English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Efficient transactional management is a delicate task. As systems facetransactions of inherently different types, ranging from point updates to longrunning analytical computations, it is hard to satisfy their individualrequirements with a single processing component. Unfortunately, most systemsnowadays rely on such a single component that implements its parallelism usingmulti-version concurrency control (MVCC). While MVCC parallelizes short-runningOLTP transactions very well, it struggles in the presence of mixed workloadscontaining long-running scan-centric OLAP queries, as scans have to work theirway through large amounts of versioned data. To overcome this problem, wepropose a system, which reintroduces the concept of heterogeneous transactionprocessing: OLAP transactions are outsourced to run on separate (virtual)snapshots while OLTP transactions run on the most recent representation of thedatabase. Inside both components, MVCC ensures a high degree of concurrency.The biggest challenge of such a heterogeneous approach is to generate thesnapshots at a high frequency. Previous approaches heavily suffered from thetremendous cost of snapshot creation. In our system, we overcome therestrictions of the OS by introducing a custom system call vm_snapshot, that ishand-tailored to our precise needs: it allows fine-granular snapshot creationat very high frequencies, rendering the snapshot creation phase orders ofmagnitudes faster than state-of-the-art approaches. Our experimental evaluationon a heterogeneous workload based on TPC-H transactions and handcrafted OLTPtransactions shows that our system enables significantly higher analyticaltransaction throughputs on mixed workloads than homogeneous approaches. In thissense, we introduce a system that accelerates Analytical processing byintroducing custom Kernel functionalities: AnKerDB.

Accelerating Analytical Processing in MVCC using Fine-Granular High-Frequency Virtual Snapshotting