Skip to contentRU

Talk

Database Internals

Date: 04.09 / Start: 00:00 – Finish: 00:00

Optimisation of Partition Allocation in a Sequence of Distributed Data Processing Tasks

In Russian

Presentation pdf

We will consider the shuffle data minimisation method taking into account data skew.

Speakers

Milena Bulkina
T-Bank

Invited experts

Sergey Teryoshkin
Research Center "Strong AI in Industry" (ITMO University)

Other talks on «Database Internals»
- Watch recording
  One More Way to Make Backup in Ignite
  Nikolai Izhikov
  Apache Software Foundation
  Room 2In Russian
- Watch recording
  Schema Registry: Ultimate Guide
  Timofei Brunko
  Yandex Cloud
  Room 2In Russian
- Watch recording
  Apache Arrow: Faster, Lower, Harder
  Evgenii Glotov
  Autotech
  Room 1In Russian
- Watch recording
  Writing Your Own Cluster Manager for Apache Spark
  Aleksandr Tokarev
  Yandex
  Room 1In Russian
- Watch recording
  How We're Making Cloud-based Greenplum
  Leonid Borchuk
  Yandex Cloud
  Room 3In Russian
- Watch recording
  Sharded and Distributed Are Not the Same: What You Must Know When PostgreSQL Is Not Enough
  Evgenii Ivanov
  Yandex
  Oleg Bondar
  Yandex
  In Russian
- Watch recording
  Let's Ditch Java to Massively Accelerate Spark/Presto... Or Not Yet?
  Pavel Solodovnikov
  CedrusData
  Room 3In Russian
- Watch recording
  Data Sketches — Fast, Cheap and (Almost) Accurate!
  Sergey Zhemzhitsky
  Arenadata
  Room 3In Russian
- Watch recording
  How We Swapped Apache Kafka for Redpanda
  Roman Ananev
  Avito
  Room 2In Russian
- Watch recording
  Storage for the Lake
  Aleksandr Kazanskii
  T-Bank
  Room 3In Russian