[Pharo-project] Azul Pauseless GC
avalloud at smalltalk.comcastbiz.net
Mon Feb 28 11:20:54 CET 2011
>> What kind of documentation do you mean?
> A paper about the GC algorithm, the name of the algorithm?
There are some docs that state what happens, the docs come with the VM
sources. But, basically, when the IGC is marking, then writes into
marked objects mark objects. This allows mark stack consistency. You
can mark incrementally until the mark stack is empty. Then you can zero
out weak references that are gone (and deal with ephemerons). After
that, you can also sweep dead object bodies and put them back into the
corresponding free block "lists".
The VisualWorks implementation is somewhat complex because there are
many moving parts. The IGC marks whatever is in old space. Perm space
("permanent" old objects) are assumed to never be garbage, so they
aren't even marked. New objects are not marked either because they are
managed more efficiently by the new space scavenger. There are remember
tables that allow you to do all of this effectively. Special care must
be taken when tenuring new objects into old space if they were
referenced from a marked object in the remember table for new space. In
64 bit systems, the class table is weak so you have to treat it as a
special case. Etcetera :)...
> Their target is/was mainly financial/trade applications huge heaps,
> on huge and expensive custom hardware. Order of 1000 cores per box
> with a 54-core custom chip.
Wow... I wonder what happens when (not if) it crashes.
> I guess it is some variation of a three-color incremental mark/sweep?
IIRC, "three-color" refers to "not marked, marked, and scanned". If so,
yes, it's sort of like that.
> One of the tricks they are pulling for that is that they return the
> memory page to the OS, and thus, they run into a trap when ever
> someone is referring to an old object address. Then, when that
> occurs they just fix the address to the new one. (as far as I
Oh, ok. With such huge images, the likelyhood of any page being
accessed must not be overly high. I suspect they may have to have some
sort of "mark stack" that cannot be paged out to make that possible.
More information about the Pharo-project