Highload fwdays'20
2020-10-13..2020-10-24
-- online --
who it's for
backend engineers, database administrators, site reliability engineers, devops engineers, software architects, platform engineers, engineering managers
topics
Elasticsearch index lifecycle management; frozen indices and rollups; WAL-G continuous backups and PITR; Aurora Serverless cost and scaling; ECS Fargate cold and warm starts; ClickHouse aggregation optimizations; MySQL performance tuning checklist; cross-country processing migration checklist; Rust and Tokio for network services; outbox pattern and event-carried state transfer; PXE/GLPI provisioning automation; high available Redis clustering
| title | author | length |
|---|---|---|
| Scale Your Elasticsearch Cluster | Philipp Krenn | 54m |
Shows exact steps: uses a three-node hot/warm/cold demo cluster (one node per tier), an ILM policy that rolls over on 5 minutes or 5 MB, moves shards… | ||
| Creating Backups for Various Transactional DBMSs Under Load | Andrey Borodin | 49m |
WAL-G backup tool development for cloud environments is described, including added support beyond PostgreSQL to MongoDB, MySQL, FoundationDB and others. The… | ||
| AWS RDS Aurora Serverless, ECS Fargate and Other Serverless Products | Evgeniy Lysenko | 01h 11m |
Covers AWS serverless offerings such as RDS Aurora Serverless and ECS Fargate, examining whether they truly solve common cloud problems. Discusses costs… | ||
| Optimizing Aggregate Functions in ClickHouse | Aleksey Milovidov | 45m |
The talk examines optimizing the AVG aggregation in ClickHouse for the query SELECT key, avg(value) FROM table GROUP BY key. It analyzes whether that simple… | ||
| 18 Ways to Fix MySQL Bottlenecks | Petr Zaytsev | 49m |
Practical checklist of 18 concrete fixes for sudden MySQL performance spikes, including scaling the instance, adding read replicas and routing reads, and using… | ||
| Problems with Relational Databases in 2020 | P. Zaytsev, A. Milovidov, A.Borodin, E. Lysenko | 01h 20m |
Three database experts from MySQL, ClickHouse and PostgreSQL discuss 2020 trends and practical problems with relational databases, covering criteria for… | ||
| How Not to Screw Up Moving Processing from 1 Country to 33 | Danil Topchiy | 46m |
Describes scaling a payment/processing system from serving one country to 33 by splitting monoliths into independent microservices for queue management and… | ||
| The RUST Language for High‑Load Network Services — Quick Start | Aleksandr Serbul | 56m |
A presentation traces the evolution of a high-load push-notification cluster from Unix/bash and PHP scripts to an asynchronous, non-blocking, multithreaded… | ||
| Event Driven Collaboration | Ian Cooper | 57m |
Argues that moving from request-driven to receiver-driven flow control succeeds when teams adopt concrete patterns: use the outbox pattern to avoid lost… | ||
| What It Takes to Build a Host | Anton Turetskiy | 59m |
The talk explains how physical servers are provisioned and brought into service, covering ordering, placement, and installation challenges and practical ways… | ||
| Why Event Sourced Systems Fail | Greg Young | 49m |
Common failures are concrete: 80–90% trace back to unfamiliarity and people, not the model. Hard technical problems are versioning across long-lived logs… | ||
| CTO Panel | Dmitriy Menshikov, Evgeniy Pilyankevich, Aleksey Solntsev, Kirill Latysh | 01h 16m |
A panel discussion featuring CTOs from Aurora Technologies, Cossack Labs, and YChamp (moderated by Kirill Latysh) about high-level engineering leadership… | ||
| Highly Available Redis Cluster Is Simple | Egor Gerasimchuk | 01h 25m |
Describes deploying a highly available Redis cluster using 3 Redis instances (1 master + 2 slaves) with Redis Sentinel for automatic failover, HAProxy as a… | ||
| Building an Efficient Replication System for Thousands of Terminals | Anton Moldovan | 01h 19m |
Describes a replication architecture that delivers updates via Redis Streams using small stored snapshots plus separate delta streams, with a push+pull hybrid… | ||
| UniSender Architecture: Growth from 100M to 1.5B Monthly Emails | Oleksandr Brichuk | 44m |
UniSender's architecture evolution from 2013 to 2020, focusing on how the team refactored a legacy monolith into microservices starting in 2015 to handle a… | ||
| NoSQL versus SQL Panel | Andrey Nikishaev, Aleksey Kovalev, Denys Reznyk | 01h 55m |
A debate between engineers from Moneyveo and Teamwork Commerce moderated by Intapp's Denis Reznik comparing NoSQL and SQL databases. They discuss definitions… | ||
| nothing matches | ||