Summary:
I ran multiple runs of crash test jobs internally, so far I've seen one iterator mismatch and one assertion failure. I've added relevant logging improvements to help debugging them. use_multiscan will be stable within a crash test run to make it easier to triage.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13888
Test Plan: `python3 tools/db_crashtest.py whitebox --prefix_size=-1 --test_batches_snapshots=0 --use_multiscan=1 --read_fault_one_in=0 --kill_random_test=88888`
Reviewed By: anand1976
Differential Revision: D80627399
Pulled By: cbi42
fbshipit-source-id: 2fa3f77e730f5bc7d1d200dc122cf84e3558c588
0b426ff58d