Skip to search formSkip to main contentSkip to account menu

Aether: A Scalable Approach to Logging

This paper identifies four logging-related impediments to database system scalability and addresses them with techniques that, when combined, comprise a holistic, scalable approach to logging.
View via Publisher (opens in a new tab)

Monkey: Optimal Navigable Key-Value Store

Monkey, an LSM-based key-value store that strikes the optimal balance between the costs of updates and lookups with any given main memory budget is presented, and how to use this model to answer what-if design questions about how changes in environmental parameters impact performance is shown.
View on ACM (opens in a new tab)

Evaluating and repairing write performance on flash devices

This paper proposes new a flash aware data layout --- append and pack --- which stabilizes device performance by eliminating random writes and assesses the impact of append andpack on OLTP workload performance using both an analytical model and micro-benchmarks.
View on ACM (opens in a new tab)

Beyond the Wall: Near-Data Processing for Databases

JAFAR, a Near-Data Processing (NDP) accelerator for pushing selects down to memory in modern column- Stores, is presented and it is shown that it has the potential to provide 9x improvement for selects in column-stores.
View on ACM (opens in a new tab)

Designing Access Methods: The RUM Conjecture

It is conjecture that when optimizing the read-update-memory overheads, optimizing in any two areas negatively impacts the third, and the RUM Conjecture is conjectured, which manifests in state of the art access methods, and is envisioned a trend toward RUMaware access methods for future data systems.
View via Publisher (opens in a new tab)

TPC-E vs. TPC-C: characterizing the new TPC-E benchmark via an I/O comparison study

This paper compares T PC-E with the familiar TPCC benchmark in order to understand the behavior of the new TPC-E benchmark, and finds that Tpc-E is more read intensive with a 9.7:1 I/O read to write ratio, while TPC -C sees a 1.9:1 read-to-write ratio.
View on ACM (opens in a new tab)

Sharing Data and Work Across Concurrent Analytical Queries

This work evaluates experimentally two sharing methodologies that exploit work sharing opportunities among concurrent queries at run-time: Simultaneous Pipelining (SP), which shares intermediate results of common sub-plans, and Global Query Plans (GQP), which build and evaluate a single query plan with shared operators.
View via Publisher (opens in a new tab)

Slalom: Coasting Through Raw Data via Adaptive Partitioning and Indexing

Slalom is presented, an in-situ query engine that accommodates workload shifts by monitoring user access patterns, and offers performance benefits by taking into account user query patterns to logically partition raw data files and build for each partition lightweight partition-specific indexes.
View via Publisher (opens in a new tab)

Scalability of write-ahead logging on multicore and multisocket hardware

This paper identifies four logging-related impediments to database system scalability, and presents a set of optimizations which partly ameliorate the latency penalty that comes with multi-socket hardware, and investigates the feasibility of applying a distributed log buffer design at the socket level.
View on Springer (opens in a new tab)

Lethe: A Tunable Delete-Aware LSM Engine

Lethe is built, a new key-value storage engine that uses a very small amount of additional metadata, a set of new delete-aware compaction policies, and a new physical data layout that weaves the sort and the delete key order to support fast persistent deletion.
View on ACM (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)