On Thu, 6 Mar 2025 16:26:31 GMT, Thomas Schatzl <tscha...@openjdk.org> wrote:
>> Hi all, >> >> please review this change that implements (currently Draft) JEP: G1: >> Improve Application Throughput with a More Efficient Write-Barrier. >> >> The reason for posting this early is that this is a large change, and the >> JEP process is already taking very long with no end in sight but we would >> like to have this ready by JDK 25. >> >> ### Current situation >> >> With this change, G1 will reduce the post write barrier to much more >> resemble Parallel GC's as described in the JEP. The reason is that G1 lacks >> in throughput compared to Parallel/Serial GC due to larger barrier. >> >> The main reason for the current barrier is how g1 implements concurrent >> refinement: >> * g1 tracks dirtied cards using sets (dirty card queue set - dcqs) of >> buffers (dirty card queues - dcq) containing the location of dirtied cards. >> Refinement threads pick up their contents to re-refine. The barrier needs to >> enqueue card locations. >> * For correctness dirty card updates requires fine-grained synchronization >> between mutator and refinement threads, >> * Finally there is generic code to avoid dirtying cards altogether >> (filters), to avoid executing the synchronization and the enqueuing as much >> as possible. >> >> These tasks require the current barrier to look as follows for an assignment >> `x.a = y` in pseudo code: >> >> >> // Filtering >> if (region(@x.a) == region(y)) goto done; // same region check >> if (y == null) goto done; // null value check >> if (card(@x.a) == young_card) goto done; // write to young gen check >> StoreLoad; // synchronize >> if (card(@x.a) == dirty_card) goto done; >> >> *card(@x.a) = dirty >> >> // Card tracking >> enqueue(card-address(@x.a)) into thread-local-dcq; >> if (thread-local-dcq is not full) goto done; >> >> call runtime to move thread-local-dcq into dcqs >> >> done: >> >> >> Overall this post-write barrier alone is in the range of 40-50 total >> instructions, compared to three or four(!) for parallel and serial gc. >> >> The large size of the inlined barrier not only has a large code footprint, >> but also prevents some compiler optimizations like loop unrolling or >> inlining. >> >> There are several papers showing that this barrier alone can decrease >> throughput by 10-20% >> ([Yang12](https://dl.acm.org/doi/10.1145/2426642.2259004)), which is >> corroborated by some benchmarks (see links). >> >> The main idea for this change is to not use fine-grained synchronization >> between refinement and mutator threads, but coarse grained based on >> atomically switching c... > > Thomas Schatzl has updated the pull request incrementally with one additional > commit since the last revision: > > * iwalulya review > * renaming > * fix some includes, forward declaration src/hotspot/share/gc/g1/g1CardTable.hpp line 76: > 74: g1_card_already_scanned = 0x1, > 75: g1_to_cset_card = 0x2, > 76: g1_from_remset_card = 0x4 Could you outline the motivation for this more precise info? Is it for optimization or essentially for correctness? src/hotspot/share/gc/g1/g1ConcurrentRefineSweepTask.cpp line 54: > 52: assert(refinement_r == card_r, "not same region source %u (%zu) dest > %u (%zu) ", refinement_r->hrm_index(), refinement_i, card_r->hrm_index(), > card_i); > 53: assert(refinement_i == card_i, "indexes are not same %zu %zu", > refinement_i, card_i); > 54: #endif I feel this assert logic can be extracted to a method, sth like `verify_card_pair`. src/hotspot/share/gc/g1/g1ConcurrentRefineThread.cpp line 64: > 62: report_inactive("Paused"); > 63: sts_join.yield(); > 64: // Reset after yield rather than accumulating across yields, else > a The comment seems obsolete after the removal of stats. src/hotspot/share/gc/g1/g1OopClosures.inline.hpp line 158: > 156: if (_has_ref_to_cset) { > 157: return; > 158: } Is it really necessary to write `false` to `_has_ref_to_cset`? ------------- PR Review Comment: https://git.openjdk.org/jdk/pull/23739#discussion_r1985041202 PR Review Comment: https://git.openjdk.org/jdk/pull/23739#discussion_r1983846649 PR Review Comment: https://git.openjdk.org/jdk/pull/23739#discussion_r1983842440 PR Review Comment: https://git.openjdk.org/jdk/pull/23739#discussion_r1983857348
