d231d81...
by
Krunal Bauskar <email address hidden>
MDEV-25029: Reduce dict_sys mutex contention for read-only workload
In theory, read-only workload shouldn't have anything to do with
dict_sys mutex. dict_sys mutex is meant to protect database metadata.
But then why does dict_sys mutex shows up as part of a read-only workload?
This workload needs to fetch stats for query processing and while reading
these stats dict_sys mutex is taken.
Is this really needed?
No. For the traditional reasons, it was the default global mutex used.
Based on 10.6 changes, flow can now use table->lock_mutex to protect
update/access of these stats. table mutexes being table specific
global contention arising out of dict_sys is reduced.
Thanks to Marko Makela for his early suggestion around proposed alternative
and review of the draft patch.
MDEV-25016 Race condition between lock_sys_t::cancel() and page split or merge
In commit 8d16da14873d880b9b5121de1619b7cb5e0f7135 (MDEV-24789)
we accidentally introduced a race condition. During the time a
waiting lock request is being removed, the request might be
moved to another page due to a concurrent page split or merge.
To prevent this, we must hold exclusive lock_sys.latch when releasing
a record lock.
lock_release_autoinc_locks(): Avoid a potential hang.
No dict_table_t::lock_mutex must be waited for while already holding
lock_sys.wait_mutex or trx_t::mutex.
MDEV-24863 AHI entries mismatch with the index while reloading the evicted tables.
This is after-merge fix of f33e57a9e66f7e1790cb84b141381bb668e281a0.
In btr_search_drop_page_hash_index(), InnoDB should take
the exclusive lock on the AHI latch if index is already
freed to avoid the freed memory access during buf_pool_resize()
MDEV-24973 Performance schema duplicates rarely executed code for mutex operations
The PERFORMANCE_SCHEMA wrapper for mutex and rw-lock operations is
causing a lot of unlikely code to be inlined in each invocation.
The impact of this may have been emphasized in MariaDB 10.6, because
InnoDB now uses the common implementation of mutexes and condition
variables (MDEV-21452).
By default, we build with cmake -DPLUGIN_PERFSCHEMA enabled,
but at runtime no instrumentation will be enabled. Similar to
commit eba2d10ac53d1d2f975027ba2b2ca39d9c9b98ad
we had better avoid inlining the rarely executed code in order to reduce
the code size and to improve the efficiency of the instruction cache.
This change was extensively tested by Axel Schwenke with and without
--enable-performance-schema (with no individual instruments enabled).
Removing the inline functions did not cause any performance regression
in either case. There seemed to be a tiny improvement, possibly due
to reduced code size and better instruction cache hit rate.
MDEV-24811 Assertion find(table) failed with innodb_evict_tables_on_commit_debug
lock_release_try(): Implement innodb_evict_tables_on_commit_debug.
Before releasing any locks, collect the identifiers of tables to
be evicted. After releasing all locks, look up for the tables and
evict them if it is safe to do so.
trx_t::commit_tables(): Remove the eviction logic.
trx_t::commit_in_memory(): Invoke release_locks() only after
commit_tables().
MDEV-24789: Reduce lock_sys mutex contention further
lock_sys_t::deadlock_check(): Assume that only lock_sys.wait_mutex
is being held by the caller.
lock_sys_t::rd_lock_try(): New function.
lock_sys_t::cancel(trx_t*): Kill an active transaction that may be
holding a lock.
lock_sys_t::cancel(trx_t*, lock_t*): Cancel a waiting lock request.
lock_trx_handle_wait(): Avoid acquiring mutexes in some cases,
and in never acquire lock_sys.latch in exclusive mode.
This function is only invoked in a semi-consistent read
(locking a clustered index record only if it matches the search condition).
Normally, lock_wait() will take care of lock waits.
lock_wait(): Invoke the new function lock_sys_t::cancel() at the end,
to avoid acquiring exclusive lock_sys.latch.
lock_rec_other_trx_holds_expl(): Use LockGuard instead of LockMutexGuard.
lock_release_autoinc_locks(): Explicitly acquire table->lock_mutex,
in case only a shared lock_sys.latch is being held. Deadlock::report()
will still hold exclusive lock_sys.latch while invoking
lock_cancel_waiting_and_release().
lock_cancel_waiting_and_release(): Acquire trx->mutex in this function,
instead of expecting the caller to do so.
lock_unlock_table_autoinc(): Only acquire shared lock_sys.latch.
lock_table_has_locks(): Do not acquire lock_sys.latch at all.
Deadlock::check_and_resolve(): Only acquire shared lock_sys.latchm
for invoking lock_sys_t::cancel(trx, wait_lock).
innobase_query_caching_table_check_low(),
row_drop_tables_for_mysql_in_background(): Do not acquire lock_sys.latch.
