rocksdb/tools/db_crashtest.py

707 lines
28 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
from __future__ import absolute_import, division, print_function, unicode_literals
import os
import sys
import time
import random
import re
import tempfile
import subprocess
import shutil
import argparse
# params overwrite priority:
# for default:
# default_params < {blackbox,whitebox}_default_params < args
# for simple:
# default_params < {blackbox,whitebox}_default_params <
# simple_default_params <
# {blackbox,whitebox}_simple_default_params < args
# for cf_consistency:
# default_params < {blackbox,whitebox}_default_params <
# cf_consistency_params < args
# for txn:
# default_params < {blackbox,whitebox}_default_params < txn_params < args
default_params = {
"acquire_snapshot_one_in": 10000,
"backup_max_size": 100 * 1024 * 1024,
# Consider larger number when backups considered more stable
"backup_one_in": 100000,
Integrity protection for live updates to WriteBatch (#7748) Summary: This PR adds the foundation classes for key-value integrity protection and the first use case: protecting live updates from the source buffers added to `WriteBatch` through the destination buffer in `MemTable`. The width of the protection info is not yet configurable -- only eight bytes per key is supported. This PR allows users to enable protection by constructing `WriteBatch` with `protection_bytes_per_key == 8`. It does not yet expose a way for users to get integrity protection via other write APIs (e.g., `Put()`, `Merge()`, `Delete()`, etc.). The foundation classes (`ProtectionInfo.*`) embed the coverage info in their type, and provide `Protect.*()` and `Strip.*()` functions to navigate between types with different coverage. For making bytes per key configurable (for powers of two up to eight) in the future, these classes are templated on the unsigned integer type used to store the protection info. That integer contains the XOR'd result of hashes with independent seeds for all covered fields. For integer fields, the hash is computed on the raw unadjusted bytes, so the result is endian-dependent. The most significant bytes are truncated when the hash value (8 bytes) is wider than the protection integer. When `WriteBatch` is constructed with `protection_bytes_per_key == 8`, we hold a `ProtectionInfoKVOTC` (i.e., one that covers key, value, optype aka `ValueType`, timestamp, and CF ID) for each entry added to the batch. The protection info is generated from the original buffers passed by the user, as well as the original metadata generated internally. When writing to memtable, each entry is transformed to a `ProtectionInfoKVOTS` (i.e., dropping coverage of CF ID and adding coverage of sequence number), since at that point we know the sequence number, and have already selected a memtable corresponding to a particular CF. This protection info is verified once the entry is encoded in the `MemTable` buffer. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7748 Test Plan: - an integration test to verify a wide variety of single-byte changes to the encoded `MemTable` buffer are caught - add to stress/crash test to verify it works in variety of configs/operations without intentional corruption - [deferred] unit tests for `ProtectionInfo.*` classes for edge cases like KV swap, `SliceParts` and `Slice` APIs are interchangeable, etc. Reviewed By: pdillinger Differential Revision: D25754492 Pulled By: ajkr fbshipit-source-id: e481bac6c03c2ab268be41359730f1ceb9964866
2021-01-29 21:17:17 +01:00
"batch_protection_bytes_per_key": lambda: random.choice([0, 8]),
"block_size": 16384,
"bloom_bits": lambda: random.choice([random.randint(0,19),
random.lognormvariate(2.3, 1.3)]),
"cache_index_and_filter_blocks": lambda: random.randint(0, 1),
"cache_size": 1048576,
"checkpoint_one_in": 1000000,
"compression_type": lambda: random.choice(
["none", "snappy", "zlib", "bzip2", "lz4", "lz4hc", "xpress", "zstd"]),
"bottommost_compression_type": lambda:
"disable" if random.randint(0, 1) == 0 else
random.choice(
["none", "snappy", "zlib", "bzip2", "lz4", "lz4hc", "xpress",
"zstd"]),
"checksum_type" : lambda: random.choice(["kCRC32c", "kxxHash", "kxxHash64"]),
"compression_max_dict_bytes": lambda: 16384 * random.randint(0, 1),
"compression_zstd_max_train_bytes": lambda: 65536 * random.randint(0, 1),
# Disabled compression_parallel_threads as the feature is not stable
# lambda: random.choice([1] * 9 + [4])
"compression_parallel_threads": 1,
Limit buffering for collecting samples for compression dictionary (#7970) Summary: For dictionary compression, we need to collect some representative samples of the data to be compressed, which we use to either generate or train (when `CompressionOptions::zstd_max_train_bytes > 0`) a dictionary. Previously, the strategy was to buffer all the data blocks during flush, and up to the target file size during compaction. That strategy allowed us to randomly pick samples from as wide a range as possible that'd be guaranteed to land in a single output file. However, some users try to make huge files in memory-constrained environments, where this strategy can cause OOM. This PR introduces an option, `CompressionOptions::max_dict_buffer_bytes`, that limits how much data blocks are buffered before we switch to unbuffered mode (which means creating the per-SST dictionary, writing out the buffered data, and compressing/writing new blocks as soon as they are built). It is not strict as we currently buffer more than just data blocks -- also keys are buffered. But it does make a step towards giving users predictable memory usage. Related changes include: - Changed sampling for dictionary compression to select unique data blocks when there is limited availability of data blocks - Made use of `BlockBuilder::SwapAndReset()` to save an allocation+memcpy when buffering data blocks for building a dictionary - Changed `ParseBoolean()` to accept an input containing characters after the boolean. This is necessary since, with this PR, a value for `CompressionOptions::enabled` is no longer necessarily the final component in the `CompressionOptions` string. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7970 Test Plan: - updated `CompressionOptions` unit tests to verify limit is respected (to the extent expected in the current implementation) in various scenarios of flush/compaction to bottommost/non-bottommost level - looked at jemalloc heap profiles right before and after switching to unbuffered mode during flush/compaction. Verified memory usage in buffering is proportional to the limit set. Reviewed By: pdillinger Differential Revision: D26467994 Pulled By: ajkr fbshipit-source-id: 3da4ef9fba59974e4ef40e40c01611002c861465
2021-02-19 23:06:59 +01:00
"compression_max_dict_buffer_bytes": lambda: (1 << random.randint(0, 40)) - 1,
"clear_column_family_one_in": 0,
"compact_files_one_in": 1000000,
"compact_range_one_in": 1000000,
"delpercent": 4,
"delrangepercent": 1,
"destroy_db_initially": 0,
"enable_pipelined_write": lambda: random.randint(0, 1),
"enable_compaction_filter": lambda: random.choice([0, 0, 0, 1]),
"expected_values_path": lambda: setup_expected_values_file(),
"flush_one_in": 1000000,
"file_checksum_impl": lambda: random.choice(["none", "crc32c", "xxh64", "big"]),
"get_live_files_one_in": 1000000,
# Note: the following two are intentionally disabled as the corresponding
# APIs are not guaranteed to succeed.
"get_sorted_wal_files_one_in": 0,
"get_current_wal_file_one_in": 0,
# Temporarily disable hash index
"index_type": lambda: random.choice([0, 0, 0, 2, 2, 3]),
"iterpercent": 10,
"mark_for_compaction_one_file_in": lambda: 10 * random.randint(0, 1),
"max_background_compactions": 20,
"max_bytes_for_level_base": 10485760,
"max_key": 100000000,
"max_write_buffer_number": 3,
"mmap_read": lambda: random.randint(0, 1),
"nooverwritepercent": 1,
"open_files": lambda : random.choice([-1, -1, 100, 500000]),
Minimize memory internal fragmentation for Bloom filters (#6427) Summary: New experimental option BBTO::optimize_filters_for_memory builds filters that maximize their use of "usable size" from malloc_usable_size, which is also used to compute block cache charges. Rather than always "rounding up," we track state in the BloomFilterPolicy object to mix essentially "rounding down" and "rounding up" so that the average FP rate of all generated filters is the same as without the option. (YMMV as heavily accessed filters might be unluckily lower accuracy.) Thus, the option near-minimizes what the block cache considers as "memory used" for a given target Bloom filter false positive rate and Bloom filter implementation. There are no forward or backward compatibility issues with this change, though it only works on the format_version=5 Bloom filter. With Jemalloc, we see about 10% reduction in memory footprint (and block cache charge) for Bloom filters, but 1-2% increase in storage footprint, due to encoding efficiency losses (FP rate is non-linear with bits/key). Why not weighted random round up/down rather than state tracking? By only requiring malloc_usable_size, we don't actually know what the next larger and next smaller usable sizes for the allocator are. We pick a requested size, accept and use whatever usable size it has, and use the difference to inform our next choice. This allows us to narrow in on the right balance without tracking/predicting usable sizes. Why not weight history of generated filter false positive rates by number of keys? This could lead to excess skew in small filters after generating a large filter. Results from filter_bench with jemalloc (irrelevant details omitted): (normal keys/filter, but high variance) $ ./filter_bench -quick -impl=2 -average_keys_per_filter=30000 -vary_key_count_ratio=0.9 Build avg ns/key: 29.6278 Number of filters: 5516 Total size (MB): 200.046 Reported total allocated memory (MB): 220.597 Reported internal fragmentation: 10.2732% Bits/key stored: 10.0097 Average FP rate %: 0.965228 $ ./filter_bench -quick -impl=2 -average_keys_per_filter=30000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory Build avg ns/key: 30.5104 Number of filters: 5464 Total size (MB): 200.015 Reported total allocated memory (MB): 200.322 Reported internal fragmentation: 0.153709% Bits/key stored: 10.1011 Average FP rate %: 0.966313 (very few keys / filter, optimization not as effective due to ~59 byte internal fragmentation in blocked Bloom filter representation) $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000 -vary_key_count_ratio=0.9 Build avg ns/key: 29.5649 Number of filters: 162950 Total size (MB): 200.001 Reported total allocated memory (MB): 224.624 Reported internal fragmentation: 12.3117% Bits/key stored: 10.2951 Average FP rate %: 0.821534 $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory Build avg ns/key: 31.8057 Number of filters: 159849 Total size (MB): 200 Reported total allocated memory (MB): 208.846 Reported internal fragmentation: 4.42297% Bits/key stored: 10.4948 Average FP rate %: 0.811006 (high keys/filter) $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000000 -vary_key_count_ratio=0.9 Build avg ns/key: 29.7017 Number of filters: 164 Total size (MB): 200.352 Reported total allocated memory (MB): 221.5 Reported internal fragmentation: 10.5552% Bits/key stored: 10.0003 Average FP rate %: 0.969358 $ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory Build avg ns/key: 30.7131 Number of filters: 160 Total size (MB): 200.928 Reported total allocated memory (MB): 200.938 Reported internal fragmentation: 0.00448054% Bits/key stored: 10.1852 Average FP rate %: 0.963387 And from db_bench (block cache) with jemalloc: $ ./db_bench -db=/dev/shm/dbbench.no_optimize -benchmarks=fillrandom -format_version=5 -value_size=90 -bloom_bits=10 -num=2000000 -threads=8 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false $ ./db_bench -db=/dev/shm/dbbench -benchmarks=fillrandom -format_version=5 -value_size=90 -bloom_bits=10 -num=2000000 -threads=8 -optimize_filters_for_memory -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false $ (for FILE in /dev/shm/dbbench.no_optimize/*.sst; do ./sst_dump --file=$FILE --show_properties | grep 'filter block' ; done) | awk '{ t += $4; } END { print t; }' 17063835 $ (for FILE in /dev/shm/dbbench/*.sst; do ./sst_dump --file=$FILE --show_properties | grep 'filter block' ; done) | awk '{ t += $4; } END { print t; }' 17430747 $ #^ 2.1% additional filter storage $ ./db_bench -db=/dev/shm/dbbench.no_optimize -use_existing_db -benchmarks=readrandom,stats -statistics -bloom_bits=10 -num=2000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false -duration=10 -cache_index_and_filter_blocks -cache_size=1000000000 rocksdb.block.cache.index.add COUNT : 33 rocksdb.block.cache.index.bytes.insert COUNT : 8440400 rocksdb.block.cache.filter.add COUNT : 33 rocksdb.block.cache.filter.bytes.insert COUNT : 21087528 rocksdb.bloom.filter.useful COUNT : 4963889 rocksdb.bloom.filter.full.positive COUNT : 1214081 rocksdb.bloom.filter.full.true.positive COUNT : 1161999 $ #^ 1.04 % observed FP rate $ ./db_bench -db=/dev/shm/dbbench -use_existing_db -benchmarks=readrandom,stats -statistics -bloom_bits=10 -num=2000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false -optimize_filters_for_memory -duration=10 -cache_index_and_filter_blocks -cache_size=1000000000 rocksdb.block.cache.index.add COUNT : 33 rocksdb.block.cache.index.bytes.insert COUNT : 8448592 rocksdb.block.cache.filter.add COUNT : 33 rocksdb.block.cache.filter.bytes.insert COUNT : 18220328 rocksdb.bloom.filter.useful COUNT : 5360933 rocksdb.bloom.filter.full.positive COUNT : 1321315 rocksdb.bloom.filter.full.true.positive COUNT : 1262999 $ #^ 1.08 % observed FP rate, 13.6% less memory usage for filters (Due to specific key density, this example tends to generate filters that are "worse than average" for internal fragmentation. "Better than average" cases can show little or no improvement.) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6427 Test Plan: unit test added, 'make check' with gcc, clang and valgrind Reviewed By: siying Differential Revision: D22124374 Pulled By: pdillinger fbshipit-source-id: f3e3aa152f9043ddf4fae25799e76341d0d8714e
2020-06-22 22:30:57 +02:00
"optimize_filters_for_memory": lambda: random.randint(0, 1),
"partition_filters": lambda: random.randint(0, 1),
"partition_pinning": lambda: random.randint(0, 3),
"pause_background_one_in": 1000000,
"prefixpercent": 5,
"progress_reports": 0,
"readpercent": 45,
"recycle_log_file_num": lambda: random.randint(0, 1),
"reopen": 20,
"snapshot_hold_ops": 100000,
"sst_file_manager_bytes_per_sec": lambda: random.choice([0, 104857600]),
"sst_file_manager_bytes_per_truncate": lambda: random.choice([0, 1048576]),
"long_running_snapshots": lambda: random.randint(0, 1),
"subcompactions": lambda: random.randint(1, 4),
"target_file_size_base": 2097152,
"target_file_size_multiplier": 2,
"top_level_index_pinning": lambda: random.randint(0, 3),
"unpartitioned_pinning": lambda: random.randint(0, 3),
"use_direct_reads": lambda: random.randint(0, 1),
"use_direct_io_for_flush_and_compaction": lambda: random.randint(0, 1),
"mock_direct_io": False,
"use_full_merge_v1": lambda: random.randint(0, 1),
"use_merge": lambda: random.randint(0, 1),
"use_ribbon_filter": lambda: random.randint(0, 1),
"verify_checksum": 1,
"write_buffer_size": 4 * 1024 * 1024,
"writepercent": 35,
"format_version": lambda: random.choice([2, 3, 4, 5, 5]),
"index_block_restart_interval": lambda: random.choice(range(1, 16)),
"use_multiget" : lambda: random.randint(0, 1),
"periodic_compaction_seconds" :
lambda: random.choice([0, 0, 1, 2, 10, 100, 1000]),
"compaction_ttl" : lambda: random.choice([0, 0, 1, 2, 10, 100, 1000]),
# Test small max_manifest_file_size in a smaller chance, as most of the
# time we wnat manifest history to be preserved to help debug
"max_manifest_file_size" : lambda : random.choice(
[t * 16384 if t < 3 else 1024 * 1024 * 1024 for t in range(1, 30)]),
# Sync mode might make test runs slower so running it in a smaller chance
"sync" : lambda : random.choice(
[1 if t == 0 else 0 for t in range(0, 20)]),
# Disable compation_readahead_size because the test is not passing.
#"compaction_readahead_size" : lambda : random.choice(
# [0, 0, 1024 * 1024]),
"db_write_buffer_size" : lambda: random.choice(
[0, 0, 0, 1024 * 1024, 8 * 1024 * 1024, 128 * 1024 * 1024]),
"avoid_unnecessary_blocking_io" : random.randint(0, 1),
"write_dbid_to_manifest" : random.randint(0, 1),
"avoid_flush_during_recovery" : random.choice(
[1 if t == 0 else 0 for t in range(0, 8)]),
"max_write_batch_group_size_bytes" : lambda: random.choice(
[16, 64, 1024 * 1024, 16 * 1024 * 1024]),
"level_compaction_dynamic_level_bytes" : True,
"verify_checksum_one_in": 1000000,
"verify_db_one_in": 100000,
"continuous_verification_interval" : 0,
"max_key_len": 3,
"key_len_percent_dist": "1,30,69",
"read_fault_one_in": lambda: random.choice([0, 1000]),
"open_metadata_write_fault_one_in": lambda: random.choice([0, 8]),
"sync_fault_injection": False,
"get_property_one_in": 1000000,
"paranoid_file_checks": lambda: random.choice([0, 1, 1, 1]),
"max_write_buffer_size_to_maintain": lambda: random.choice(
[0, 1024 * 1024, 2 * 1024 * 1024, 4 * 1024 * 1024, 8 * 1024 * 1024]),
"user_timestamp_size": 0,
}
_TEST_DIR_ENV_VAR = 'TEST_TMPDIR'
_DEBUG_LEVEL_ENV_VAR = 'DEBUG_LEVEL'
def is_release_mode():
return os.environ.get(_DEBUG_LEVEL_ENV_VAR) == "0"
def get_dbname(test_name):
test_dir_name = "rocksdb_crashtest_" + test_name
test_tmpdir = os.environ.get(_TEST_DIR_ENV_VAR)
if test_tmpdir is None or test_tmpdir == "":
dbname = tempfile.mkdtemp(prefix=test_dir_name)
else:
dbname = test_tmpdir + "/" + test_dir_name
shutil.rmtree(dbname, True)
os.mkdir(dbname)
return dbname
expected_values_file = None
def setup_expected_values_file():
global expected_values_file
if expected_values_file is not None:
return expected_values_file
expected_file_name = "rocksdb_crashtest_" + "expected"
test_tmpdir = os.environ.get(_TEST_DIR_ENV_VAR)
if test_tmpdir is None or test_tmpdir == "":
expected_values_file = tempfile.NamedTemporaryFile(
prefix=expected_file_name, delete=False).name
else:
# if tmpdir is specified, store the expected_values_file in the same dir
expected_values_file = test_tmpdir + "/" + expected_file_name
if os.path.exists(expected_values_file):
os.remove(expected_values_file)
open(expected_values_file, 'a').close()
return expected_values_file
def is_direct_io_supported(dbname):
with tempfile.NamedTemporaryFile(dir=dbname) as f:
try:
os.open(f.name, os.O_DIRECT)
except BaseException:
return False
return True
blackbox_default_params = {
# total time for this script to test db_stress
"duration": 6000,
# time for one db_stress instance to run
"interval": 120,
# since we will be killing anyway, use large value for ops_per_thread
"ops_per_thread": 100000000,
"set_options_one_in": 10000,
"test_batches_snapshots": 1,
}
whitebox_default_params = {
"duration": 10000,
"log2_keys_per_lock": 10,
"ops_per_thread": 200000,
"random_kill_odd": 888887,
"test_batches_snapshots": lambda: random.randint(0, 1),
}
simple_default_params = {
"allow_concurrent_memtable_write": lambda: random.randint(0, 1),
"column_families": 1,
"max_background_compactions": 1,
"max_bytes_for_level_base": 67108864,
"memtablerep": "skip_list",
"prefixpercent": 0,
"readpercent": 50,
"prefix_size" : -1,
"target_file_size_base": 16777216,
"target_file_size_multiplier": 1,
"test_batches_snapshots": 0,
"write_buffer_size": 32 * 1024 * 1024,
"level_compaction_dynamic_level_bytes": False,
"paranoid_file_checks": lambda: random.choice([0, 1, 1, 1]),
}
blackbox_simple_default_params = {
"open_files": -1,
"set_options_one_in": 0,
}
whitebox_simple_default_params = {}
cf_consistency_params = {
"disable_wal": lambda: random.randint(0, 1),
"reopen": 0,
"test_cf_consistency": 1,
# use small value for write_buffer_size so that RocksDB triggers flush
# more frequently
"write_buffer_size": 1024 * 1024,
"enable_pipelined_write": lambda: random.randint(0, 1),
# Snapshots are used heavily in this test mode, while they are incompatible
# with compaction filter.
"enable_compaction_filter": 0,
}
txn_params = {
"use_txn" : 1,
# Avoid lambda to set it once for the entire test
"txn_write_policy": random.randint(0, 2),
"unordered_write": random.randint(0, 1),
"disable_wal": 0,
# OpenReadOnly after checkpoint is not currnetly compatible with WritePrepared txns
"checkpoint_one_in": 0,
# pipeline write is not currnetly compatible with WritePrepared txns
"enable_pipelined_write": 0,
}
best_efforts_recovery_params = {
"best_efforts_recovery": True,
"skip_verifydb": True,
"verify_db_one_in": 0,
"continuous_verification_interval": 0,
}
blob_params = {
"allow_setting_blob_options_dynamically": 1,
# Enable blob files and GC with a 75% chance initially; note that they might still be
# enabled/disabled during the test via SetOptions
"enable_blob_files": lambda: random.choice([0] + [1] * 3),
"min_blob_size": lambda: random.choice([0, 8, 16]),
"blob_file_size": lambda: random.choice([1048576, 16777216, 268435456, 1073741824]),
"blob_compression_type": lambda: random.choice(["none", "snappy", "lz4", "zstd"]),
"enable_blob_garbage_collection": lambda: random.choice([0] + [1] * 3),
"blob_garbage_collection_age_cutoff": lambda: random.choice([0.0, 0.25, 0.5, 0.75, 1.0]),
# The following are currently incompatible with the integrated BlobDB
"use_merge": 0,
}
ts_params = {
"test_cf_consistency": 0,
"test_batches_snapshots": 0,
"user_timestamp_size": 8,
"use_merge": 0,
"use_full_merge_v1": 0,
# In order to disable SingleDelete
"nooverwritepercent": 0,
"use_txn": 0,
"read_only": 0,
"secondary_catch_up_one_in": 0,
"continuous_verification_interval": 0,
"checkpoint_one_in": 0,
"enable_blob_files": 0,
"use_blob_db": 0,
"enable_compaction_filter": 0,
"ingest_external_file_one_in": 0,
}
def finalize_and_sanitize(src_params):
dest_params = dict([(k, v() if callable(v) else v)
for (k, v) in src_params.items()])
Limit buffering for collecting samples for compression dictionary (#7970) Summary: For dictionary compression, we need to collect some representative samples of the data to be compressed, which we use to either generate or train (when `CompressionOptions::zstd_max_train_bytes > 0`) a dictionary. Previously, the strategy was to buffer all the data blocks during flush, and up to the target file size during compaction. That strategy allowed us to randomly pick samples from as wide a range as possible that'd be guaranteed to land in a single output file. However, some users try to make huge files in memory-constrained environments, where this strategy can cause OOM. This PR introduces an option, `CompressionOptions::max_dict_buffer_bytes`, that limits how much data blocks are buffered before we switch to unbuffered mode (which means creating the per-SST dictionary, writing out the buffered data, and compressing/writing new blocks as soon as they are built). It is not strict as we currently buffer more than just data blocks -- also keys are buffered. But it does make a step towards giving users predictable memory usage. Related changes include: - Changed sampling for dictionary compression to select unique data blocks when there is limited availability of data blocks - Made use of `BlockBuilder::SwapAndReset()` to save an allocation+memcpy when buffering data blocks for building a dictionary - Changed `ParseBoolean()` to accept an input containing characters after the boolean. This is necessary since, with this PR, a value for `CompressionOptions::enabled` is no longer necessarily the final component in the `CompressionOptions` string. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7970 Test Plan: - updated `CompressionOptions` unit tests to verify limit is respected (to the extent expected in the current implementation) in various scenarios of flush/compaction to bottommost/non-bottommost level - looked at jemalloc heap profiles right before and after switching to unbuffered mode during flush/compaction. Verified memory usage in buffering is proportional to the limit set. Reviewed By: pdillinger Differential Revision: D26467994 Pulled By: ajkr fbshipit-source-id: 3da4ef9fba59974e4ef40e40c01611002c861465
2021-02-19 23:06:59 +01:00
if dest_params.get("compression_max_dict_bytes") == 0:
dest_params["compression_zstd_max_train_bytes"] = 0
dest_params["compression_max_dict_buffer_bytes"] = 0
if dest_params.get("compression_type") != "zstd":
dest_params["compression_zstd_max_train_bytes"] = 0
if dest_params.get("allow_concurrent_memtable_write", 1) == 1:
dest_params["memtablerep"] = "skip_list"
if dest_params["mmap_read"] == 1:
dest_params["use_direct_io_for_flush_and_compaction"] = 0
dest_params["use_direct_reads"] = 0
if (dest_params["use_direct_io_for_flush_and_compaction"] == 1
or dest_params["use_direct_reads"] == 1) and \
not is_direct_io_supported(dest_params["db"]):
if is_release_mode():
print("{} does not support direct IO. Disabling use_direct_reads and "
"use_direct_io_for_flush_and_compaction.\n".format(
dest_params["db"]))
dest_params["use_direct_reads"] = 0
dest_params["use_direct_io_for_flush_and_compaction"] = 0
else:
dest_params["mock_direct_io"] = True
# DeleteRange is not currnetly compatible with Txns and timestamp
if (dest_params.get("test_batches_snapshots") == 1 or
dest_params.get("use_txn") == 1 or
dest_params.get("user_timestamp_size") > 0):
dest_params["delpercent"] += dest_params["delrangepercent"]
dest_params["delrangepercent"] = 0
# Only under WritePrepared txns, unordered_write would provide the same guarnatees as vanilla rocksdb
if dest_params.get("unordered_write", 0) == 1:
dest_params["txn_write_policy"] = 1
dest_params["allow_concurrent_memtable_write"] = 1
if dest_params.get("disable_wal", 0) == 1:
dest_params["atomic_flush"] = 1
dest_params["sync"] = 0
dest_params["write_fault_one_in"] = 0
if dest_params.get("open_files", 1) != -1:
# Compaction TTL and periodic compactions are only compatible
# with open_files = -1
dest_params["compaction_ttl"] = 0
dest_params["periodic_compaction_seconds"] = 0
if dest_params.get("compaction_style", 0) == 2:
# Disable compaction TTL in FIFO compaction, because right
# now assertion failures are triggered.
dest_params["compaction_ttl"] = 0
dest_params["periodic_compaction_seconds"] = 0
if dest_params["partition_filters"] == 1:
if dest_params["index_type"] != 2:
dest_params["partition_filters"] = 0
else:
dest_params["use_block_based_filter"] = 0
if dest_params.get("atomic_flush", 0) == 1:
# disable pipelined write when atomic flush is used.
dest_params["enable_pipelined_write"] = 0
if dest_params.get("sst_file_manager_bytes_per_sec", 0) == 0:
dest_params["sst_file_manager_bytes_per_truncate"] = 0
if dest_params.get("enable_compaction_filter", 0) == 1:
# Compaction filter is incompatible with snapshots. Need to avoid taking
# snapshots, as well as avoid operations that use snapshots for
# verification.
dest_params["acquire_snapshot_one_in"] = 0
dest_params["compact_range_one_in"] = 0
# Give the iterator ops away to reads.
dest_params["readpercent"] += dest_params.get("iterpercent", 10)
dest_params["iterpercent"] = 0
dest_params["test_batches_snapshots"] = 0
Integrity protection for live updates to WriteBatch (#7748) Summary: This PR adds the foundation classes for key-value integrity protection and the first use case: protecting live updates from the source buffers added to `WriteBatch` through the destination buffer in `MemTable`. The width of the protection info is not yet configurable -- only eight bytes per key is supported. This PR allows users to enable protection by constructing `WriteBatch` with `protection_bytes_per_key == 8`. It does not yet expose a way for users to get integrity protection via other write APIs (e.g., `Put()`, `Merge()`, `Delete()`, etc.). The foundation classes (`ProtectionInfo.*`) embed the coverage info in their type, and provide `Protect.*()` and `Strip.*()` functions to navigate between types with different coverage. For making bytes per key configurable (for powers of two up to eight) in the future, these classes are templated on the unsigned integer type used to store the protection info. That integer contains the XOR'd result of hashes with independent seeds for all covered fields. For integer fields, the hash is computed on the raw unadjusted bytes, so the result is endian-dependent. The most significant bytes are truncated when the hash value (8 bytes) is wider than the protection integer. When `WriteBatch` is constructed with `protection_bytes_per_key == 8`, we hold a `ProtectionInfoKVOTC` (i.e., one that covers key, value, optype aka `ValueType`, timestamp, and CF ID) for each entry added to the batch. The protection info is generated from the original buffers passed by the user, as well as the original metadata generated internally. When writing to memtable, each entry is transformed to a `ProtectionInfoKVOTS` (i.e., dropping coverage of CF ID and adding coverage of sequence number), since at that point we know the sequence number, and have already selected a memtable corresponding to a particular CF. This protection info is verified once the entry is encoded in the `MemTable` buffer. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7748 Test Plan: - an integration test to verify a wide variety of single-byte changes to the encoded `MemTable` buffer are caught - add to stress/crash test to verify it works in variety of configs/operations without intentional corruption - [deferred] unit tests for `ProtectionInfo.*` classes for edge cases like KV swap, `SliceParts` and `Slice` APIs are interchangeable, etc. Reviewed By: pdillinger Differential Revision: D25754492 Pulled By: ajkr fbshipit-source-id: e481bac6c03c2ab268be41359730f1ceb9964866
2021-01-29 21:17:17 +01:00
if dest_params.get("test_batches_snapshots") == 0:
dest_params["batch_protection_bytes_per_key"] = 0
return dest_params
def gen_cmd_params(args):
params = {}
params.update(default_params)
if args.test_type == 'blackbox':
params.update(blackbox_default_params)
if args.test_type == 'whitebox':
params.update(whitebox_default_params)
if args.simple:
params.update(simple_default_params)
if args.test_type == 'blackbox':
params.update(blackbox_simple_default_params)
if args.test_type == 'whitebox':
params.update(whitebox_simple_default_params)
if args.cf_consistency:
params.update(cf_consistency_params)
if args.txn:
params.update(txn_params)
if args.test_best_efforts_recovery:
params.update(best_efforts_recovery_params)
if args.enable_ts:
params.update(ts_params)
# Best-effort recovery and BlobDB are currently incompatible. Test BE recovery
# if specified on the command line; otherwise, apply BlobDB related overrides
# with a 10% chance.
if (not args.test_best_efforts_recovery and
not args.enable_ts and
random.choice([0] * 9 + [1]) == 1):
params.update(blob_params)
for k, v in vars(args).items():
if v is not None:
params[k] = v
return params
def gen_cmd(params, unknown_params):
finalzied_params = finalize_and_sanitize(params)
cmd = ['./db_stress'] + [
'--{0}={1}'.format(k, v)
for k, v in [(k, finalzied_params[k]) for k in sorted(finalzied_params)]
if k not in set(['test_type', 'simple', 'duration', 'interval',
'random_kill_odd', 'cf_consistency', 'txn',
'test_best_efforts_recovery', 'enable_ts'])
and v is not None] + unknown_params
return cmd
# Inject inconsistency to db directory.
def inject_inconsistencies_to_db_dir(dir_path):
files = os.listdir(dir_path)
file_num_rgx = re.compile(r'(?P<number>[0-9]{6})')
largest_fnum = 0
for f in files:
m = file_num_rgx.search(f)
if m and not f.startswith('LOG'):
largest_fnum = max(largest_fnum, int(m.group('number')))
candidates = [
f for f in files if re.search(r'[0-9]+\.sst', f)
]
deleted = 0
corrupted = 0
for f in candidates:
rnd = random.randint(0, 99)
f_path = os.path.join(dir_path, f)
if rnd < 10:
os.unlink(f_path)
deleted = deleted + 1
elif 10 <= rnd and rnd < 30:
with open(f_path, "a") as fd:
fd.write('12345678')
corrupted = corrupted + 1
print('Removed %d table files' % deleted)
print('Corrupted %d table files' % corrupted)
# Add corrupted MANIFEST and SST
for num in range(largest_fnum + 1, largest_fnum + 10):
rnd = random.randint(0, 1)
fname = ("MANIFEST-%06d" % num) if rnd == 0 else ("%06d.sst" % num)
print('Write %s' % fname)
with open(os.path.join(dir_path, fname), "w") as fd:
fd.write("garbage")
# This script runs and kills db_stress multiple times. It checks consistency
# in case of unsafe crashes in RocksDB.
def blackbox_crash_main(args, unknown_args):
cmd_params = gen_cmd_params(args)
dbname = get_dbname('blackbox')
exit_time = time.time() + cmd_params['duration']
print("Running blackbox-crash-test with \n"
+ "interval_between_crash=" + str(cmd_params['interval']) + "\n"
+ "total-duration=" + str(cmd_params['duration']) + "\n")
while time.time() < exit_time:
run_had_errors = False
killtime = time.time() + cmd_params['interval']
cmd = gen_cmd(dict(
list(cmd_params.items())
+ list({'db': dbname}.items())), unknown_args)
child = subprocess.Popen(cmd, stderr=subprocess.PIPE)
print("Running db_stress with pid=%d: %s\n\n"
% (child.pid, ' '.join(cmd)))
stop_early = False
while time.time() < killtime:
if child.poll() is not None:
print("WARNING: db_stress ended before kill: exitcode=%d\n"
% child.returncode)
stop_early = True
break
time.sleep(1)
if not stop_early:
if child.poll() is not None:
print("WARNING: db_stress ended before kill: exitcode=%d\n"
% child.returncode)
else:
child.kill()
print("KILLED %d\n" % child.pid)
time.sleep(1) # time to stabilize after a kill
while True:
line = child.stderr.readline().strip().decode('utf-8')
if line == '':
break
elif not line.startswith('WARNING'):
run_had_errors = True
print('stderr has error message:')
print('***' + line + '***')
if run_had_errors:
sys.exit(2)
time.sleep(1) # time to stabilize before the next run
if args.test_best_efforts_recovery:
inject_inconsistencies_to_db_dir(dbname)
time.sleep(1) # time to stabilize before the next run
# we need to clean up after ourselves -- only do this on test success
shutil.rmtree(dbname, True)
# This python script runs db_stress multiple times. Some runs with
# kill_random_test that causes rocksdb to crash at various points in code.
def whitebox_crash_main(args, unknown_args):
cmd_params = gen_cmd_params(args)
dbname = get_dbname('whitebox')
cur_time = time.time()
exit_time = cur_time + cmd_params['duration']
half_time = cur_time + cmd_params['duration'] // 2
print("Running whitebox-crash-test with \n"
+ "total-duration=" + str(cmd_params['duration']) + "\n")
total_check_mode = 4
check_mode = 0
kill_random_test = cmd_params['random_kill_odd']
kill_mode = 0
while time.time() < exit_time:
if check_mode == 0:
additional_opts = {
# use large ops per thread since we will kill it anyway
"ops_per_thread": 100 * cmd_params['ops_per_thread'],
}
# run with kill_random_test, with three modes.
# Mode 0 covers all kill points. Mode 1 covers less kill points but
# increases change of triggering them. Mode 2 covers even less
# frequent kill points and further increases triggering change.
if kill_mode == 0:
additional_opts.update({
"kill_random_test": kill_random_test,
})
elif kill_mode == 1:
if cmd_params.get('disable_wal', 0) == 1:
my_kill_odd = kill_random_test // 50 + 1
else:
my_kill_odd = kill_random_test // 10 + 1
additional_opts.update({
"kill_random_test": my_kill_odd,
"kill_exclude_prefixes": "WritableFileWriter::Append,"
+ "WritableFileWriter::WriteBuffered",
})
elif kill_mode == 2:
# TODO: May need to adjust random odds if kill_random_test
# is too small.
additional_opts.update({
"kill_random_test": (kill_random_test // 5000 + 1),
"kill_exclude_prefixes": "WritableFileWriter::Append,"
"WritableFileWriter::WriteBuffered,"
"PosixMmapFile::Allocate,WritableFileWriter::Flush",
})
# Run kill mode 0, 1 and 2 by turn.
kill_mode = (kill_mode + 1) % 3
elif check_mode == 1:
# normal run with universal compaction mode
additional_opts = {
"kill_random_test": None,
"ops_per_thread": cmd_params['ops_per_thread'],
"compaction_style": 1,
}
# Single level universal has a lot of special logic. Ensure we cover
# it sometimes.
if random.randint(0, 1) == 1:
additional_opts.update({
"num_levels": 1,
})
elif check_mode == 2:
# normal run with FIFO compaction mode
# ops_per_thread is divided by 5 because FIFO compaction
# style is quite a bit slower on reads with lot of files
additional_opts = {
"kill_random_test": None,
"ops_per_thread": cmd_params['ops_per_thread'] // 5,
"compaction_style": 2,
}
else:
# normal run
additional_opts = {
"kill_random_test": None,
"ops_per_thread": cmd_params['ops_per_thread'],
}
cmd = gen_cmd(dict(list(cmd_params.items())
+ list(additional_opts.items())
+ list({'db': dbname}.items())), unknown_args)
print("Running:" + ' '.join(cmd) + "\n") # noqa: E999 T25377293 Grandfathered in
popen = subprocess.Popen(cmd, stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
stdoutdata, stderrdata = popen.communicate()
if stdoutdata:
stdoutdata = stdoutdata.decode('utf-8')
if stderrdata:
stderrdata = stderrdata.decode('utf-8')
retncode = popen.returncode
msg = ("check_mode={0}, kill option={1}, exitcode={2}\n".format(
check_mode, additional_opts['kill_random_test'], retncode))
print(msg)
print(stdoutdata)
expected = False
if additional_opts['kill_random_test'] is None and (retncode == 0):
# we expect zero retncode if no kill option
expected = True
elif additional_opts['kill_random_test'] is not None and retncode <= 0:
# When kill option is given, the test MIGHT kill itself.
# If it does, negative retncode is expected. Otherwise 0.
expected = True
if not expected:
print("TEST FAILED. See kill option and exit code above!!!\n")
sys.exit(1)
stdoutdata = stdoutdata.lower()
errorcount = (stdoutdata.count('error') -
stdoutdata.count('got errors 0 times'))
print("#times error occurred in output is " + str(errorcount) + "\n")
if (errorcount > 0):
print("TEST FAILED. Output has 'error'!!!\n")
sys.exit(2)
if (stdoutdata.find('fail') >= 0):
print("TEST FAILED. Output has 'fail'!!!\n")
sys.exit(2)
# First half of the duration, keep doing kill test. For the next half,
# try different modes.
if time.time() > half_time:
# we need to clean up after ourselves -- only do this on test
# success
shutil.rmtree(dbname, True)
os.mkdir(dbname)
cmd_params.pop('expected_values_path', None)
check_mode = (check_mode + 1) % total_check_mode
time.sleep(1) # time to stabilize after a kill
def main():
parser = argparse.ArgumentParser(description="This script runs and kills \
db_stress multiple times")
parser.add_argument("test_type", choices=["blackbox", "whitebox"])
parser.add_argument("--simple", action="store_true")
parser.add_argument("--cf_consistency", action='store_true')
parser.add_argument("--txn", action='store_true')
parser.add_argument("--test_best_efforts_recovery", action='store_true')
parser.add_argument("--enable_ts", action='store_true')
all_params = dict(list(default_params.items())
+ list(blackbox_default_params.items())
+ list(whitebox_default_params.items())
+ list(simple_default_params.items())
+ list(blackbox_simple_default_params.items())
+ list(whitebox_simple_default_params.items())
+ list(blob_params.items())
+ list(ts_params.items()))
for k, v in all_params.items():
parser.add_argument("--" + k, type=type(v() if callable(v) else v))
# unknown_args are passed directly to db_stress
args, unknown_args = parser.parse_known_args()
test_tmpdir = os.environ.get(_TEST_DIR_ENV_VAR)
if test_tmpdir is not None and not os.path.isdir(test_tmpdir):
print('%s env var is set to a non-existent directory: %s' %
(_TEST_DIR_ENV_VAR, test_tmpdir))
sys.exit(1)
if args.test_type == 'blackbox':
blackbox_crash_main(args, unknown_args)
if args.test_type == 'whitebox':
whitebox_crash_main(args, unknown_args)
# Only delete the `expected_values_file` if test passes
if os.path.exists(expected_values_file):
os.remove(expected_values_file)
if __name__ == '__main__':
main()