RFR (S): JEP-142: Reduce Cache Contention on Specified Fields
aleksey.shipilev at oracle.com
Tue Nov 27 05:59:14 PST 2012
On 11/27/2012 05:52 PM, Jesper Wilhelmsson wrote:
> Annotated fields and classes will be padded and require more memory.
> What would be the optimal behavior in an out of memory situation? Should
> the GC try to remove the padding to keep OOME away, or should we just
> accept that these objects are now larger and we are out of memory.
No can do. That means repackaging the field in existing classes forced
by GC; this is impossible unless JEP-159 is here.
> Also, the current design adds twice the size of a normal cache line, one
> potential improvement could be to make sure that allocation and GC are
> aware of these padded fields and always place them at the start of a
> cache line and only pads as much as needed to fill the rest of the cache
Yes, that was the inclination we are considering. We are padding in both
directions because we miss the GC interop at this point. This can be
added non-disruptively after the fact.
More information about the hotspot-dev