Avoiding Full GCs in HBase with MemStore-Local Allocation Buffers: Part 3

http://www.cloudera.com/blog/2011/03/avoiding-full-gcs-in-hbase-with-memstore-local-allocation-buffers-part-3/

by tlipcon • 15 years ago

26 4 15 years ago

cloudera.com

j2d2j2d2• 15 years ago

The CMS strategy strikes me as being very similar to how Azuls concurrent GC works.

Could anyone with better understanding of GC comment?

tlipcon2• 15 years ago

Azul's concurrent GC is much more clever. They use some tricks with memory mapping in order to perform really efficient read barriers (which traditional VMs have considered too costly). This allows compaction to happen while mutator threads proceed.

This is a nice presentation about it: http://www.research.ibm.com/mre05/Click.pdf

And of course the paper: http://usenix.org/events/vee05/full_papers/p46-click.pdf

SpikeGronim• 15 years ago

That is an awesome GC and I wish I could have it. AFAIK they are having trouble because they mmap/munmap a lot, and virtual memory systems on modern OS don't do that efficiently enough.

Avoiding Full GCs in HBase with MemStore-Local Allocation Buffers: Part 3

Related Stories