-
Type:
Improvement
-
Status: Triage Needed
-
Priority:
Normal
-
Resolution: Unresolved
-
Fix Version/s: None
-
Component/s: Documentation/Website
-
Labels:None
-
Platform:All
-
Impacts:None
The recommendations on http://cassandra.apache.org/doc/latest/operating/hardware.html are pretty out of date. We should improve the following:
- GC recommendations. We (The Last Pickle) routinely use 16GB heaps with 8-10GB of new gen, Survivor ratio of 4-6 and max tenuring threshold of 6. It works far better than G1GC
- The instance sizes in AWS are pretty outdated. M1s are years out of date. i3's work well with NVMe disks, EBS works OK if you want easy backups and replacements.