News for hackers. Stuff that matters.

A comment on CockroachDB 2.0 released. Parent comment

Re:CockroachDB 2.0 released by darksaints on Wednesday April 04, 2018 @11:51AM (#16755879)
That might be a good intermediate option, but they still don't have instances with 4x24 cpu, or >488GB ram.
[ Parent | on HN ]
Re:CockroachDB 2.0 released by openasocket on Wednesday April 04, 2018 @12:06PM (#16756042)
Did you look at the x1 options? Up to 128 CPUs and 3,904GB of RAM on the x1e.32xlarge.
[ Parent | on HN ]
Re:CockroachDB 2.0 released by darksaints on Wednesday April 04, 2018 @12:28PM (#16756285)
Those aren't bare metal. And in terms of database scalability, I would jump for bare metal before beefier servers, due to the fact that the disk is local and you don't have to deal with EBS noisy neighbors.
[ Parent | on HN ]
Re:CockroachDB 2.0 released by openasocket on Wednesday April 04, 2018 @12:43PM (#16756464)
The x1e.32xlarge has 4TB of SSD in addition to dedicated EBS bandwidth.
[ Parent | on HN ]
Re:CockroachDB 2.0 released by saosebastiao on Wednesday April 04, 2018 @01:15PM (#16756814)
I haven't tried it, but IIRC that's only network bandwidth to the block store. Better than the alternative for sure, but I would assume disk access is still noisy unless you have a dedicated drive.
[ Parent | on HN ]
Re:CockroachDB 2.0 released by welder on Wednesday April 04, 2018 @06:46PM (#16760012)
The max IOPS for provisioned EBS is less than 10% the max IOPS of dedicated hardware SSDs.
[ Parent | on HN ]
Re:CockroachDB 2.0 released by openasocket on Wednesday April 04, 2018 @01:22PM (#16756870)
True, but you do have 4TB dedicated SSD
[ Parent | on HN ]