mirrors/scylladb
1
0
Fork 0
mirror of https://github.com/scylladb/scylladb.git synced 2026-04-29 04:37:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 'Cleanup sstables in resharding and other compaction types' from Benny Halevy

Browse Source 
This series extends sstable cleanup to resharding and other (offstrategy, major, and regular) compaction types so to:
* cleanup uploaded sstables (#11933)
* cleanup staging sstables after they are moved back to the main directory and become eligible for compaction (#9559)

When perform_cleanup is called, all sstables are scanned, and those that require cleanup are marked as such, and are added for tracking to table_state::cleanup_sstable_set.  They are removed from that set once released by compaction.
Along with that sstables set, we keep the owned_ranges_ptr used by cleanup in the table_state to allow other compaction types (offstrategy, major, or regular) to cleanup those sstables that are marked as require_cleanup and that were skipped by cleanup compaction for either being in the maintenance set (requiring offstrategy compaction) or in staging.

Resharding is using a more straightforward mechanism of passing the owned token ranges when resharding uploaded sstables and using it to detect sstable that require cleanup, now done as piggybacked on resharding compaction.

Closes #12422

* github.com:scylladb/scylladb:
  table: discard_sstables: update_sstable_cleanup_state when deleting sstables
  compaction_manager: compact_sstables: retrieve owned ranges if required
  sstables: add a printer for shared_sstable
  compaction_manager: keep owned_ranges_ptr in compaction_state
  compaction_manager: perform_cleanup: keep sstables in compaction_state::sstables_requiring_cleanup
  compaction: refactor compaction_state out of compaction_manager
  compaction: refactor compaction_fwd.hh out of compaction_descriptor.hh
  compaction_manager: compacting_sstable_registration: keep a ref to the compaction_state
  compaction_manager: refactor get_candidates
  compaction_manager: get_candidates: mark as const
  table, compaction_manager: add requires_cleanup
  sstable_set: add for_each_sstable_until
  distributed_loader: reshard: update sstable cleanup state
  table, compaction_manager: add update_sstable_cleanup_state
  compaction_manager: needs_cleanup: delete unused schema param
  compaction_manager: perform_cleanup: disallow empty sorted_owened_ranges
  distributed_loader: reshard: consider sstables for cleanup
  distributed_loader: process_upload_dir: pass owned_ranges_ptr to reshard
  distributed_loader: reshard: add optional owned_ranges_ptr param
  distributed_loader: reshard: get a ref to table_state
  distributed_loader: reshard: capture creator by ref
  distributed_loader: reshard: reserve num_jobs buckets
  compaction: move owned ranges filtering to base class
  compaction: move owned_ranges into descriptor
This commit is contained in:
Botond Dénes
2023-04-11 14:52:29 +03:00
parent 38c98b370f 96660b2ef7
commit f1bbf705f9
19 changed files with 432 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
test/boost/sstable_compaction_test.cc
View File

@@ -1998,7 +1998,7 @@ SEASTAR_TEST_CASE(sstable_cleanup_correctness_test) {
auto local_ranges = compaction::make_owned_ranges_ptr(db.get_keyspace_local_ranges(ks_name));
auto descriptor = sstables::compaction_descriptor({std::move(sst)}, default_priority_class(), compaction_descriptor::default_level,
compaction_descriptor::default_max_sstable_bytes, run_identifier, compaction_type_options::make_cleanup(std::move(local_ranges)));
compaction_descriptor::default_max_sstable_bytes, run_identifier, compaction_type_options::make_cleanup(), std::move(local_ranges));
auto ret = compact_sstables(std::move(descriptor), cf, sst_gen).get0();
BOOST_REQUIRE(ret.new_sstables.size() == 1);
@@ -3571,23 +3571,23 @@ SEASTAR_TEST_CASE(sstable_needs_cleanup_test) {
{
auto local_ranges = { token_range(0, 9) };
auto sst = sst_gen(keys[0], keys[9]);
BOOST_REQUIRE(!needs_cleanup(sst, local_ranges, s));
BOOST_REQUIRE(!needs_cleanup(sst, local_ranges));
}
{
auto local_ranges = { token_range(0, 1), token_range(3, 4), token_range(5, 6) };
auto sst = sst_gen(keys[0], keys[1]);
BOOST_REQUIRE(!needs_cleanup(sst, local_ranges, s));
BOOST_REQUIRE(!needs_cleanup(sst, local_ranges));
auto sst2 = sst_gen(keys[2], keys[2]);
BOOST_REQUIRE(needs_cleanup(sst2, local_ranges, s));
BOOST_REQUIRE(needs_cleanup(sst2, local_ranges));
auto sst3 = sst_gen(keys[0], keys[6]);
BOOST_REQUIRE(needs_cleanup(sst3, local_ranges, s));
BOOST_REQUIRE(needs_cleanup(sst3, local_ranges));
auto sst5 = sst_gen(keys[7], keys[7]);
BOOST_REQUIRE(needs_cleanup(sst5, local_ranges, s));
BOOST_REQUIRE(needs_cleanup(sst5, local_ranges));
}
});
}
@@ -4886,3 +4886,28 @@ SEASTAR_TEST_CASE(compaction_manager_stop_and_drain_race_test) {
testlog.info("stopping compaction manager");
co_await cm.stop();
}
SEASTAR_TEST_CASE(test_print_shared_sstables_vector) {
return test_env::do_with_async([] (test_env& env) {
simple_schema ss;
auto s = ss.schema();
auto pks = ss.make_pkeys(2);
auto sst_gen = env.make_sst_factory(s);
std::vector<sstables::shared_sstable> ssts(2);
auto mut0 = mutation(s, pks[0]);
mut0.partition().apply_insert(*s, ss.make_ckey(0), ss.new_timestamp());
ssts[0] = make_sstable_containing(sst_gen, {std::move(mut0)});
auto mut1 = mutation(s, pks[1]);
mut1.partition().apply_insert(*s, ss.make_ckey(1), ss.new_timestamp());
ssts[1] = make_sstable_containing(sst_gen, {std::move(mut1)});
std::string msg = format("{}", ssts);
for (const auto& sst : ssts) {
auto gen_str = format("{}", sst->generation());
BOOST_REQUIRE(msg.find(gen_str) != std::string::npos);
}
});
}