We shouldn't offload the responsibility of the read_begin flush
for shared data mutations to the user. read_end requires a load
barrier at the least, not a store barrier.
ck_epoch_reclaim is now the replacement for ck_epoch_flush.
ck_epoch_purge guarantees that all entries are reclaimed
for the provided record before exiting.
n_peak counter has been added, which provides the peak number
of items across all reclamation lists. n_reclamations provides
the number of reclamations across the lifetime of the record.
These are cleared on unregister.
ck_epoch_update has been renamed to ck_epoch_tick.
Hazardous sections which mutate shared structures are now
expected to begin with ck_epoch_write_begin and end with
ck_epoch_end.
Hazardous sections which read shared structures are now
expected to begin with ck_epoch_read_begin and end with
ck_epoch_end.
ck_hp_free is now more aggressive. It will attempt a
reclamation cycle any time the pending count is long.
I should probably add a ck_hp_retire to have a version
which allows for bulk updates to local reclamation lists.
Samy Al Bahra
Samy Al Bahra