MétaCan
Menu
Back to cohort
Record W2398890672

Towards Adaptive Resource Allocation for Database Workloads.

2015· article· en· W2398890672 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueVery Large Data Bases · 2015
Typearticle
Languageen
FieldComputer Science
TopicCloud Computing and Resource Management
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceWorkloadScalabilityResource allocationDistributed computingPerformance tuningPerformance metricReal-time computingDatabaseOperating system
DOInot available

Abstract

fetched live from OpenAlex

Modern computer systems provide hardware resources that allow database systems to execute a large number of tasks in parallel. However, no software system is perfectly scalable, and allocating more resources does not necessarily result in better performance. For commensurate resource allocation and increased efficiency, it is desirable to dynamically allocate hardware resources according to workload demands and conduct hardware consolidation. Given the complexity of database systems and their workloads, it is challenging to design such an adaptive algorithm. This paper addresses this problem using a simple feedback mechanism. The contributions of this work are twofold. First, an application-agnostic performance metric based on hardware performance counters is proposed to measure system performance online. This fine-grained metric enables agile feedback even for long running analytical workloads. Second, an allocation algorithm is presented that is designed based on fuzzy control techniques. The controller does not need a system model or prior training. Evaluation results show that a good correlation exists between the system-level metric and application-specific performance metrics. Further, a database system with our controller can achieve performance comparable to that obtained with manual tuning.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.674
Threshold uncertainty score0.605

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.003
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.094
GPT teacher head0.296
Teacher spread0.202 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it