# Scalable Service

> Elastic Performance
---

> Ever-flowing like water, soft yet resilient, converging streams to adapt to endless change!


**Great Performance**


        Hardware Fully Harnessed



**R/W Separation**


        Unlimited Read Scaling



**Connection Pooling**


        High Concurrency



**Load Balancing**


        Traffic Control



**Horizontal Scaling**


        Distributive Extension



**Storage Expansion**


        Transparent Compression



**Mass Deployment**


        Large clusters made easy



**Elasticity**


        Cloud-like Elasticity





--------

## Great Performance: Hardware Fully Harnessed {#great-performance}

> Highlights amazing scalability and top-tier hardware performance.\
> Maximizing the potential of modern hardware with optimized configurations.

- Single-node query rate reaches 2 million rows/second
- Single-node write rate can reach 1 million rows/second
- Default table size limit: 32TB (2^32 x 8KiB Page)

--------

## R/W Separation: Unlimited Read Scaling {#rw-separation}

> Offers unlimited replicas through cascading replication with auto traffic routing.\
> Scale read workloads horizontally without impacting write performance.

- Read-only Service: Route to read-only replicas with primary as backup
- Offline Service: Route to special analytics instance with replicas as backup
- Production Case: One primary with 34+ replicas through cascading bridges

--------

## Connection Pooling: High Concurrency {#connection-pooling}

> Built-in PGBouncer connection pool, ready out of the box and syncing with postgres.\
> Handle thousands of concurrent connections efficiently with resource optimization.

- Xact pooling converts 20000+ client connections to several active server connections
- Enabled by default, automatically syncing db/user with postgres
- Deploy multiple pgbouncer instances to circumvent bottlenecks

--------

## Load Balancing: Traffic Control {#load-balancing}

> Monitor and schedule request traffic in real-time with HAProxy console.\
> Intelligent traffic distribution with health checks and failover capabilities.

- Stateless HAProxy can be scaled at will or deployed on dedicated servers
- Weights can be adjusted via CLI, draining or warming up instances gracefully
- Password-protected HAProxy GUI exposed uniformly through Nginx

--------

## Horizontal Scaling: Distributive Extension {#horizontal-scaling}

> Citus extension with multi-write and multi-tenant capabilities.\
> Scale beyond single-node limitations with distributed PostgreSQL.

- Accelerate real-time OLAP analytics using multi-node parallel processing
- Shard by row key or schema, supporting multi-tenant scenarios
- Online partition rebalancing, adjusting throughput capacity

--------

## Storage Expansion: Transparent Compression {#storage-expansion}

> Achieve 10:1 or even higher compression ratios with columnar and other exts\
> R/W data in S3 with FDW, hot/cold separation and unlimited capacity expansion

- Use timescaledb, pg_mooncake, pg_duckdb for columnar compression
- Use duckdb_fdw, pg_parquet, pg_analytics to read/write object storage tables
- Expand or contract storage with S/H RAID, ZFS, and PG tablespaces

--------

## Mass Deployment: Large clusters made easy {#mass-deployment}

> Designed for extreme scale - flexible for 25K vCPU clusters or 1c1m node\
> No limit on nodes per deployment - soft constrained only by monitoring capacity

- Batch Ops at scale through Ansible, saying goodbye to console ClickOps
- Largest production deployment record: 25,000 vCPU, 3,000+ instances

--------

## Elasticity: Cloud-like Elasticity {#elasticity}

> Supports cloud EC2 deployment, fully leveraging the elastic advantages of cloud\
> Flexible multi-cloud strategies - enjoy RDS elasticity with EC2/EBS prices

- Pigsty only needs cloud servers, works the same across any cloud provider
- Seamless switching between public, private, hybrid, and multi-cloud
- Scale compute and storage as needed