The Blog Year in Review: Top 10 for 2024

2024 was a HUGE year for MinIO. Not only did we release AIStor, the most powerful version of MinIO to date, but we also attended 54 events, wrote 159 blogs, won over 10 awards and so much more. And all of it wouldn’t be possible without the support of our amazing MinIO community. 

So, as a shoutout to you all, we are looking back on your top 10 most-read articles of 2024. Let’s start with #10 and work our way up to first place. 

#10 - Working with Small Objects in AI/ML workloads

In 10th place, AJ takes a look at some of the difficulties inherent in storing and retrieving large numbers of small objects and digs into how MinIO optimizes these operations and our new features for working with .tar and .zip files on MinIO client and server.

#9 - Add Pools and expand capacity

Server pools help you expand the capacity of your existing MinIO cluster quickly and easily. This post looks at what to consider before expanding a server pool, how to create your initial pool and then later how to expand it by adding a new pool.

#8 - MinIO’s S3 over RDMA Initiative: Setting New Standards in Object Storage for High-Speed AI Data Infrastructure

A critical new feature of AIStor is our added support for S3 over RDMA. With the proliferation of 400GbE and even 800GbE NICs, conventional protocols such as TCP/IP struggle to maintain efficiency, creating bottlenecks due to high CPU overhead and latency. By leveraging RDMA’s low-latency, high-throughput capabilities, MinIO enables customers to take full advantage of their hyperfast Ethernet investments.

#7 - The Most Powerful Version of MinIO Ever - Introducing AIStor

Great to see another AIStor post make our list. AIStor represents our singular focus on building the world’s best object store for AI/ML workloads. It also reflects real-world learning from EiB+ deployments. At this scale, problems emerge that most storage vendors will never see, because they can’t operate at that scale, so we created the industry’s most feature-complete object store. 

#6 - Prefix vs Folder

In order to achieve the level of performance, scalability and feature richness that MinIO is known for, objects are stored in a unique way. In this article, AJ takes you through what’s a prefix, a folder and several other important basics to understand the underlying architecture of how we run. 

#5 - Managing AI workloads with Tagging and Policies

Tags are a valuable tool to categorize and work with buckets and objects. Filtering by tags is much more flexible, descriptive and specific than filtering by bucket or path. Creating tags and using them to filter with no additional latency demonstrates the value of MinIO's integrated metadata architecture. MinIO saves metadata with data, removing the need to query an additional database in order to work with tags. 

#4 - Integrate MinIO with Keycloak OIDC

Keycloak is a Single Sign-On (SSO) solution that simplifies user authentication. Instead of authenticating directly with MinIO, users log in through Keycloak. Without it, you would need to create and manage separate identities for each user, which can become tedious and difficult to maintain over time. This article shows how to set up MinIO to work with Keycloak and explains how OIDC is configured with MinIO—so you can use it outside of Keycloak.

#3 - The Challenge in Big Data is Small Files

Small files strike again. They can cause big problems for storage platforms and the applications they power. Many of today’s workloads—especially streaming and log analytics—place great demands on applications and storage systems by forcing them to work with massive numbers of small files. We take a deeper look at the small files problem, digging into its origins and concluding with solutions.

#2 - Deploy MinIO and Trino with Kubernetes

This tutorial deploys a cohesive system that allows distributed SQL querying across large datasets stored in MinIO, with Trino leveraging metadata from Hive Metastore and table schemas from Redis.

#1 - Benchmarking AIStor with WARP and Perf test

And finally… your number one! WARP is an open source full-featured S3 performance assessment software built to conduct tests between WARP clients and #objectstorage hosts. Perf Test is an easy-to-use automated performance test that provides a streamlined experience and concise results. This article takes you through how to run both of these with different parameters to get the best out of benchmarking your cluster.

Thank you to our wonderful MinIO community for making 2024 an incredibly memorable and successful year. 2025 has even more in store for you all, and we can’t wait for you to be along for the ride.