PgConf.Russia 2020

Cloud storage has some unique characteristics compared to traditional storage mainly because it is virtualized and controlled by software. One example is that AWS EBS shows higher throughput with larger I/O size up to 256 KiB without hurting latency. Hence, a user can get only about 4 MiB/sec with 1,000 IOPS EBS volume if the I/O request size is 4 KiB, whereas a user can get about 250 MiB/sec if the I/O request size is 256 KiB. This is because EBS consumes one I/O in a given IOPS budget for every I/O request regardless of the I/O size (up to 256 KiB). Unfortunately, PostgreSQL cannot exploit the full potential of cloud storage because PostgreSQL has designed without considering the unique characteristics of cloud storage.

In this talk, I will introduce the AppOS extension that improves the throughput of a write-intensive workload by 10x by transparently making PostgreSQL cloud storage-native. AppOS works like a storage driver that efficiently exploits the characteristics of cloud storage, such as I/O size dependency to storage throughput and latency, atomic write support in cloud block storage, and fast, but non-durable local SSDs. To do this, AppOS comprises a Linux-compatible file I/O stack including virtual file system, page cache, block I/O layer, cloud storage driver. On top of the file I/O stack, syscall module supports registering pre- and post-handler for file I/O-related system calls in order to transparently work without modifying PostgreSQL codes.

I will focus on presenting key use cases and performance results of the AppOS extension after explaining the internals. Specifically, I will show the performance results of OLTP and some batch workloads using standard benchmarking tools like pgbench and sysbench. I will also present performance results and implications on multiple clouds including AWS, GCP, and Azure.

Небольшая история о том, как переход на PostgreSQL увеличил на порядок эффективность работы компании:

1. Программный код сократился в 50 раз, в команде разработки бэкенда вместо 15 человек осталось трое
2. Сроки разработки нового функционала стали измеряться днями, а не месяцами
3. Стоимость владения в расчете на 1 млн. пользователей снизилась в 20 раз
4. Структура данных и документация существенно упростилась: вместо 100 тыс. таблиц со сложными связями стало 20 простых таблиц
5. Повышение безопасности системы за счет запрета внешних SQL команд к базе данных
6. Быстрый сбор аналитики по ключевым параметрам
7. Без остановки работы бизнеса

200 баз, несколько кластеров, несколько терабайт данных Поделимся своим опытом настройки и использования patroni cluster Кластер СУБД под Linux, сервер 1С под windows. Используем: Сборка PostgreSQL для 1С, Patroni, Consul, Consul dns, Commvault, Ansible Vagrant файл и Ansible playbook c ролями прилагается.

The story about powering a 1.5 petabyte analytics application with 2816 cores and 18.7 TB of memory in the Citus cluster at the Microsoft. The Windows team measures the quality of new software builds by scrutinizing 20,000 diagnostic metrics based on data flowing in from 800 million Windows devices. At the same time, the team evaluates feedback from Microsoft engineers who are using pre-release versions of Windows updates. At Microsoft, the Windows diagnostic metrics are displayed on a real-time analytics dashboard called “Release Quality View” (RQV), which helps the internal “ship-room” team assess the quality of the customer experience before each new Windows update is released. Given the importance of Windows for Microsoft’s customers, the RQV analytics dashboard is a critical tool for Windows engineers, program managers, and execs.