An efficient consistency protocol for a DSD-based persistent object system
Bibliographic record
Abstract
Persistent object stores (POS) provide a good foundation for distributed applications. By executing nested object transactions, the application programmer can make updates to shared objects from different processing nodes across the network without having to manage the communications or con-currency control aspects of data access in the distributed environment. In such systems, the shared objects are "cached" in the nodes' local memories and these copies must be kept consistent in order to ensure correct execution of the transactions. Therefore, the memory consistency protocol has a great impact on the efficiency and usability of the POS. The LOTEC protocol was designed to maintain data consistency while reducing the associated consistency maintenance communication overhead for shared objects in a distributed shared virtual memory (DSVM) environment. While LOTEC achieves its goal, the use of fixed-size memory pages limits the performance improvement. Also, the locking protocol reduces the potential for concurrent execution of the nested object transactions. In this thesis, a new memory consistency protocol is presented in the context of a distributed shared data (DSD)-based POS. This protocol improves performance and reduces overhead by managing concurrent data access using versions of smaller groups of an object's attributes. When compared with LOTEC, the new protocol reduces a number of delay-causing situations that may arise during transaction execution. In addition, a new algorithm for creating smaller groups of attributes from an object called object chunking is presented and analyzed. Simulation results indicate that object chunking can significantly reduce the amount of data that must be moved in order to maintain memory consistency.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".