REVIEW 7 cited by
LlamaTune: Sample-Efficient DBMS Configuration Tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Tuning a database system to achieve optimal performance on a given workload is a long-standing problem in the database community. A number of recent works have leveraged ML-based approaches to guide the sampling of large parameter spaces (hundreds of tuning knobs) in search for high performance configurations. Looking at Microsoft production services operating millions of databases, sample efficiency emerged as a crucial requirement to use tuners on diverse workloads. This motivates our investigation in LlamaTune, a tuner design that leverages domain knowledge to improve the sample efficiency of existing optimizers. LlamaTune employs an automated dimensionality reduction technique based on randomized projections, a biased-sampling approach to handle special values for certain knobs, and knob values bucketization, to reduce the size of the search space. LlamaTune compares favorably with the state-of-the-art optimizers across a diverse set of workloads. It identifies the best performing configurations with up to $11\times$ fewer workload runs, and reaching up to $21\%$ higher throughput. We also show that benefits from LlamaTune generalize across both BO-based and RL-based optimizers, as well as different DBMS versions. While the journey to perform database tuning at cloud-scale remains long, LlamaTune goes a long way in making automatic DBMS tuning practical at scale.
Forward citations
Cited by 7 Pith papers
-
Xkernel: Principled Performance Tunability of Operating System Kernels
A Linux mechanism, Scoped Indirect Execution, safely retunes hard-coded kernel performance constants in milliseconds on a deployed kernel, without rebuilding or rebooting.
-
TuxBot: Semantic-Aware Online OS Tuning with Large Language Models
SemaTune uses LLM guidance with semantic context to tune up to 41 Linux OS parameters, delivering 72.5% performance gains over defaults and 153.3% over non-LLM baselines on 13 workloads while avoiding degraded states.
-
AgenticDB: Self-Evolving Reconfiguration Framework for Database Workloads
AgenticDB introduces an agentic AI system that interactively reconfigures MySQL and PostgreSQL workloads using DBMS and OS changes guided by runtime feedback, outperforming baselines by 118.1% on average.
-
Accuracy Can Lie: On the Impact of Surrogate Model in Configuration Tuning
Across 29 systems, 10 models and 17 tuners, higher surrogate-model accuracy frequently fails to improve, and sometimes degrades, configuration tuning quality.
-
MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration
MCTuner reports up to 19.2% performance gains and roughly 1.4x faster discovery of good configurations by combining LLM knob selection with recursive space decomposition and Bayesian optimization.
-
From Good to Great: Improving Memory Tiering Performance Through Parameter Tuning
Bayesian Optimization of memory tiering knobs yields up to 2x performance gains over default configurations, although the best settings rarely transfer across inputs or hardware.
-
Fine-tuning LLaMA 2 interference: a comparative study of language implementations for optimal efficiency
The preprint claims Mojo SDK matches C and C++ for Llama 2 inference on Apple Silicon with Python-like ease of use, but the text contains no visible benchmark numbers to verify that claim.
Discussion (0). Continue with ORCID to comment.