Extend trace filtering to more operation types

[ajkr]

• Extended trace filtering to cover MultiGet(), Seek(), and SeekForPrev(). Now all user ops that can be traced support filtering.
• Enabled the new filter masks in db_stress since it only cares to trace writes.

Test Plan:

• trace-heavy db_stress command reduced 30% elapsed time (79.21 -> 55.47 seconds)

Benchmark command:

$ /usr/bin/time ./db_stress -ops_per_thread=100000 -sync_fault_injection=1 --db=/dev/shm/rocksdb_stress_db/ --expected_values_dir=/dev/shm/rocksdb_stress_expected/ --clear_column_family_one_in=0

• replay-heavy db_stress command reduced 12.4% elapsed time (23.69 -> 20.75 seconds)

Setup command:

$  ./db_stress -ops_per_thread=100000000 -sync_fault_injection=1 -db=/dev/shm/rocksdb_stress_db/ -expected_values_dir=/dev/shm/rocksdb_stress_expected --clear_column_family_one_in=0 & sleep 120; pkill -9 db_stress

Benchmark command:

$ /usr/bin/time ./db_stress -ops_per_thread=1 -reopen=0 -expected_values_dir=/dev/shm/rocksdb_stress_expected/ -db=/dev/shm/rocksdb_stress_db/ --clear_column_family_one_in=0 --destroy_db_initially=0

[facebook-github-bot]

@ajkr has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[zhichao-cao]

LGTM, thanks!

[ajkr]

Thanks for the review!