EC2 Instance Store

Cassandra 5.0 AWS Storage Requirements: GP3, I4g Instances, and Performance Optimization

What’s New in 2025

Key Updates and Changes

• EBS GP3 Volumes: 20% cost savings over GP2 with independent IOPS/throughput scaling
• I4g Instances: Graviton2-powered with 30TB NVMe, 15% better compute performance
• I4i vs I4g: 45-60% lower cost per TB with Im4gn/Is4gen families
• Unified Compaction: Cassandra 5.0 reduces storage overhead and improves I/O patterns
• EBS Optimization: Enhanced throughput up to 80 Gbps on latest instance types

Storage Performance Improvements

• GP3 Baseline: 3,000 IOPS and 125 MiB/s regardless of volume size
• GP3 Maximum: Up to 16,000 IOPS and 1,000 MiB/s (4x faster than GP2 max)
• NVMe Performance: I4g delivers up to 7.6 million IOPS per instance
• EBS Elastic Volumes: Live migration between volume types without downtime
• Storage Classes: New archive and deep archive tiers for long-term retention

Cassandra 5.0 AWS Storage Requirements

Cassandra 5.0 performs extensive sequential disk I/O for commit logs and SSTable writes, while requiring random I/O for read operations. The enhanced Unified Compaction strategy in Cassandra 5.0 provides more predictable I/O patterns and reduced storage overhead.

Continue reading

Cassandra AWS Storage Requirements

Cassandra AWS Storage Requirements

Cassandra does a lot sequential disk IO for the commit log and writing out SSTable. You still need random I/O for read operations. The more read operations that are cache misses, the more your EBS volumes need IOPS.

Cassandra writes to four areas

• commit logs
• SSTable
• an index file
• a bloom filter

Consider EC2 instance store instead of EBS for Cassandra

AWS provides EC2 instance local storage called instance storage which is not available with all EC2 instance types, and Elastic Block Store (EBS). Instance storage does not have to go over a SAN or Intranet, instead it uses the local hardware bus. Instance storage is right there on the server you are renting. The downside of EC2 instance storage is the expense, and it is not as flexible as EBS. Due to historic problems with EBS, it used to be the only real option for running Cassandra in AWS. EBS has a reputation for degrading performance over time. Some of this has likely been fixed with enhanced EBS, but instance storage is more reliable.

Continue reading