Open-sourcing a 10x reduction in Apache Cassandra tail latency

Re:Open-sourcing a 10x reduction in Apache Cassandra tail la... by yazr on Monday March 05, 2018 @05:02PM (#16524879)

Or just try and benchmark Azul VM with pause-less GCs ?!

(I have used Azul in low-latency production environments. It has pros and cons but it certainly beats re-writing the storage layer... )

[ Parent | on HN ]

Re:Open-sourcing a 10x reduction in Apache Cassandra tail la... by truth_seeker on Tuesday March 06, 2018 @12:51AM (#16527128)

Curious to know the cons of using it, except being commercial.

[ Parent | on HN ]

Re:Open-sourcing a 10x reduction in Apache Cassandra tail la... by manigandham on Tuesday March 06, 2018 @06:07AM (#16528117)

> except being commercial

That's the biggest, especially for when it's a Facebook company. Otherwise it works well but can be pricey.

The JVM is getting a new fully concurrent collector though called Shenandoah: https://www.google.com/search?q=shenandoah+gc

[ Parent | on HN ]

Re:Open-sourcing a 10x reduction in Apache Cassandra tail la... by domsj on Tuesday March 06, 2018 @02:12PM (#16531185)

Not just shenandoah[1], it's also getting zgc[2], so the low latency future looks bright for the jvm.

[ Parent | on HN ]

Re:Open-sourcing a 10x reduction in Apache Cassandra tail la... by yazr on Thursday March 08, 2018 @04:33AM (#16543344)

Needs a stronger machine to be effective (more cores & more memory)

Minor configuration issues (we had a very complex environment, custom kernel, weird network stuff, JNIs)

[ Parent | on HN ]