PgConf.Russia 2020

Совсем недавно мы выпустили версию 1.0 нашего пулера соединений Odyssey. Он призван решить проблемы управления соединениям высоконагруженных инсталляций PostgreSQL. В этом докладе я хотел бы рассказать об архитектуре и эксплуатации Одиссея. Также будут затронуты проблемы, которые были решены в достаточно длинном переходе между 1.0rc и 1.0.

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.

Walk-through of extending PostgreSQL with a user-defined type. The journey begins from the basics, from creating simple domain types over existing types, and continues to implementing a full-blown datatype from scratch in C.

PostgreSQL's advanced index types, GiST, GIN, and SP-GiST, are covered in enough detail to give an understanding of what each of them is good for. Support functions for each of them are shown for the example 'color' datatype.

An enterprise-grade PostgreSQL requires many complementary technologies to the database core: high availability and automated failover, monitoring and alerting, centralized logging, connection pooling, etc. That is, a stack of components around PostgreSQL. Kubernetes has enabled a new model to deploy software abstracting away the infrastructure. However, containers are not lightweight VMs, and the packing of software paradigms that work on VMs are not valid on containers/Kubernetes. How should be PostgreSQL and its stack be deployed on Kubernetes? Enter StackGres. An open source software that is the result of re-engineering PostgreSQL to become cloud native. Join this talk to learn and see demos of how to generate PostgreSQL minimal containers; how the sidecar pattern is used (abused) to integrate PostgreSQL’s stack components, and how the networking and storage are handled. More info: stackgres.io.