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.
rocksdb/db/db_statistics_test.cc

269 lines
9.5 KiB

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include <string>
#include "db/db_test_util.h"
#include "monitoring/thread_status_util.h"
#include "port/stack_trace.h"
#include "rocksdb/statistics.h"
#include "util/random.h"
namespace ROCKSDB_NAMESPACE {
class DBStatisticsTest : public DBTestBase {
public:
DBStatisticsTest()
: DBTestBase("db_statistics_test", /*env_do_fsync=*/true) {}
};
TEST_F(DBStatisticsTest, CompressionStatsTest) {
CompressionType type;
if (Snappy_Supported()) {
type = kSnappyCompression;
fprintf(stderr, "using snappy\n");
} else if (Zlib_Supported()) {
type = kZlibCompression;
fprintf(stderr, "using zlib\n");
} else if (BZip2_Supported()) {
type = kBZip2Compression;
fprintf(stderr, "using bzip2\n");
} else if (LZ4_Supported()) {
type = kLZ4Compression;
fprintf(stderr, "using lz4\n");
} else if (XPRESS_Supported()) {
type = kXpressCompression;
fprintf(stderr, "using xpress\n");
} else if (ZSTD_Supported()) {
type = kZSTD;
fprintf(stderr, "using ZSTD\n");
} else {
fprintf(stderr, "skipping test, compression disabled\n");
return;
}
Options options = CurrentOptions();
options.compression = type;
options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
options.statistics->set_stats_level(StatsLevel::kExceptTimeForMutex);
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
BlockBasedTableOptions bbto;
bbto.enable_index_compression = false;
options.table_factory.reset(NewBlockBasedTableFactory(bbto));
DestroyAndReopen(options);
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
auto PopStat = [&](Tickers t) -> uint64_t {
return options.statistics->getAndResetTickerCount(t);
};
int kNumKeysWritten = 100;
double compress_to = 0.5;
// About three KVs per block
int len = static_cast<int>(BlockBasedTableOptions().block_size / 3);
int uncomp_est = kNumKeysWritten * (len + 20);
Random rnd(301);
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
std::string buf;
// Check that compressions occur and are counted when compression is turned on
for (int i = 0; i < kNumKeysWritten; ++i) {
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
ASSERT_OK(
Put(Key(i), test::CompressibleString(&rnd, compress_to, len, &buf)));
}
ASSERT_OK(Flush());
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
EXPECT_EQ(34, PopStat(NUMBER_BLOCK_COMPRESSED));
EXPECT_NEAR2(uncomp_est, PopStat(BYTES_COMPRESSED_FROM), uncomp_est / 10);
EXPECT_NEAR2(uncomp_est * compress_to, PopStat(BYTES_COMPRESSED_TO),
uncomp_est / 10);
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_DECOMPRESSED));
EXPECT_EQ(0, PopStat(BYTES_DECOMPRESSED_FROM));
EXPECT_EQ(0, PopStat(BYTES_DECOMPRESSED_TO));
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
// And decompressions
for (int i = 0; i < kNumKeysWritten; ++i) {
auto r = Get(Key(i));
}
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
EXPECT_EQ(34, PopStat(NUMBER_BLOCK_DECOMPRESSED));
EXPECT_NEAR2(uncomp_est, PopStat(BYTES_DECOMPRESSED_TO), uncomp_est / 10);
EXPECT_NEAR2(uncomp_est * compress_to, PopStat(BYTES_DECOMPRESSED_FROM),
uncomp_est / 10);
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
EXPECT_EQ(0, PopStat(BYTES_COMPRESSION_BYPASSED));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSION_REJECTED));
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSION_BYPASSED));
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSION_REJECTED));
// Check when compression is rejected.
compress_to = 0.95;
DestroyAndReopen(options);
for (int i = 0; i < kNumKeysWritten; ++i) {
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
ASSERT_OK(
Put(Key(i), test::CompressibleString(&rnd, compress_to, len, &buf)));
}
ASSERT_OK(Flush());
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
for (int i = 0; i < kNumKeysWritten; ++i) {
auto r = Get(Key(i));
}
EXPECT_EQ(34, PopStat(NUMBER_BLOCK_COMPRESSION_REJECTED));
EXPECT_NEAR2(uncomp_est, PopStat(BYTES_COMPRESSION_REJECTED),
uncomp_est / 10);
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSED));
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSION_BYPASSED));
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_DECOMPRESSED));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSED_FROM));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSED_TO));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSION_BYPASSED));
EXPECT_EQ(0, PopStat(BYTES_DECOMPRESSED_FROM));
EXPECT_EQ(0, PopStat(BYTES_DECOMPRESSED_TO));
// Check when compression is disabled.
options.compression = kNoCompression;
DestroyAndReopen(options);
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
for (int i = 0; i < kNumKeysWritten; ++i) {
ASSERT_OK(
Put(Key(i), test::CompressibleString(&rnd, compress_to, len, &buf)));
}
ASSERT_OK(Flush());
for (int i = 0; i < kNumKeysWritten; ++i) {
auto r = Get(Key(i));
}
Changes and enhancements to compression stats, thresholds (#11388) Summary: ## Option API updates * Add new CompressionOptions::max_compressed_bytes_per_kb, which corresponds to 1024.0 / min allowable compression ratio. This avoids the hard-coded minimum ratio of 8/7. * Remove unnecessary constructor for CompressionOptions. * Document undocumented CompressionOptions. Use idiom for default values shown clearly in one place (not precariously repeated). ## Stat API updates * Deprecate the BYTES_COMPRESSED, BYTES_DECOMPRESSED histograms. Histograms incur substantial extra space & time costs compared to tickers, and the distribution of uncompressed data block sizes tends to be uninteresting. If we're interested in that distribution, I don't see why it should be limited to blocks stored as compressed. * Deprecate the NUMBER_BLOCK_NOT_COMPRESSED ticker, because the name is very confusing. * New or existing tickers relevant to compression: * BYTES_COMPRESSED_FROM * BYTES_COMPRESSED_TO * BYTES_COMPRESSION_BYPASSED * BYTES_COMPRESSION_REJECTED * COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES (both existing) * NUMBER_BLOCK_COMPRESSED (existing) * NUMBER_BLOCK_COMPRESSION_BYPASSED * NUMBER_BLOCK_COMPRESSION_REJECTED * BYTES_DECOMPRESSED_FROM * BYTES_DECOMPRESSED_TO We can compute a number of things with these stats: * "Successful" compression ratio: BYTES_COMPRESSED_FROM / BYTES_COMPRESSED_TO * Compression ratio of data on which compression was attempted: (BYTES_COMPRESSED_FROM + BYTES_COMPRESSION_REJECTED) / (BYTES_COMPRESSED_TO + BYTES_COMPRESSION_REJECTED) * Compression ratio of data that could be eligible for compression: (BYTES_COMPRESSED_FROM + X) / (BYTES_COMPRESSED_TO + X) where X = BYTES_COMPRESSION_REJECTED + NUMBER_BLOCK_COMPRESSION_REJECTED * Overall SST compression ratio (compression disabled vs. actual): (Y - BYTES_COMPRESSED_TO + BYTES_COMPRESSED_FROM) / Y where Y = COMPACT_WRITE_BYTES + FLUSH_WRITE_BYTES Keeping _REJECTED separate from _BYPASSED helps us to understand "wasted" CPU time in compression. ## BlockBasedTableBuilder Various small refactorings, optimizations, and name clean-ups. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11388 Test Plan: unit tests added * `options_settable_test.cc`: use non-deprecated idiom for configuring CompressionOptions from string. The old idiom is tested elsewhere and does not need to be updated to support the new field. Reviewed By: ajkr Differential Revision: D45128202 Pulled By: pdillinger fbshipit-source-id: 5a652bf5c022b7ec340cf79018cccf0686962803
2 years ago
EXPECT_EQ(34, PopStat(NUMBER_BLOCK_COMPRESSION_BYPASSED));
EXPECT_NEAR2(uncomp_est, PopStat(BYTES_COMPRESSION_BYPASSED),
uncomp_est / 10);
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSED));
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_COMPRESSION_REJECTED));
EXPECT_EQ(0, PopStat(NUMBER_BLOCK_DECOMPRESSED));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSED_FROM));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSED_TO));
EXPECT_EQ(0, PopStat(BYTES_COMPRESSION_REJECTED));
EXPECT_EQ(0, PopStat(BYTES_DECOMPRESSED_FROM));
EXPECT_EQ(0, PopStat(BYTES_DECOMPRESSED_TO));
}
TEST_F(DBStatisticsTest, MutexWaitStatsDisabledByDefault) {
Options options = CurrentOptions();
options.create_if_missing = true;
options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
CreateAndReopenWithCF({"pikachu"}, options);
const uint64_t kMutexWaitDelay = 100;
ThreadStatusUtil::TEST_SetStateDelay(ThreadStatus::STATE_MUTEX_WAIT,
kMutexWaitDelay);
ASSERT_OK(Put("hello", "rocksdb"));
ASSERT_EQ(TestGetTickerCount(options, DB_MUTEX_WAIT_MICROS), 0);
ThreadStatusUtil::TEST_SetStateDelay(ThreadStatus::STATE_MUTEX_WAIT, 0);
}
TEST_F(DBStatisticsTest, MutexWaitStats) {
Options options = CurrentOptions();
options.create_if_missing = true;
options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
options.statistics->set_stats_level(StatsLevel::kAll);
CreateAndReopenWithCF({"pikachu"}, options);
const uint64_t kMutexWaitDelay = 100;
ThreadStatusUtil::TEST_SetStateDelay(ThreadStatus::STATE_MUTEX_WAIT,
kMutexWaitDelay);
ASSERT_OK(Put("hello", "rocksdb"));
ASSERT_GE(TestGetTickerCount(options, DB_MUTEX_WAIT_MICROS), kMutexWaitDelay);
ThreadStatusUtil::TEST_SetStateDelay(ThreadStatus::STATE_MUTEX_WAIT, 0);
}
TEST_F(DBStatisticsTest, ResetStats) {
Options options = CurrentOptions();
options.create_if_missing = true;
options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
DestroyAndReopen(options);
for (int i = 0; i < 2; ++i) {
// pick arbitrary ticker and histogram. On first iteration they're zero
// because db is unused. On second iteration they're zero due to Reset().
ASSERT_EQ(0, TestGetTickerCount(options, NUMBER_KEYS_WRITTEN));
HistogramData histogram_data;
options.statistics->histogramData(DB_WRITE, &histogram_data);
ASSERT_EQ(0.0, histogram_data.max);
if (i == 0) {
// The Put() makes some of the ticker/histogram stats nonzero until we
// Reset().
ASSERT_OK(Put("hello", "rocksdb"));
ASSERT_EQ(1, TestGetTickerCount(options, NUMBER_KEYS_WRITTEN));
options.statistics->histogramData(DB_WRITE, &histogram_data);
ASSERT_GT(histogram_data.max, 0.0);
ASSERT_OK(options.statistics->Reset());
}
}
}
TEST_F(DBStatisticsTest, ExcludeTickers) {
Options options = CurrentOptions();
options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
DestroyAndReopen(options);
options.statistics->set_stats_level(StatsLevel::kExceptTickers);
ASSERT_OK(Put("foo", "value"));
ASSERT_EQ(0, options.statistics->getTickerCount(BYTES_WRITTEN));
options.statistics->set_stats_level(StatsLevel::kExceptHistogramOrTimers);
Reopen(options);
ASSERT_EQ("value", Get("foo"));
ASSERT_GT(options.statistics->getTickerCount(BYTES_READ), 0);
}
TEST_F(DBStatisticsTest, VerifyChecksumReadStat) {
Options options = CurrentOptions();
options.file_checksum_gen_factory = GetFileChecksumGenCrc32cFactory();
options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
Reopen(options);
// Expected to be populated regardless of `PerfLevel` in user thread
SetPerfLevel(kDisable);
{
// Scenario 0: only WAL data. Not verified so require ticker to be zero.
ASSERT_OK(Put("foo", "value"));
ASSERT_OK(db_->VerifyFileChecksums(ReadOptions()));
ASSERT_OK(db_->VerifyChecksum());
ASSERT_EQ(0,
options.statistics->getTickerCount(VERIFY_CHECKSUM_READ_BYTES));
}
// Create one SST.
ASSERT_OK(Flush());
std::unordered_map<std::string, uint64_t> table_files;
uint64_t table_files_size = 0;
GetAllDataFiles(kTableFile, &table_files, &table_files_size);
{
// Scenario 1: Table verified in `VerifyFileChecksums()`. This should read
// the whole file so we require the ticker stat exactly matches the file
// size.
ASSERT_OK(options.statistics->Reset());
ASSERT_OK(db_->VerifyFileChecksums(ReadOptions()));
ASSERT_EQ(table_files_size,
options.statistics->getTickerCount(VERIFY_CHECKSUM_READ_BYTES));
}
{
// Scenario 2: Table verified in `VerifyChecksum()`. This opens a
// `TableReader` to verify each block. It can involve duplicate reads of the
// same data so we set a lower-bound only.
ASSERT_OK(options.statistics->Reset());
ASSERT_OK(db_->VerifyChecksum());
ASSERT_GE(options.statistics->getTickerCount(VERIFY_CHECKSUM_READ_BYTES),
table_files_size);
}
}
} // namespace ROCKSDB_NAMESPACE
int main(int argc, char** argv) {
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}