With definitions established, this post examines where HANA, Exadata X3 and flash memory each sit in the in-memory landscape – and what they actually have in common.
Category: Storage
Storage is the foundation on which database performance is built. Latency, throughput, and consistency at this layer directly shape how systems behave under load.
While often abstracted away in modern architectures, storage characteristics continue to define the limits of what databases can achieve – especially as workloads become more demanding and less predictable.
Thoughts on In Memory Databases (Part 1)
Everyone is talking about in-memory databases, but what does "memory" actually mean in this context? Here's an attempt to cut through the hype and establish some clear definitions.
Exadata X3 – Sound The Trumpets
It's crazy time in the world of Oracle, because Oracle OpenWorld 2012 is only a week away. Which means that between now and then the world of Oracle blogging and tweeting will gradually reach fever pitch speculating on the various announcements that will be issued, products that will be launched and outrageous claims that will … Continue reading Exadata X3 – Sound The Trumpets
Database Consolidation Part 4 – Flash Memory Makes The Difference
Flash memory changes the consolidation equation – here's how it addresses the I/O bottleneck that historically made high-density database consolidation impractical.
Database Consolidation Part 3 – It’s All About Capacity
Consolidating databases onto shared infrastructure only works if you understand the capacity model – including the art and risk of overcommitting resources.
Database Consolidation Part 2 – Shared Infrastructure Design Choices
Once you've decided to consolidate, the next question is where shared infrastructure should diverge. This post examines the key architectural design choices and their trade-offs.
Database Consolidation Part 1 – Business Drivers and Technical Challenges
Database consolidation means more than moving databases onto bigger iron – it means turning them into managed services. Here are the business drivers and technical obstacles that define the journey.
SLOB on Violin 3000 Series with PCIe Direct Attach
A reader Alex asked if I could post a comparative set of tests from my previous 3000 series Infiniband testing but using the PCIe direct-attached method. I was actually very keen to test this myself as I wanted to see how close the Infiniband connectivity method could get to the PCIe latencies. Why? Well, PCIe … Continue reading SLOB on Violin 3000 Series with PCIe Direct Attach
SLOB on Violin 3000 Series with Infiniband
SLOB benchmark results from Martin Bach's hands-on testing of a Violin 3000 series flash array connected via Infiniband – comparing latency and throughput against PCIe-based flash.
SLOB testing on Violin and Exadata
A head-to-head SLOB benchmark comparing Violin flash memory arrays against Oracle Exadata – testing raw Oracle physical I/O throughput on two very different architectures.
flashdba 