- ck_epoch_begin: Disallow early load of epoch as it leads to measurable
performance degradation in some benchmarks.
- ck_epoch_synchronize: Enforce barrier semantics.
This function allows for explicit execution of all
deferred callbacks in an epoch_record. The primary
motivation is currently for performance profiling
but there are other use-cases where best-effort
semantics could be applied.
I had the pleasure of spending a significant amount of time at the most
recent LPC with Mathieu Desnoyers and Paul McKenney. In discussing
RCU semantics in relation to epoch reclamation, it was argued that
epoch reclamation is a specialisation of RCU (rather than a generalization).
In light of this discussion, I thought it would make more sense to not expose
write-side synchronization semantics aside from ck_epoch_call (similar to
RCU call), ck_epoch_poll (identical to tick), ck_epoch_barrier and
ck_epoch_synchronization (similar to ck_epoch_synchronization). Writers will
now longer have to use write-side epoch sections but can instead rely on
epoch_barrier/synchronization for blocking semantics and ck_epoch_poll
for old tick semantics.
One advantage of this is we can avoid write-side recursion for certain workloads.
Additionally, for infrequent writes, epoch_barrier and epoch_synchronization both
allow for blocking semantics to be used so you don't have to pay the cost of
epoch_entry for non-blocking dispatch.
Example usage:
e = stack_pop(mystack);
ck_epoch_synchronize(...);
free(e);
read_begin and read_end has been replaced with ck_epoch_begin and ck_epoch_end.
If multiple writers need SMR guarantees, then they can also use ck_epoch_begin
and ck_epoch_end. Any dispatch in presence of multiple writers should be done
with-in an epoch section (for now).
There are some follow-up commits to come.
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.
Matthew Macy
Samy Al Bahra
Olivier Houchard
Samy Al Bahra
Samy Al Bahra