Refactor rtree to be lock-free.

Recent huge allocation refactoring associates huge allocations with
arenas, but it remains necessary to quickly look up huge allocation
metadata during reallocation/deallocation.  A global radix tree remains
a good solution to this problem, but locking would have become the
primary bottleneck after (upcoming) migration of chunk management from
global to per arena data structures.

This lock-free implementation uses double-checked reads to traverse the
tree, so that in the steady state, each read or write requires only a
single atomic operation.

This implementation also assures that no more than two tree levels
actually exist, through a combination of careful virtual memory
allocation which makes large sparse nodes cheap, and skipping the root
node on x64 (possible because the top 16 bits are all 0 in practice).
This commit is contained in:
Jason Evans
2015-01-30 22:54:08 -08:00
parent c810fcea1f
commit 8d0e04d42f
7 changed files with 384 additions and 229 deletions

View File

@@ -369,14 +369,21 @@ quarantine_alloc_hook
quarantine_alloc_hook_work
quarantine_cleanup
register_zone
rtree_child_read
rtree_child_read_hard
rtree_child_tryread
rtree_delete
rtree_get
rtree_get_locked
rtree_new
rtree_postfork_child
rtree_postfork_parent
rtree_prefork
rtree_node_valid
rtree_set
rtree_start_level
rtree_subkey
rtree_subtree_read
rtree_subtree_read_hard
rtree_subtree_tryread
rtree_val_read
rtree_val_write
s2u
s2u_compute
s2u_lookup