diff options
author | Sanjay Ghemawat <sanjay@google.com> | 2012-04-17 08:36:46 -0700 |
---|---|---|
committer | Sanjay Ghemawat <sanjay@google.com> | 2012-04-17 08:36:46 -0700 |
commit | 85584d497e7b354853b72f450683d59fcf6b9c5c (patch) | |
tree | b6aad4f973f87487c3caa5600e7596219c79f645 /table/filter_block.cc | |
parent | bc1ee4d25e09b04e074db330a41f54ef4af0e31b (diff) | |
download | leveldb-85584d497e7b354853b72f450683d59fcf6b9c5c.tar.gz |
Added bloom filter support.v1.4
In particular, we add a new FilterPolicy class. An instance
of this class can be supplied in Options when opening a
database. If supplied, the instance is used to generate
summaries of keys (e.g., a bloom filter) which are placed in
sstables. These summaries are consulted by DB::Get() so we
can avoid reading sstable blocks that are guaranteed to not
contain the key we are looking for.
This change provides one implementation of FilterPolicy
based on bloom filters.
Other changes:
- Updated version number to 1.4.
- Some build tweaks.
- C binding for CompactRange.
- A few more benchmarks: deleteseq, deleterandom, readmissing, seekrandom.
- Minor .gitignore update.
Diffstat (limited to 'table/filter_block.cc')
-rw-r--r-- | table/filter_block.cc | 111 |
1 files changed, 111 insertions, 0 deletions
diff --git a/table/filter_block.cc b/table/filter_block.cc new file mode 100644 index 0000000..203e15c --- /dev/null +++ b/table/filter_block.cc @@ -0,0 +1,111 @@ +// Copyright (c) 2012 The LevelDB Authors. All rights reserved. +// Use of this source code is governed by a BSD-style license that can be +// found in the LICENSE file. See the AUTHORS file for names of contributors. + +#include "table/filter_block.h" + +#include "leveldb/filter_policy.h" +#include "util/coding.h" + +namespace leveldb { + +// See doc/table_format.txt for an explanation of the filter block format. + +// Generate new filter every 2KB of data +static const size_t kFilterBaseLg = 11; +static const size_t kFilterBase = 1 << kFilterBaseLg; + +FilterBlockBuilder::FilterBlockBuilder(const FilterPolicy* policy) + : policy_(policy) { +} + +void FilterBlockBuilder::StartBlock(uint64_t block_offset) { + uint64_t filter_index = (block_offset / kFilterBase); + assert(filter_index >= filter_offsets_.size()); + while (filter_index > filter_offsets_.size()) { + GenerateFilter(); + } +} + +void FilterBlockBuilder::AddKey(const Slice& key) { + Slice k = key; + start_.push_back(keys_.size()); + keys_.append(k.data(), k.size()); +} + +Slice FilterBlockBuilder::Finish() { + if (!start_.empty()) { + GenerateFilter(); + } + + // Append array of per-filter offsets + const uint32_t array_offset = result_.size(); + for (size_t i = 0; i < filter_offsets_.size(); i++) { + PutFixed32(&result_, filter_offsets_[i]); + } + + PutFixed32(&result_, array_offset); + result_.push_back(kFilterBaseLg); // Save encoding parameter in result + return Slice(result_); +} + +void FilterBlockBuilder::GenerateFilter() { + const size_t num_keys = start_.size(); + if (num_keys == 0) { + // Fast path if there are no keys for this filter + filter_offsets_.push_back(result_.size()); + return; + } + + // Make list of keys from flattened key structure + start_.push_back(keys_.size()); // Simplify length computation + tmp_keys_.resize(num_keys); + for (size_t i = 0; i < num_keys; i++) { + const char* base = keys_.data() + start_[i]; + size_t length = start_[i+1] - start_[i]; + tmp_keys_[i] = Slice(base, length); + } + + // Generate filter for current set of keys and append to result_. + filter_offsets_.push_back(result_.size()); + policy_->CreateFilter(&tmp_keys_[0], num_keys, &result_); + + tmp_keys_.clear(); + keys_.clear(); + start_.clear(); +} + +FilterBlockReader::FilterBlockReader(const FilterPolicy* policy, + const Slice& contents) + : policy_(policy), + data_(NULL), + offset_(NULL), + num_(0), + base_lg_(0) { + size_t n = contents.size(); + if (n < 5) return; // 1 byte for base_lg_ and 4 for start of offset array + base_lg_ = contents[n-1]; + uint32_t last_word = DecodeFixed32(contents.data() + n - 5); + if (last_word > n - 5) return; + data_ = contents.data(); + offset_ = data_ + last_word; + num_ = (n - 5 - last_word) / 4; +} + +bool FilterBlockReader::KeyMayMatch(uint64_t block_offset, const Slice& key) { + uint64_t index = block_offset >> base_lg_; + if (index < num_) { + uint32_t start = DecodeFixed32(offset_ + index*4); + uint32_t limit = DecodeFixed32(offset_ + index*4 + 4); + if (start <= limit && limit <= (offset_ - data_)) { + Slice filter = Slice(data_ + start, limit - start); + return policy_->KeyMayMatch(key, filter); + } else if (start == limit) { + // Empty filters do not match any keys + return false; + } + } + return true; // Errors are treated as potential matches +} + +} |