惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
B
Blog RSS Feed
量子位
aimingoo的专栏
aimingoo的专栏
V
Visual Studio Blog
Y
Y Combinator Blog
Vercel News
Vercel News
云风的 BLOG
云风的 BLOG
宝玉的分享
宝玉的分享
Engineering at Meta
Engineering at Meta
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
GbyAI
GbyAI
人人都是产品经理
人人都是产品经理
博客园 - 叶小钗
Stack Overflow Blog
Stack Overflow Blog
大猫的无限游戏
大猫的无限游戏
Microsoft Security Blog
Microsoft Security Blog
B
Blog
Last Week in AI
Last Week in AI
有赞技术团队
有赞技术团队
博客园 - 聂微东
腾讯CDC
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
J
Java Code Geeks

Supabase Blog

AI Agents Know About Supabase. They Don't Always Use It Right. Custom OIDC Providers for Supabase Auth 100,000 GitHub stars Supabase docs over SSH Navigating Regional Network Blocks Supabase Joins the Stripe Projects Developer Preview Log Drains: Now available on Pro Supabase Storage: major performance, security, and reliability updates Supabase incident on February 12, 2026 Hydra joins Supabase X / Twitter OAuth 2.0 is now available for Supabase Auth BKND joins Supabase Supabase is now an official Claude connector Supabase PrivateLink is now available Introducing: Postgres Best Practices When to use Read Replicas vs. bigger compute Introducing TRAE SOLO integration with Supabase Supabase Security Retro: 2025 Sync Stripe Data to Your Supabase Database in One Click Building ChatGPT Apps with Supabase Edge Functions and mcp-use Own Your Observability: Supabase Metrics API Introducing iceberg-js: A JavaScript Client for Apache Iceberg Introducing Supabase for Platforms Adding Async Streaming to Postgres Foreign Data Wrappers Build "Sign in with Your App" using Supabase Auth Introducing Seven New Email Templates for Supabase Auth The new Supabase power for Kiro Introducing Supabase ETL Introducing Analytics Buckets Introducing Vector Buckets
High Performance Disk
Paul Cioanca, Jonny Summers-Muir, Greg Papas · 2024-12-05 · via Supabase Blog

High Performance Disk

High Performance disks store up to 60 TB of data with 100x improved durability, and provision up to 5x more IOPS than the default disks we offer.

We've been tackling disk scalability from two angles. On the software side, our implementation of Oriole DB's index-organized tables significantly reduces disk I/O operations, improving performance without additional hardware resources.

On the infrastructure side we've added new disk options that allow for advanced scaling of your Postgres databases.

One of the most significant improvements is our increased storage capacity. We've moved beyond our previous 16 TB limit, now offering up to 60 TB of storage for your largest databases. But with greater capacity comes the need for enhanced performance - particularly in how quickly your database can read and write data. This makes IOPS (Input/Output Operations Per Second) especially important.

To address these needs, our new High Performance disks can handle up to 80,000 IOPS - a 5x increase from the 16,000 IOPS limit of our General Purpose disks.

IOPS is a critical metric that measures how many read and write operations your database can perform each second. Think of it as the "speed limit" for your database's ability to access stored data. Higher IOPS means faster database operations, which translates to better application performance, especially for data-intensive workloads.

Throughput, measured in MiB/s (Mebibytes per second), is equally important as it determines how much total data can flow through your disk at once. While IOPS tells you how many individual read/write operations can happen per second, throughput determines the total volume of data that can be moved. With our General Purpose disks, you start with a baseline throughput of 125 MiB/s, which can be provisioned up to 1,000 MiB/s. Our High Performance disks automatically scale throughput with IOPS, providing better performance for data-intensive workloads.

Effective throughput and IOPS also depends on your compute instance size. You can read more about these interdependencies in our compute and disk documentation.

Another benefit of our High Performance disks is increased durability. Our new disks offer 99.999% durability, a 100x increase over our standard disk. This means that if you use High Performance Disk, you will almost never need to worry about disk failure — say goodbye to recovery from backups.

With these advanced options comes complexity—both in the number of options available, and how they interplay with compute settings. To address this we've redesigned our disk management interface to coexist and interoperate with our compute upgrade UI. When designing the new UI, we adhered to the following principles:

Transparent Billing#

  • Real-time cost updates as you adjust your disk configuration
  • Clear breakdown of how each change affects your bill

Updated Disk Size Insights#

The Disk Size Usage graph breaks down the space used by the Database, Write-Ahead Log, and the System, rather than simply showing "used space."

Preventing Footguns#

Effective IOPS is limited by both your compute add-on and disk configuration and it is technically possible to over provision the disk throughput and IOPS with the instance not being able to make full use of it. For example, to achieve maximum IOPS (80,000), you'll need a 16XL or larger compute instance. The dashboard warns you when it detects scenarios like these.

The pricing for High Performance Disk starts at $0.195 per GB, and you can provision IOPS at $0.119 per IOPS. The storage pricing for General Purpose disks remains unchanged, and you can provision IOPS at $0.024 per IOPS and 0.095$ per Mbps throughput.

For more details on pricing breakdown vs. General Purpose Disk, check out our pricing page.

Ready to try out our new disk options? Visit Compute and Disk in the Supabase Dashboard.

We're excited to see what you'll build with these new capabilities. As always, we're committed to providing the tools you need to scale your applications effectively while maintaining the simplicity and developer experience you've come to expect from Supabase.