PgConf.Russia 2020

I will speak about our experience in solving the fault-tolerance problem for PostgreSQL, which options we reviewed and how we chose Patroni.

I will cover solution testing, quick implementation to the production and issues we faced as well as the way we solved them.

200 bases, several clusters, several terabytes of data Share our experience setting up and using patroni cluster DBMS Cluster on Linux, 1C server for windows. We use: PostgreSQL assembly for 1C, Patroni, Consul, Consul dns, Commvault, Ansible Vagrant file and Ansible playbook with roles attached.

Greenplum is a horizontal scalable database based on PostgreSQL core. It is used for OLAP workloads and a standard task is to quickly load or unload large amounts of data. The external data resources are usually another distributed systems. In this talk I will show how Greenplum can work with external data. What is the architecture and performance of external and foreign tables and how to handle streaming data. What will be changed in the next version. The examples of Kafka and ClickHouse connectors development.

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.