff | Douglas Rumbaugh | 2025-02-06 | 15 | -98/+587 |
| | | |||||
| * | Bug fixes | Douglas Rumbaugh | 2025-02-04 | 3 | -3/+8 |
| | | |||||
| * | PSUDB update | Douglas Rumbaugh | 2025-02-03 | 1 | -0/+0 |
| | | |||||
| * | More updates | Douglas Rumbaugh | 2025-01-31 | 11 | -62/+124 |
| | | |||||
| * | progress | Douglas Rumbaugh | 2025-01-27 | 14 | -275/+273 |
| | | |||||
| * | some progress | Douglas Rumbaugh | 2025-01-24 | 3 | -74/+33 |
| | | |||||
| * | Finished rename of Epoch to Version + imported changes to psudb-common | Douglas Rumbaugh | 2025-01-22 | 5 | -7/+176 |
| | | |||||
| * | Progress | Douglas Rumbaugh | 2025-01-17 | 12 | -347/+256 |
| | | |||||
| * | Additional layout policies + more flexibility in buffer flushing | Douglas Rumbaugh | 2025-01-16 | 10 | -60/+364 |
| | | |||||
| * | Tail latency parm sweep | Douglas Rumbaugh | 2025-01-08 | 2 | -1/+121 |
| | | |||||
| * | Ajusted progress bar in insert benchmark | Douglas Rumbaugh | 2025-01-07 | 1 | -1/+0 |
| | | |||||
| * | Triespline: minor tweak to buffer query | Douglas Rumbaugh | 2025-01-07 | 1 | -1/+2 |
| | | | | | A change that should have been in the last commit | ||||
| * | Merge branch 'generalized-merging' of ↵ | Douglas Rumbaugh | 2025-01-07 | 11 | -9/+13 |
| |\ | | | | | | | github.com:dbrumbaugh/dynamic-extension-working into generalized-merging | ||||
| | * | Fixed the reversed scale factor and buffer size on benchmarks | Douglas B. Rumbaugh | 2024-12-23 | 11 | -9/+13 |
| | | | |||||
| * | | Fixed a few Triespline related bugs | Douglas Rumbaugh | 2025-01-07 | 2 | -31/+21 |
| |/ | |||||
| * | Began migrating benchmarks over to new interface | Douglas Rumbaugh | 2024-12-23 | 16 | -51/+82 |
| | | |||||
| * | More updates | Douglas B. Rumbaugh | 2024-12-22 | 3 | -6/+6 |
| | | | | | | | | BSM is currently broken--I'll need to think a bit about how best to actually implement this in the current framework (if I even want to port it over) because it doesn't use the same flushing mechanism as most other approaches. | ||||
| * | Continued development | Douglas B. Rumbaugh | 2024-12-22 | 33 | -377/+261 |
| | | |||||
| * | Began overhauling reconstruction mechanism | Douglas B. Rumbaugh | 2024-12-22 | 11 | -755/+469 |
| | | |||||
| * | Adjusted query result interfacesHEADmaster | Douglas B. Rumbaugh | 2024-12-06 | 20 | -468/+459 |
| | | | | | | | | Now, the vector<> is part of the user-defined type, not required by the framework. This should allow for more flexibility in either using alternative containers, or for more sensible implementations of queries with single value results (like range count). | ||||
| * | Warning fixes | Douglas B. Rumbaugh | 2024-12-06 | 10 | -23/+34 |
| | | |||||