Revision 249eff0f304d3afe8b12110b7fb929bd2ac0e494 authored by Peter Dillinger on 27 April 2020, 20:18:18 UTC, committed by Facebook GitHub Bot on 27 April 2020, 20:20:27 UTC
Summary:
Since read threads do not coordinate on loading data into block
cache, two threads between Lookup and Insert can end up loading and
inserting the same data. This is particularly concerning with
cache_index_and_filter_blocks since those are hot and more likely to
be race targets if ejected from (or not pre-populated in) the cache.

Particularly with moves toward disaggregated / network storage, the cost
of redundant retrieval might be high, and we should at least have some
hard statistics from which we can estimate impact.

Example with full filter thrashing "cliff":

    $ ./db_bench --benchmarks=fillrandom --num=15000000 --cache_index_and_filter_blocks -bloom_bits=10
    ...
    $ ./db_bench --db=/tmp/rocksdbtest-172704/dbbench --use_existing_db --benchmarks=readrandom,stats --num=200000 --cache_index_and_filter_blocks --cache_size=$((130 * 1024 * 1024)) --bloom_bits=10 --threads=16 -statistics 2>&1 | egrep '^rocksdb.block.cache.(.*add|.*redundant)' | grep -v compress | sort
    rocksdb.block.cache.add COUNT : 14181
    rocksdb.block.cache.add.failures COUNT : 0
    rocksdb.block.cache.add.redundant COUNT : 476
    rocksdb.block.cache.data.add COUNT : 12749
    rocksdb.block.cache.data.add.redundant COUNT : 18
    rocksdb.block.cache.filter.add COUNT : 1003
    rocksdb.block.cache.filter.add.redundant COUNT : 217
    rocksdb.block.cache.index.add COUNT : 429
    rocksdb.block.cache.index.add.redundant COUNT : 241
    $ ./db_bench --db=/tmp/rocksdbtest-172704/dbbench --use_existing_db --benchmarks=readrandom,stats --num=200000 --cache_index_and_filter_blocks --cache_size=$((120 * 1024 * 1024)) --bloom_bits=10 --threads=16 -statistics 2>&1 | egrep '^rocksdb.block.cache.(.*add|.*redundant)' | grep -v compress | sort
    rocksdb.block.cache.add COUNT : 1182223
    rocksdb.block.cache.add.failures COUNT : 0
    rocksdb.block.cache.add.redundant COUNT : 302728
    rocksdb.block.cache.data.add COUNT : 31425
    rocksdb.block.cache.data.add.redundant COUNT : 12
    rocksdb.block.cache.filter.add COUNT : 795455
    rocksdb.block.cache.filter.add.redundant COUNT : 130238
    rocksdb.block.cache.index.add COUNT : 355343
    rocksdb.block.cache.index.add.redundant COUNT : 172478
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6681

Test Plan: Some manual testing (above) and unit test covering key metrics is included

Reviewed By: ltamasi

Differential Revision: D21134113

Pulled By: pdillinger

fbshipit-source-id: c11497b5f00f4ffdfe919823904e52d0a1a91d87
1 parent 75b13ea
History
File Mode Size
.circleci
buckifier
build_tools
cache
cmake
coverage
db
db_stress_tool
docs
env
examples
file
hdfs
include
java
logging
memory
memtable
monitoring
options
port
table
test_util
third-party
tools
trace_replay
util
utilities
.clang-format -rw-r--r-- 138 bytes
.gitignore -rw-r--r-- 939 bytes
.lgtm.yml -rw-r--r-- 67 bytes
.travis.yml -rw-r--r-- 7.8 KB
.watchmanconfig -rw-r--r-- 130 bytes
AUTHORS -rw-r--r-- 322 bytes
CMakeLists.txt -rw-r--r-- 41.6 KB
CODE_OF_CONDUCT.md -rw-r--r-- 3.3 KB
CONTRIBUTING.md -rw-r--r-- 706 bytes
COPYING -rw-r--r-- 17.7 KB
DEFAULT_OPTIONS_HISTORY.md -rw-r--r-- 1.5 KB
DUMP_FORMAT.md -rw-r--r-- 763 bytes
HISTORY.md -rw-r--r-- 114.1 KB
INSTALL.md -rw-r--r-- 7.5 KB
LANGUAGE-BINDINGS.md -rw-r--r-- 1.1 KB
LICENSE.Apache -rw-r--r-- 11.1 KB
LICENSE.leveldb -rw-r--r-- 1.5 KB
Makefile -rw-r--r-- 77.0 KB
README.md -rw-r--r-- 1.8 KB
ROCKSDB_LITE.md -rw-r--r-- 1.0 KB
TARGETS -rw-r--r-- 37.6 KB
USERS.md -rw-r--r-- 6.8 KB
Vagrantfile -rw-r--r-- 1017 bytes
WINDOWS_PORT.md -rw-r--r-- 12.5 KB
appveyor.yml -rw-r--r-- 3.8 KB
defs.bzl -rw-r--r-- 1.9 KB
issue_template.md -rw-r--r-- 294 bytes
src.mk -rw-r--r-- 35.5 KB
thirdparty.inc -rw-r--r-- 7.8 KB

README.md

back to top