Alekh Jindal

Alekh Jindal

Auto-generated profile, based on publicly available information

Alekh Jindal

SmartApps, Bellevue, WA, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 March 2024 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
HHHanxian Huang
Hanxian Huang
TSTarique Siddiqui
Tarique Siddiqui
RARana Alotaibi
Rana Alotaibi
CCCarlo Curino
Carlo Curino
JLJyoti Leeka
Jyoti Leeka
YTYuanyuan Tian
Yuanyuan Tian
Database systems often rely on historical query traces to perform workload-based performance tuning. However, real production workloads are time-evolving, making historical queries ineffective for optimizing future workloads. To address this challenge, we propose SIBYL, an end-to-end machine learning-based framework that accurately forecasts a sequence of future queries, with the entire query statements, in various prediction windows. Drawing insights from real-workloads, we propose template-based featurization techniques and develop a stacked-LSTM with an encoder-decoder architecture for accurate forecasting of query workloads. We also develop techniques to improve forecasting accuracy over large prediction windows and achieve high scalability over large workloads with high variability in arrival rates of queries. Finally, we propose techniques to handle workload drifts. Our evaluation on four real workloads demonstrates that SIBYL can forecast workloads with an 87.3% median F1 score, and can result in 1.7× and 1.3× performance improvement when applied to materialized view selection and index selection applications, respectively.

4 June 2023
Verified
Conference Paper
Open access
BMBarzan Mozafari
Barzan Mozafari
RBRadu Alexandru Burcuta
Radu Alexandru Burcuta
ACAlan Cabrera
Alan Cabrera
ACAndrei Constantin
Andrei Constantin
DFDerek Francis
Derek Francis
CZChi Zhang
Chi Zhang
Data clouds in general, and cloud data warehouses (CDWs) in particular, have lowered the upfront expertise and infrastructure barriers, making it easy for a wider range of users to query large and diverse sources of data. This has made modern data pipelines more complex, harder to optimize, and therefore less resource efficient. As a result, the ongoing cost of data clouds can easily become prohibitively expensive. Further, since CDWs are general-purpose solutions that must serve a wide range of workloads, their out-of-box performance is sub-optimal for any single workload. Data teams therefore spend significant effort manually optimizing their queries and cloud infrastructure to curb costs while achieving reasonable performance. Aside from the opportunity cost of diverting data teams from business goals, manual optimization of millions of constantly changing queries is simply daunting. To the best of our knowledge, Keebo's Warehouse Optimization is the first fully-automated solution capable of making real-time optimization decisions that minimize the CDWs' overall cost while meeting the users' performance goals. Keebo learns from how users and applications interact with their CDW and uses its trained models to automatically optimize the warehouse settings, adjusts its resources (e.g., compute, memory), scale it up or down, suspend or resume it, and also self-correct in real-time based on the impact of its own actions.

8 December 2023 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
BHBrandon Haynes
Brandon Haynes
RARana Alotaibi
Rana Alotaibi
APAnna Pavlenko
Anna Pavlenko
JLJyoti Leeka
Jyoti Leeka
AJAlekh Jindal
Alekh Jindal
YTYuanyuan Tian
Yuanyuan Tian
Large scale analytics engines have become a core dependency for modern data-driven enterprises to derive business insights and drive actions. These engines support a large number of analytic jobs processing huge volumes of data on a daily basis, and workloads are often inundated with overlapping computations across multiple jobs. Reusing common computation is crucial for efficient cluster resource utilization and reducing job execution time. Detecting common computation is the first and key step for reducing this computational redundancy. However, detecting equivalence on large-scale analytics engines requires efficient and scalable solutions that are fully automated. In addition, to maximize computation reuse, equivalence needs to be detected at the semantic level instead of just the syntactic level (i.e., the ability to detect semantic equivalence of seemingly different-looking queries). Unfortunately, existing solutions fall short of satisfying these requirements. In this paper, we take a major step towards filling this gap by proposing GEqO, a portable and lightweight machine-learning-based framework for efficiently identifying semantically equivalent computations at scale. GEqO introduces two machine-learning-based filters that quickly prune out nonequivalent subexpressions and employs a semi-supervised learning feedback loop to iteratively improve its model with an intelligent sampling mechanism. Further, with its novel database-agnostic featurization method, GEqO can transfer the learning from one workload and database to another. Our extensive empirical evaluation shows that, on TPC-DS-like queries, GEqO yields significant performance gains-up to 200x faster than automated verifiers-and finds up to 2x more equivalences than optimizer and signature-based equivalence detection approaches.

20 November 2019
Verified
Conference Paper
Open access
HPHiren Patel
Hiren Patel
AJAlekh Jindal
Alekh Jindal
CSClemens Szyperski
Clemens Szyperski

1 August 2023 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
SQShi Qiao
Shi Qiao
AJAlekh Jindal
Alekh Jindal
There is a renewed interest in data marketplaces with cloud data warehouses that make sharing and accessing data on-demand and extremely easy. However, analyzing marketplace datasets is challenge since current tools for creating the data models are manual and slow. In this paper, we propose to demonstrate a learning-based approach to discover, deploy, and optimize data models. We present the resulting system, PikePlace, show an evaluation over Snowflake marketplace and TPC-H datasets, and describe several demonstration scenarios that the audience can play with.