Revision ba0967b567cfdad44e9e1762a17dd1802e02c2ce authored by Andrew Kryczka on 26 August 2019, 21:59:24 UTC, committed by Facebook Github Bot on 26 August 2019, 22:00:43 UTC
Summary: This condition is now a normal occurrence during write burst so there is no need to warn the user about it. Here is a scenario where it happens under completely normal conditions. * Initially we have a DB of three levels (L0, L1, and L2) that is stable, i.e., compaction scores are all less than one. * Now a write burst comes along. At first L0 blows up a bit in size as compaction hasn't had a chance to catch up. * As a result of the above, `base_bytes_min` also increases since it is based on L0 size as of https://github.com/facebook/rocksdb/issues/4338 * If `base_bytes_min` increased enough (i.e., to be larger than L1), then we are shown the warning that the DB has more levels than necessary. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5742 Differential Revision: D17059221 fbshipit-source-id: e4a31d6eea42089a8d273095f19653991bd91bea
1 parent 62829ff
| File | Mode | Size |
|---|---|---|
| backupable | ||
| blob_db | ||
| cassandra | ||
| checkpoint | ||
| compaction_filters | ||
| convenience | ||
| leveldb_options | ||
| memory | ||
| merge_operators | ||
| option_change_migration | ||
| options | ||
| persistent_cache | ||
| simulator_cache | ||
| table_properties_collectors | ||
| trace | ||
| transactions | ||
| ttl | ||
| write_batch_with_index | ||
| debug.cc | -rw-r--r-- | 2.6 KB |
| env_librados.cc | -rw-r--r-- | 36.3 KB |
| env_librados.md | -rw-r--r-- | 4.6 KB |
| env_librados_test.cc | -rw-r--r-- | 34.6 KB |
| env_mirror.cc | -rw-r--r-- | 7.9 KB |
| env_mirror_test.cc | -rw-r--r-- | 7.1 KB |
| env_timed.cc | -rw-r--r-- | 5.1 KB |
| env_timed_test.cc | -rw-r--r-- | 1.2 KB |
| merge_operators.h | -rw-r--r-- | 2.0 KB |
| object_registry.cc | -rw-r--r-- | 2.8 KB |
| object_registry_test.cc | -rw-r--r-- | 5.8 KB |
| util_merge_operators_test.cc | -rw-r--r-- | 3.3 KB |
Computing file changes ...
