You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
Niko PLP 081ffa92ee Squashed 'librocksdb-sys/rocksdb/' content from commit 217f76421 1 year ago
..
advisor Squashed 'librocksdb-sys/rocksdb/' content from commit 217f76421 1 year ago
test Squashed 'librocksdb-sys/rocksdb/' content from commit 217f76421 1 year ago
README.md Squashed 'librocksdb-sys/rocksdb/' content from commit 217f76421 1 year ago

README.md

Rocksdb Tuning Advisor

Motivation

The performance of Rocksdb is contingent on its tuning. However, because of the complexity of its underlying technology and a large number of configurable parameters, a good configuration is sometimes hard to obtain. The aim of the python command-line tool, Rocksdb Advisor, is to automate the process of suggesting improvements in the configuration based on advice from Rocksdb experts.

Overview

Experts share their wisdom as rules comprising of conditions and suggestions in the INI format (refer rules.ini). Users provide the Rocksdb configuration that they want to improve upon (as the familiar Rocksdb OPTIONS file — example) and the path of the file which contains Rocksdb logs and statistics. The Advisor creates appropriate DataSource objects (for Rocksdb logs, options, statistics etc.) and provides them to the Rules Engine. The Rules uses rules from experts to parse data-sources and trigger appropriate rules. The Advisor's output gives information about which rules were triggered, why they were triggered and what each of them suggests. Each suggestion provided by a triggered rule advises some action on a Rocksdb configuration option, for example, increase CFOptions.write_buffer_size, set bloom_bits to 2 etc.

Usage

Prerequisites

The tool needs the following to run:

  • python3

Running the tool

An example command to run the tool:

cd rocksdb/tools/advisor
python3 -m advisor.rule_parser_example --rules_spec=advisor/rules.ini --rocksdb_options=test/input_files/OPTIONS-000005 --log_files_path_prefix=test/input_files/LOG-0 --stats_dump_period_sec=20

Command-line arguments

Most important amongst all the input that the Advisor needs, are the rules spec and starting Rocksdb configuration. The configuration is provided as the familiar Rocksdb Options file (refer example). The Rules spec is written in the INI format (more details in rules.ini).

In brief, a Rule is made of conditions and is triggered when all its constituent conditions are triggered. When triggered, a Rule suggests changes (increase/decrease/set to a suggested value) to certain Rocksdb options that aim to improve Rocksdb performance. Every Condition has a 'source' i.e. the data source that would be checked for triggering that condition. For example, a log Condition (with 'source=LOG') is triggered if a particular 'regex' is found in the Rocksdb LOG files. As of now the Rules Engine supports 3 types of Conditions (and consequently data-sources): LOG, OPTIONS, TIME_SERIES. The TIME_SERIES data can be sourced from the Rocksdb statistics or perf context.

For more information about the remaining command-line arguments, run:

cd rocksdb/tools/advisor
python3 -m advisor.rule_parser_example --help

Sample output

Here, a Rocksdb log-based rule has been triggered:

Rule: stall-too-many-memtables
LogCondition: stall-too-many-memtables regex: Stopping writes because we have \d+ immutable memtables \(waiting for flush\), max_write_buffer_number is set to \d+
Suggestion: inc-bg-flush option : DBOptions.max_background_flushes action : increase suggested_values : ['2']
Suggestion: inc-write-buffer option : CFOptions.max_write_buffer_number action : increase
scope: col_fam:
{'default'}

Running the tests

Tests for the code have been added to the test/ directory. For example, to run the unit tests for db_log_parser.py:

cd rocksdb/tools/advisor
python3 -m unittest -v test.test_db_log_parser