8000 compaction_readahead_size doesn't work when it is larger than max_sectors_kb · Issue #12038 · facebook/rocksdb · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
compaction_readahead_size doesn't work when it is larger than max_sectors_kb #12038
Open
@mdcallag

Description

@mdcallag

From tests I run with RocksDB 8.7 and 8.8 what I see with rareq-sz from iostat is many small reads (block sized) from compaction when compaction_readahead_size is larger than /sys/block/$device/queue/max_sectors_kb. Reducing compaction_readahead_size resolves the problem. I assume it should be smaller than max_sectors_kb+rocksdb_block_size or some other fudge factor because the readahead requested can be slightly larger than compaction_readahead_size.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions

    0