diff options
Diffstat (limited to 'api/leveldb/util')
-rw-r--r-- | api/leveldb/util/arena.h | 68 | ||||
-rw-r--r-- | api/leveldb/util/coding.cc | 194 | ||||
-rw-r--r-- | api/leveldb/util/coding.h | 104 | ||||
-rw-r--r-- | api/leveldb/util/comparator.cc | 80 | ||||
-rw-r--r-- | api/leveldb/util/env.cc | 96 | ||||
-rw-r--r-- | api/leveldb/util/env_posix.cc | 617 | ||||
-rw-r--r-- | api/leveldb/util/logging.cc | 80 | ||||
-rw-r--r-- | api/leveldb/util/logging.h | 47 | ||||
-rw-r--r-- | api/leveldb/util/options.cc | 29 | ||||
-rw-r--r-- | api/leveldb/util/posix_logger.h | 98 | ||||
-rw-r--r-- | api/leveldb/util/random.h | 72 | ||||
-rw-r--r-- | api/leveldb/util/status.cc | 74 |
12 files changed, 1559 insertions, 0 deletions
diff --git a/api/leveldb/util/arena.h b/api/leveldb/util/arena.h new file mode 100644 index 00000000000..8f7dde226c4 --- /dev/null +++ b/api/leveldb/util/arena.h @@ -0,0 +1,68 @@ +// Copyright (c) 2011 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. + +#ifndef STORAGE_LEVELDB_UTIL_ARENA_H_ +#define STORAGE_LEVELDB_UTIL_ARENA_H_ + +#include <cstddef> +#include <vector> +#include <assert.h> +#include <stdint.h> + +namespace leveldb { + +class Arena { + public: + Arena(); + ~Arena(); + + // Return a pointer to a newly allocated memory block of "bytes" bytes. + char* Allocate(size_t bytes); + + // Allocate memory with the normal alignment guarantees provided by malloc + char* AllocateAligned(size_t bytes); + + // Returns an estimate of the total memory usage of data allocated + // by the arena (including space allocated but not yet used for user + // allocations). + size_t MemoryUsage() const { + return blocks_memory_ + blocks_.capacity() * sizeof(char*); + } + + private: + char* AllocateFallback(size_t bytes); + char* AllocateNewBlock(size_t block_bytes); + + // Allocation state + char* alloc_ptr_; + size_t alloc_bytes_remaining_; + + // Array of new[] allocated memory blocks + std::vector<char*> blocks_; + + // Bytes of memory in blocks allocated so far + size_t blocks_memory_; + + // No copying allowed + Arena(const Arena&); + void operator=(const Arena&); +}; + +inline char* Arena::Allocate(size_t bytes) { + // The semantics of what to return are a bit messy if we allow + // 0-byte allocations, so we disallow them here (we don't need + // them for our internal use). + assert(bytes > 0); + if (bytes <= alloc_bytes_remaining_) { + char* result = alloc_ptr_; + alloc_ptr_ += bytes; + alloc_bytes_remaining_ -= bytes; + return result; + } + return AllocateFallback(bytes); +} + +} // namespace leveldb + +#endif // STORAGE_LEVELDB_UTIL_ARENA_H_ diff --git a/api/leveldb/util/coding.cc b/api/leveldb/util/coding.cc new file mode 100644 index 00000000000..dbd7a6545c6 --- /dev/null +++ b/api/leveldb/util/coding.cc @@ -0,0 +1,194 @@ +// Copyright (c) 2011 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 "util/coding.h" + +namespace leveldb { + +void EncodeFixed32(char* buf, uint32_t value) { +#if __BYTE_ORDER == __LITTLE_ENDIAN + memcpy(buf, &value, sizeof(value)); +#else + buf[0] = value & 0xff; + buf[1] = (value >> 8) & 0xff; + buf[2] = (value >> 16) & 0xff; + buf[3] = (value >> 24) & 0xff; +#endif +} + +void EncodeFixed64(char* buf, uint64_t value) { +#if __BYTE_ORDER == __LITTLE_ENDIAN + memcpy(buf, &value, sizeof(value)); +#else + buf[0] = value & 0xff; + buf[1] = (value >> 8) & 0xff; + buf[2] = (value >> 16) & 0xff; + buf[3] = (value >> 24) & 0xff; + buf[4] = (value >> 32) & 0xff; + buf[5] = (value >> 40) & 0xff; + buf[6] = (value >> 48) & 0xff; + buf[7] = (value >> 56) & 0xff; +#endif +} + +void PutFixed32(std::string* dst, uint32_t value) { + char buf[sizeof(value)]; + EncodeFixed32(buf, value); + dst->append(buf, sizeof(buf)); +} + +void PutFixed64(std::string* dst, uint64_t value) { + char buf[sizeof(value)]; + EncodeFixed64(buf, value); + dst->append(buf, sizeof(buf)); +} + +char* EncodeVarint32(char* dst, uint32_t v) { + // Operate on characters as unsigneds + unsigned char* ptr = reinterpret_cast<unsigned char*>(dst); + static const int B = 128; + if (v < (1<<7)) { + *(ptr++) = v; + } else if (v < (1<<14)) { + *(ptr++) = v | B; + *(ptr++) = v>>7; + } else if (v < (1<<21)) { + *(ptr++) = v | B; + *(ptr++) = (v>>7) | B; + *(ptr++) = v>>14; + } else if (v < (1<<28)) { + *(ptr++) = v | B; + *(ptr++) = (v>>7) | B; + *(ptr++) = (v>>14) | B; + *(ptr++) = v>>21; + } else { + *(ptr++) = v | B; + *(ptr++) = (v>>7) | B; + *(ptr++) = (v>>14) | B; + *(ptr++) = (v>>21) | B; + *(ptr++) = v>>28; + } + return reinterpret_cast<char*>(ptr); +} + +void PutVarint32(std::string* dst, uint32_t v) { + char buf[5]; + char* ptr = EncodeVarint32(buf, v); + dst->append(buf, ptr - buf); +} + +char* EncodeVarint64(char* dst, uint64_t v) { + static const int B = 128; + unsigned char* ptr = reinterpret_cast<unsigned char*>(dst); + while (v >= B) { + *(ptr++) = (v & (B-1)) | B; + v >>= 7; + } + *(ptr++) = static_cast<unsigned char>(v); + return reinterpret_cast<char*>(ptr); +} + +void PutVarint64(std::string* dst, uint64_t v) { + char buf[10]; + char* ptr = EncodeVarint64(buf, v); + dst->append(buf, ptr - buf); +} + +void PutLengthPrefixedSlice(std::string* dst, const Slice& value) { + PutVarint32(dst, value.size()); + dst->append(value.data(), value.size()); +} + +int VarintLength(uint64_t v) { + int len = 1; + while (v >= 128) { + v >>= 7; + len++; + } + return len; +} + +const char* GetVarint32PtrFallback(const char* p, + const char* limit, + uint32_t* value) { + uint32_t result = 0; + for (uint32_t shift = 0; shift <= 28 && p < limit; shift += 7) { + uint32_t byte = *(reinterpret_cast<const unsigned char*>(p)); + p++; + if (byte & 128) { + // More bytes are present + result |= ((byte & 127) << shift); + } else { + result |= (byte << shift); + *value = result; + return reinterpret_cast<const char*>(p); + } + } + return NULL; +} + +bool GetVarint32(Slice* input, uint32_t* value) { + const char* p = input->data(); + const char* limit = p + input->size(); + const char* q = GetVarint32Ptr(p, limit, value); + if (q == NULL) { + return false; + } else { + *input = Slice(q, limit - q); + return true; + } +} + +const char* GetVarint64Ptr(const char* p, const char* limit, uint64_t* value) { + uint64_t result = 0; + for (uint32_t shift = 0; shift <= 63 && p < limit; shift += 7) { + uint64_t byte = *(reinterpret_cast<const unsigned char*>(p)); + p++; + if (byte & 128) { + // More bytes are present + result |= ((byte & 127) << shift); + } else { + result |= (byte << shift); + *value = result; + return reinterpret_cast<const char*>(p); + } + } + return NULL; +} + +bool GetVarint64(Slice* input, uint64_t* value) { + const char* p = input->data(); + const char* limit = p + input->size(); + const char* q = GetVarint64Ptr(p, limit, value); + if (q == NULL) { + return false; + } else { + *input = Slice(q, limit - q); + return true; + } +} + +const char* GetLengthPrefixedSlice(const char* p, const char* limit, + Slice* result) { + uint32_t len; + p = GetVarint32Ptr(p, limit, &len); + if (p == NULL) return NULL; + if (p + len > limit) return NULL; + *result = Slice(p, len); + return p + len; +} + +bool GetLengthPrefixedSlice(Slice* input, Slice* result) { + uint32_t len; + if (GetVarint32(input, &len) && + input->size() >= len) { + *result = Slice(input->data(), len); + input->remove_prefix(len); + return true; + } else { + return false; + } +} + +} // namespace leveldb diff --git a/api/leveldb/util/coding.h b/api/leveldb/util/coding.h new file mode 100644 index 00000000000..cba97ec421a --- /dev/null +++ b/api/leveldb/util/coding.h @@ -0,0 +1,104 @@ +// Copyright (c) 2011 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. +// +// Endian-neutral encoding: +// * Fixed-length numbers are encoded with least-significant byte first +// * In addition we support variable length "varint" encoding +// * Strings are encoded prefixed by their length in varint format + +#ifndef STORAGE_LEVELDB_UTIL_CODING_H_ +#define STORAGE_LEVELDB_UTIL_CODING_H_ + +#include <stdint.h> +#include <string.h> +#include <string> +#include "leveldb_wt.h" +#include "port/port.h" + +namespace leveldb { + +// Standard Put... routines append to a string +extern void PutFixed32(std::string* dst, uint32_t value); +extern void PutFixed64(std::string* dst, uint64_t value); +extern void PutVarint32(std::string* dst, uint32_t value); +extern void PutVarint64(std::string* dst, uint64_t value); +extern void PutLengthPrefixedSlice(std::string* dst, const Slice& value); + +// Standard Get... routines parse a value from the beginning of a Slice +// and advance the slice past the parsed value. +extern bool GetVarint32(Slice* input, uint32_t* value); +extern bool GetVarint64(Slice* input, uint64_t* value); +extern bool GetLengthPrefixedSlice(Slice* input, Slice* result); + +// Pointer-based variants of GetVarint... These either store a value +// in *v and return a pointer just past the parsed value, or return +// NULL on error. These routines only look at bytes in the range +// [p..limit-1] +extern const char* GetVarint32Ptr(const char* p,const char* limit, uint32_t* v); +extern const char* GetVarint64Ptr(const char* p,const char* limit, uint64_t* v); + +// Returns the length of the varint32 or varint64 encoding of "v" +extern int VarintLength(uint64_t v); + +// Lower-level versions of Put... that write directly into a character buffer +// REQUIRES: dst has enough space for the value being written +extern void EncodeFixed32(char* dst, uint32_t value); +extern void EncodeFixed64(char* dst, uint64_t value); + +// Lower-level versions of Put... that write directly into a character buffer +// and return a pointer just past the last byte written. +// REQUIRES: dst has enough space for the value being written +extern char* EncodeVarint32(char* dst, uint32_t value); +extern char* EncodeVarint64(char* dst, uint64_t value); + +// Lower-level versions of Get... that read directly from a character buffer +// without any bounds checking. + +inline uint32_t DecodeFixed32(const char* ptr) { + if (port::kLittleEndian) { + // Load the raw bytes + uint32_t result; + memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load + return result; + } else { + return ((static_cast<uint32_t>(static_cast<unsigned char>(ptr[0]))) + | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[1])) << 8) + | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[2])) << 16) + | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[3])) << 24)); + } +} + +inline uint64_t DecodeFixed64(const char* ptr) { + if (port::kLittleEndian) { + // Load the raw bytes + uint64_t result; + memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load + return result; + } else { + uint64_t lo = DecodeFixed32(ptr); + uint64_t hi = DecodeFixed32(ptr + 4); + return (hi << 32) | lo; + } +} + +// Internal routine for use by fallback path of GetVarint32Ptr +extern const char* GetVarint32PtrFallback(const char* p, + const char* limit, + uint32_t* value); +inline const char* GetVarint32Ptr(const char* p, + const char* limit, + uint32_t* value) { + if (p < limit) { + uint32_t result = *(reinterpret_cast<const unsigned char*>(p)); + if ((result & 128) == 0) { + *value = result; + return p + 1; + } + } + return GetVarint32PtrFallback(p, limit, value); +} + +} // namespace leveldb + +#endif // STORAGE_LEVELDB_UTIL_CODING_H_ diff --git a/api/leveldb/util/comparator.cc b/api/leveldb/util/comparator.cc new file mode 100644 index 00000000000..c6c9e17efee --- /dev/null +++ b/api/leveldb/util/comparator.cc @@ -0,0 +1,80 @@ +// Copyright (c) 2011 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 <algorithm> +#include <stdint.h> +#include "leveldb_wt.h" +#include "port/port.h" +#include "util/logging.h" + +namespace leveldb { + +Comparator::~Comparator() { } + +#ifndef WITHOUT_HYPERLEVELDB +uint64_t Comparator::KeyNum(const Slice& key) const { + return 0; +} +#endif + +namespace { +class BytewiseComparatorImpl : public Comparator { + public: + BytewiseComparatorImpl() { } + + virtual const char* Name() const { + return "leveldb.BytewiseComparator"; + } + + virtual int Compare(const Slice& a, const Slice& b) const { + return a.compare(b); + } + + virtual void FindShortestSeparator( + std::string* start, + const Slice& limit) const { + // Find length of common prefix + size_t min_length = std::min(start->size(), limit.size()); + size_t diff_index = 0; + while ((diff_index < min_length) && + ((*start)[diff_index] == limit[diff_index])) { + diff_index++; + } + + if (diff_index >= min_length) { + // Do not shorten if one string is a prefix of the other + } else { + uint8_t diff_byte = static_cast<uint8_t>((*start)[diff_index]); + if (diff_byte < static_cast<uint8_t>(0xff) && + diff_byte + 1 < static_cast<uint8_t>(limit[diff_index])) { + (*start)[diff_index]++; + start->resize(diff_index + 1); + assert(Compare(*start, limit) < 0); + } + } + } + + virtual void FindShortSuccessor(std::string* key) const { + // Find first character that can be incremented + size_t n = key->size(); + for (size_t i = 0; i < n; i++) { + const uint8_t byte = (*key)[i]; + if (byte != static_cast<uint8_t>(0xff)) { + (*key)[i] = byte + 1; + key->resize(i+1); + return; + } + } + // *key is a run of 0xffs. Leave it alone. + } +}; +} // namespace + +static const Comparator* bytewise = new BytewiseComparatorImpl; + +const Comparator* BytewiseComparator() { + return bytewise; +} + +} // namespace leveldb diff --git a/api/leveldb/util/env.cc b/api/leveldb/util/env.cc new file mode 100644 index 00000000000..33062fbdd1b --- /dev/null +++ b/api/leveldb/util/env.cc @@ -0,0 +1,96 @@ +// Copyright (c) 2011 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 "hyperleveldb/env.h" + +namespace leveldb { + +Env::~Env() { +} + +SequentialFile::~SequentialFile() { +} + +RandomAccessFile::~RandomAccessFile() { +} + +WritableFile::~WritableFile() { +} + +Logger::~Logger() { +} + +FileLock::~FileLock() { +} + +void Log(Logger* info_log, const char* format, ...) { + if (info_log != NULL) { + va_list ap; + va_start(ap, format); + info_log->Logv(format, ap); + va_end(ap); + } +} + +static Status DoWriteStringToFile(Env* env, const Slice& data, + const std::string& fname, + bool should_sync) { + WritableFile* file; + Status s = env->NewWritableFile(fname, &file); + if (!s.ok()) { + return s; + } + s = file->Append(data); + if (s.ok() && should_sync) { + s = file->Sync(); + } + if (s.ok()) { + s = file->Close(); + } + delete file; // Will auto-close if we did not close above + if (!s.ok()) { + env->DeleteFile(fname); + } + return s; +} + +Status WriteStringToFile(Env* env, const Slice& data, + const std::string& fname) { + return DoWriteStringToFile(env, data, fname, false); +} + +Status WriteStringToFileSync(Env* env, const Slice& data, + const std::string& fname) { + return DoWriteStringToFile(env, data, fname, true); +} + +Status ReadFileToString(Env* env, const std::string& fname, std::string* data) { + data->clear(); + SequentialFile* file; + Status s = env->NewSequentialFile(fname, &file); + if (!s.ok()) { + return s; + } + static const int kBufferSize = 8192; + char* space = new char[kBufferSize]; + while (true) { + Slice fragment; + s = file->Read(kBufferSize, &fragment, space); + if (!s.ok()) { + break; + } + data->append(fragment.data(), fragment.size()); + if (fragment.empty()) { + break; + } + } + delete[] space; + delete file; + return s; +} + +EnvWrapper::~EnvWrapper() { +} + +} // namespace leveldb diff --git a/api/leveldb/util/env_posix.cc b/api/leveldb/util/env_posix.cc new file mode 100644 index 00000000000..66dab413360 --- /dev/null +++ b/api/leveldb/util/env_posix.cc @@ -0,0 +1,617 @@ +// Copyright (c) 2011 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 <deque> +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#if defined(LEVELDB_PLATFORM_ANDROID) +#include <sys/stat.h> +#endif +#include "leveldb_wt.h" +#include "port/port.h" +#include "util/logging.h" +#include "util/posix_logger.h" + +namespace leveldb { + +namespace { + +static Status IOError(const std::string& context, int err_number) { + return Status::IOError(context, strerror(err_number)); +} + +class PosixSequentialFile: public SequentialFile { + private: + std::string filename_; + FILE* file_; + + public: + PosixSequentialFile(const std::string& fname, FILE* f) + : filename_(fname), file_(f) { } + virtual ~PosixSequentialFile() { fclose(file_); } + + virtual Status Read(size_t n, Slice* result, char* scratch) { + Status s; + size_t r = fread_unlocked(scratch, 1, n, file_); + *result = Slice(scratch, r); + if (r < n) { + if (feof(file_)) { + // We leave status as ok if we hit the end of the file + } else { + // A partial read with an error: return a non-ok status + s = IOError(filename_, errno); + } + } + return s; + } + + virtual Status Skip(uint64_t n) { + if (fseek(file_, n, SEEK_CUR)) { + return IOError(filename_, errno); + } + return Status::OK(); + } +}; + +// pread() based random-access +class PosixRandomAccessFile: public RandomAccessFile { + private: + std::string filename_; + int fd_; + + public: + PosixRandomAccessFile(const std::string& fname, int fd) + : filename_(fname), fd_(fd) { } + virtual ~PosixRandomAccessFile() { close(fd_); } + + virtual Status Read(uint64_t offset, size_t n, Slice* result, + char* scratch) const { + Status s; + ssize_t r = pread(fd_, scratch, n, static_cast<off_t>(offset)); + *result = Slice(scratch, (r < 0) ? 0 : r); + if (r < 0) { + // An error: return a non-ok status + s = IOError(filename_, errno); + } + return s; + } +}; + +// mmap() based random-access +class PosixMmapReadableFile: public RandomAccessFile { + private: + std::string filename_; + void* mmapped_region_; + size_t length_; + + public: + // base[0,length-1] contains the mmapped contents of the file. + PosixMmapReadableFile(const std::string& fname, void* base, size_t length) + : filename_(fname), mmapped_region_(base), length_(length) { } + virtual ~PosixMmapReadableFile() { munmap(mmapped_region_, length_); } + + virtual Status Read(uint64_t offset, size_t n, Slice* result, + char* scratch) const { + Status s; + if (offset + n > length_) { + *result = Slice(); + s = IOError(filename_, EINVAL); + } else { + *result = Slice(reinterpret_cast<char*>(mmapped_region_) + offset, n); + } + return s; + } +}; + +// We preallocate up to an extra megabyte and use memcpy to append new +// data to the file. This is safe since we either properly close the +// file before reading from it, or for log files, the reading code +// knows enough to skip zero suffixes. +class PosixMmapFile : public WritableFile { + private: + std::string filename_; + int fd_; + size_t page_size_; + size_t map_size_; // How much extra memory to map at a time + char* base_; // The mapped region + char* limit_; // Limit of the mapped region + char* dst_; // Where to write next (in range [base_,limit_]) + char* last_sync_; // Where have we synced up to + uint64_t file_offset_; // Offset of base_ in file + + // Have we done an munmap of unsynced data? + bool pending_sync_; + + // Roundup x to a multiple of y + static size_t Roundup(size_t x, size_t y) { + return ((x + y - 1) / y) * y; + } + + size_t TruncateToPageBoundary(size_t s) { + s -= (s & (page_size_ - 1)); + assert((s % page_size_) == 0); + return s; + } + + bool UnmapCurrentRegion() { + bool result = true; + if (base_ != NULL) { + if (last_sync_ < limit_) { + // Defer syncing this data until next Sync() call, if any + pending_sync_ = true; + } + if (munmap(base_, limit_ - base_) != 0) { + result = false; + } + file_offset_ += limit_ - base_; + base_ = NULL; + limit_ = NULL; + last_sync_ = NULL; + dst_ = NULL; + + // Increase the amount we map the next time, but capped at 1MB + if (map_size_ < (1<<20)) { + map_size_ *= 2; + } + } + return result; + } + + bool MapNewRegion() { + assert(base_ == NULL); + if (ftruncate(fd_, file_offset_ + map_size_) < 0) { + return false; + } + void* ptr = mmap(NULL, map_size_, PROT_READ | PROT_WRITE, MAP_SHARED, + fd_, file_offset_); + if (ptr == MAP_FAILED) { + return false; + } + base_ = reinterpret_cast<char*>(ptr); + limit_ = base_ + map_size_; + dst_ = base_; + last_sync_ = base_; + return true; + } + + public: + PosixMmapFile(const std::string& fname, int fd, size_t page_size) + : filename_(fname), + fd_(fd), + page_size_(page_size), + map_size_(Roundup(65536, page_size)), + base_(NULL), + limit_(NULL), + dst_(NULL), + last_sync_(NULL), + file_offset_(0), + pending_sync_(false) { + assert((page_size & (page_size - 1)) == 0); + } + + + ~PosixMmapFile() { + if (fd_ >= 0) { + PosixMmapFile::Close(); + } + } + + virtual Status Append(const Slice& data) { + const char* src = data.data(); + size_t left = data.size(); + while (left > 0) { + assert(base_ <= dst_); + assert(dst_ <= limit_); + size_t avail = limit_ - dst_; + if (avail == 0) { + if (!UnmapCurrentRegion() || + !MapNewRegion()) { + return IOError(filename_, errno); + } + } + + size_t n = (left <= avail) ? left : avail; + memcpy(dst_, src, n); + dst_ += n; + src += n; + left -= n; + } + return Status::OK(); + } + + virtual Status Close() { + Status s; + size_t unused = limit_ - dst_; + if (!UnmapCurrentRegion()) { + s = IOError(filename_, errno); + } else if (unused > 0) { + // Trim the extra space at the end of the file + if (ftruncate(fd_, file_offset_ - unused) < 0) { + s = IOError(filename_, errno); + } + } + + if (close(fd_) < 0) { + if (s.ok()) { + s = IOError(filename_, errno); + } + } + + fd_ = -1; + base_ = NULL; + limit_ = NULL; + return s; + } + + virtual Status Flush() { + return Status::OK(); + } + + virtual Status Sync() { + Status s; + + if (pending_sync_) { + // Some unmapped data was not synced + pending_sync_ = false; + if (fdatasync(fd_) < 0) { + s = IOError(filename_, errno); + } + } + + if (dst_ > last_sync_) { + // Find the beginnings of the pages that contain the first and last + // bytes to be synced. + size_t p1 = TruncateToPageBoundary(last_sync_ - base_); + size_t p2 = TruncateToPageBoundary(dst_ - base_ - 1); + last_sync_ = dst_; + if (msync(base_ + p1, p2 - p1 + page_size_, MS_SYNC) < 0) { + s = IOError(filename_, errno); + } + } + + return s; + } + +#ifndef WITHOUT_HYPERLEVELDB + virtual Status WriteAt(uint64_t offset, const Slice& data) { return Status::NotSupported("sorry!"); } +#endif +}; + +static int LockOrUnlock(int fd, bool lock) { + errno = 0; + struct flock f; + memset(&f, 0, sizeof(f)); + f.l_type = (lock ? F_WRLCK : F_UNLCK); + f.l_whence = SEEK_SET; + f.l_start = 0; + f.l_len = 0; // Lock/unlock entire file + return fcntl(fd, F_SETLK, &f); +} + +class PosixFileLock : public FileLock { + public: + int fd_; +}; + +class PosixEnv : public Env { + public: + PosixEnv(); + virtual ~PosixEnv() { + fprintf(stderr, "Destroying Env::Default()\n"); + exit(1); + } + + virtual Status NewSequentialFile(const std::string& fname, + SequentialFile** result) { + FILE* f = fopen(fname.c_str(), "r"); + if (f == NULL) { + *result = NULL; + return IOError(fname, errno); + } else { + *result = new PosixSequentialFile(fname, f); + return Status::OK(); + } + } + + virtual Status NewRandomAccessFile(const std::string& fname, + RandomAccessFile** result) { + *result = NULL; + Status s; + int fd = open(fname.c_str(), O_RDONLY); + if (fd < 0) { + s = IOError(fname, errno); + } else if (sizeof(void*) >= 8) { + // Use mmap when virtual address-space is plentiful. + uint64_t size; + s = GetFileSize(fname, &size); + if (s.ok()) { + void* base = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0); + if (base != MAP_FAILED) { + *result = new PosixMmapReadableFile(fname, base, size); + } else { + s = IOError(fname, errno); + } + } + close(fd); + } else { + *result = new PosixRandomAccessFile(fname, fd); + } + return s; + } + + virtual Status NewWritableFile(const std::string& fname, + WritableFile** result) { + Status s; + const int fd = open(fname.c_str(), O_CREAT | O_RDWR | O_TRUNC, 0644); + if (fd < 0) { + *result = NULL; + s = IOError(fname, errno); + } else { + *result = new PosixMmapFile(fname, fd, page_size_); + } + return s; + } + + virtual bool FileExists(const std::string& fname) { + return access(fname.c_str(), F_OK) == 0; + } + + virtual Status GetChildren(const std::string& dir, + std::vector<std::string>* result) { + result->clear(); + DIR* d = opendir(dir.c_str()); + if (d == NULL) { + return IOError(dir, errno); + } + struct dirent* entry; + while ((entry = readdir(d)) != NULL) { + result->push_back(entry->d_name); + } + closedir(d); + return Status::OK(); + } + + virtual Status DeleteFile(const std::string& fname) { + Status result; + if (unlink(fname.c_str()) != 0) { + result = IOError(fname, errno); + } + return result; + }; + + virtual Status CreateDir(const std::string& name) { + Status result; + if (mkdir(name.c_str(), 0755) != 0) { + result = IOError(name, errno); + } + return result; + }; + + virtual Status DeleteDir(const std::string& name) { + Status result; + if (rmdir(name.c_str()) != 0) { + result = IOError(name, errno); + } + return result; + }; + + virtual Status GetFileSize(const std::string& fname, uint64_t* size) { + Status s; + struct stat sbuf; + if (stat(fname.c_str(), &sbuf) != 0) { + *size = 0; + s = IOError(fname, errno); + } else { + *size = sbuf.st_size; + } + return s; + } + + virtual Status RenameFile(const std::string& src, const std::string& target) { + Status result; + if (rename(src.c_str(), target.c_str()) != 0) { + result = IOError(src, errno); + } + return result; + } + + virtual Status LockFile(const std::string& fname, FileLock** lock) { + *lock = NULL; + Status result; + int fd = open(fname.c_str(), O_RDWR | O_CREAT, 0644); + if (fd < 0) { + result = IOError(fname, errno); + } else if (LockOrUnlock(fd, true) == -1) { + result = IOError("lock " + fname, errno); + close(fd); + } else { + PosixFileLock* my_lock = new PosixFileLock; + my_lock->fd_ = fd; + *lock = my_lock; + } + return result; + } + + virtual Status UnlockFile(FileLock* lock) { + PosixFileLock* my_lock = reinterpret_cast<PosixFileLock*>(lock); + Status result; + if (LockOrUnlock(my_lock->fd_, false) == -1) { + result = IOError("unlock", errno); + } + close(my_lock->fd_); + delete my_lock; + return result; + } + + virtual void Schedule(void (*function)(void*), void* arg); + + virtual void StartThread(void (*function)(void* arg), void* arg); + + virtual Status GetTestDirectory(std::string* result) { + const char* env = getenv("TEST_TMPDIR"); + if (env && env[0] != '\0') { + *result = env; + } else { + char buf[100]; + snprintf(buf, sizeof(buf), "/tmp/leveldbtest-%d", int(geteuid())); + *result = buf; + } + // Directory may already exist + CreateDir(*result); + return Status::OK(); + } + + static uint64_t gettid() { + pthread_t tid = pthread_self(); + uint64_t thread_id = 0; + memcpy(&thread_id, &tid, std::min(sizeof(thread_id), sizeof(tid))); + return thread_id; + } + + virtual Status NewLogger(const std::string& fname, Logger** result) { + FILE* f = fopen(fname.c_str(), "w"); + if (f == NULL) { + *result = NULL; + return IOError(fname, errno); + } else { + *result = new PosixLogger(f, &PosixEnv::gettid); + return Status::OK(); + } + } + + virtual uint64_t NowMicros() { + struct timeval tv; + gettimeofday(&tv, NULL); + return static_cast<uint64_t>(tv.tv_sec) * 1000000 + tv.tv_usec; + } + + virtual void SleepForMicroseconds(int micros) { + usleep(micros); + } + +#ifndef WITHOUT_HYPERLEVELDB + virtual Status CopyFile(const std::string&, const std::string&) { return Status::NotSupported("sorry!"); } + virtual Status LinkFile(const std::string&, const std::string&) { return Status::NotSupported("sorry!"); } +#endif + + private: + void PthreadCall(const char* label, int result) { + if (result != 0) { + fprintf(stderr, "pthread %s: %s\n", label, strerror(result)); + exit(1); + } + } + + // BGThread() is the body of the background thread + void BGThread(); + static void* BGThreadWrapper(void* arg) { + reinterpret_cast<PosixEnv*>(arg)->BGThread(); + return NULL; + } + + size_t page_size_; + pthread_mutex_t mu_; + pthread_cond_t bgsignal_; + pthread_t bgthread_; + bool started_bgthread_; + + // Entry per Schedule() call + struct BGItem { void* arg; void (*function)(void*); }; + typedef std::deque<BGItem> BGQueue; + BGQueue queue_; +}; + +PosixEnv::PosixEnv() : page_size_(getpagesize()), + started_bgthread_(false) { + PthreadCall("mutex_init", pthread_mutex_init(&mu_, NULL)); + PthreadCall("cvar_init", pthread_cond_init(&bgsignal_, NULL)); +} + +void PosixEnv::Schedule(void (*function)(void*), void* arg) { + PthreadCall("lock", pthread_mutex_lock(&mu_)); + + // Start background thread if necessary + if (!started_bgthread_) { + started_bgthread_ = true; + PthreadCall( + "create thread", + pthread_create(&bgthread_, NULL, &PosixEnv::BGThreadWrapper, this)); + } + + // If the queue is currently empty, the background thread may currently be + // waiting. + if (queue_.empty()) { + PthreadCall("signal", pthread_cond_signal(&bgsignal_)); + } + + // Add to priority queue + queue_.push_back(BGItem()); + queue_.back().function = function; + queue_.back().arg = arg; + + PthreadCall("unlock", pthread_mutex_unlock(&mu_)); +} + +void PosixEnv::BGThread() { + while (true) { + // Wait until there is an item that is ready to run + PthreadCall("lock", pthread_mutex_lock(&mu_)); + while (queue_.empty()) { + PthreadCall("wait", pthread_cond_wait(&bgsignal_, &mu_)); + } + + void (*function)(void*) = queue_.front().function; + void* arg = queue_.front().arg; + queue_.pop_front(); + + PthreadCall("unlock", pthread_mutex_unlock(&mu_)); + (*function)(arg); + } +} + +namespace { +struct StartThreadState { + void (*user_function)(void*); + void* arg; +}; +} +static void* StartThreadWrapper(void* arg) { + StartThreadState* state = reinterpret_cast<StartThreadState*>(arg); + state->user_function(state->arg); + delete state; + return NULL; +} + +void PosixEnv::StartThread(void (*function)(void* arg), void* arg) { + pthread_t t; + StartThreadState* state = new StartThreadState; + state->user_function = function; + state->arg = arg; + PthreadCall("start thread", + pthread_create(&t, NULL, &StartThreadWrapper, state)); +} + +} // namespace + +static pthread_once_t once = PTHREAD_ONCE_INIT; +static Env* default_env; +static void InitDefaultEnv() { default_env = new PosixEnv; } + +Env* Env::Default() { + pthread_once(&once, InitDefaultEnv); + return default_env; +} + +} // namespace leveldb diff --git a/api/leveldb/util/logging.cc b/api/leveldb/util/logging.cc new file mode 100644 index 00000000000..1d60ce22701 --- /dev/null +++ b/api/leveldb/util/logging.cc @@ -0,0 +1,80 @@ +// Copyright (c) 2011 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 "util/logging.h" + +#include <errno.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include "leveldb_wt.h" + +namespace leveldb { + +void AppendNumberTo(std::string* str, uint64_t num) { + char buf[30]; + snprintf(buf, sizeof(buf), "%llu", (unsigned long long) num); + str->append(buf); +} + +void AppendEscapedStringTo(std::string* str, const Slice& value) { + for (size_t i = 0; i < value.size(); i++) { + char c = value[i]; + if (c >= ' ' && c <= '~') { + str->push_back(c); + } else { + char buf[10]; + snprintf(buf, sizeof(buf), "\\x%02x", + static_cast<unsigned int>(c) & 0xff); + str->append(buf); + } + } +} + +std::string NumberToString(uint64_t num) { + std::string r; + AppendNumberTo(&r, num); + return r; +} + +std::string EscapeString(const Slice& value) { + std::string r; + AppendEscapedStringTo(&r, value); + return r; +} + +bool ConsumeChar(Slice* in, char c) { + if (!in->empty() && (*in)[0] == c) { + in->remove_prefix(1); + return true; + } else { + return false; + } +} + +bool ConsumeDecimalNumber(Slice* in, uint64_t* val) { + uint64_t v = 0; + int digits = 0; + while (!in->empty()) { + char c = (*in)[0]; + if (c >= '0' && c <= '9') { + ++digits; + const int delta = (c - '0'); + static const uint64_t kMaxUint64 = ~static_cast<uint64_t>(0); + if (v > kMaxUint64/10 || + (v == kMaxUint64/10 && delta > kMaxUint64%10)) { + // Overflow + return false; + } + v = (v * 10) + delta; + in->remove_prefix(1); + } else { + break; + } + } + *val = v; + return (digits > 0); +} + +} // namespace leveldb diff --git a/api/leveldb/util/logging.h b/api/leveldb/util/logging.h new file mode 100644 index 00000000000..b0c5da813e8 --- /dev/null +++ b/api/leveldb/util/logging.h @@ -0,0 +1,47 @@ +// Copyright (c) 2011 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. +// +// Must not be included from any .h files to avoid polluting the namespace +// with macros. + +#ifndef STORAGE_LEVELDB_UTIL_LOGGING_H_ +#define STORAGE_LEVELDB_UTIL_LOGGING_H_ + +#include <stdio.h> +#include <stdint.h> +#include <string> +#include "port/port.h" + +namespace leveldb { + +class Slice; +class WritableFile; + +// Append a human-readable printout of "num" to *str +extern void AppendNumberTo(std::string* str, uint64_t num); + +// Append a human-readable printout of "value" to *str. +// Escapes any non-printable characters found in "value". +extern void AppendEscapedStringTo(std::string* str, const Slice& value); + +// Return a human-readable printout of "num" +extern std::string NumberToString(uint64_t num); + +// Return a human-readable version of "value". +// Escapes any non-printable characters found in "value". +extern std::string EscapeString(const Slice& value); + +// If *in starts with "c", advances *in past the first character and +// returns true. Otherwise, returns false. +extern bool ConsumeChar(Slice* in, char c); + +// Parse a human-readable number from "*in" into *value. On success, +// advances "*in" past the consumed number and sets "*val" to the +// numeric value. Otherwise, returns false and leaves *in in an +// unspecified state. +extern bool ConsumeDecimalNumber(Slice* in, uint64_t* val); + +} // namespace leveldb + +#endif // STORAGE_LEVELDB_UTIL_LOGGING_H_ diff --git a/api/leveldb/util/options.cc b/api/leveldb/util/options.cc new file mode 100644 index 00000000000..6956ab6e739 --- /dev/null +++ b/api/leveldb/util/options.cc @@ -0,0 +1,29 @@ +// Copyright (c) 2011 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 "hyperleveldb/options.h" + +#include "hyperleveldb/comparator.h" +#include "hyperleveldb/env.h" + +namespace leveldb { + +Options::Options() + : comparator(BytewiseComparator()), + create_if_missing(false), + error_if_exists(false), + paranoid_checks(false), + env(Env::Default()), + info_log(NULL), + write_buffer_size(4<<20), + max_open_files(1000), + block_cache(NULL), + block_size(4096), + block_restart_interval(16), + compression(kSnappyCompression), + filter_policy(NULL) { +} + + +} // namespace leveldb diff --git a/api/leveldb/util/posix_logger.h b/api/leveldb/util/posix_logger.h new file mode 100644 index 00000000000..f15de45e05e --- /dev/null +++ b/api/leveldb/util/posix_logger.h @@ -0,0 +1,98 @@ +// Copyright (c) 2011 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. +// +// Logger implementation that can be shared by all environments +// where enough posix functionality is available. + +#ifndef STORAGE_LEVELDB_UTIL_POSIX_LOGGER_H_ +#define STORAGE_LEVELDB_UTIL_POSIX_LOGGER_H_ + +#include <algorithm> +#include <stdio.h> +#include <sys/time.h> +#include <time.h> +#include "leveldb_wt.h" + +namespace leveldb { + +class PosixLogger : public Logger { + private: + FILE* file_; + uint64_t (*gettid_)(); // Return the thread id for the current thread + public: + PosixLogger(FILE* f, uint64_t (*gettid)()) : file_(f), gettid_(gettid) { } + virtual ~PosixLogger() { + fclose(file_); + } + virtual void Logv(const char* format, va_list ap) { + const uint64_t thread_id = (*gettid_)(); + + // We try twice: the first time with a fixed-size stack allocated buffer, + // and the second time with a much larger dynamically allocated buffer. + char buffer[500]; + for (int iter = 0; iter < 2; iter++) { + char* base; + int bufsize; + if (iter == 0) { + bufsize = sizeof(buffer); + base = buffer; + } else { + bufsize = 30000; + base = new char[bufsize]; + } + char* p = base; + char* limit = base + bufsize; + + struct timeval now_tv; + gettimeofday(&now_tv, NULL); + const time_t seconds = now_tv.tv_sec; + struct tm t; + localtime_r(&seconds, &t); + p += snprintf(p, limit - p, + "%04d/%02d/%02d-%02d:%02d:%02d.%06d %llx ", + t.tm_year + 1900, + t.tm_mon + 1, + t.tm_mday, + t.tm_hour, + t.tm_min, + t.tm_sec, + static_cast<int>(now_tv.tv_usec), + static_cast<long long unsigned int>(thread_id)); + + // Print the message + if (p < limit) { + va_list backup_ap; + va_copy(backup_ap, ap); + p += vsnprintf(p, limit - p, format, backup_ap); + va_end(backup_ap); + } + + // Truncate to available space if necessary + if (p >= limit) { + if (iter == 0) { + continue; // Try again with larger buffer + } else { + p = limit - 1; + } + } + + // Add newline if necessary + if (p == base || p[-1] != '\n') { + *p++ = '\n'; + } + + assert(p <= limit); + fwrite(base, 1, p - base, file_); + fflush(file_); + if (base != buffer) { + delete[] base; + } + break; + } + } +}; + +} // namespace leveldb + +#endif // STORAGE_LEVELDB_UTIL_POSIX_LOGGER_H_ diff --git a/api/leveldb/util/random.h b/api/leveldb/util/random.h new file mode 100644 index 00000000000..66e0c94e7cb --- /dev/null +++ b/api/leveldb/util/random.h @@ -0,0 +1,72 @@ +// Copyright (c) 2011 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. + +#ifndef STORAGE_LEVELDB_UTIL_RANDOM_H_ +#define STORAGE_LEVELDB_UTIL_RANDOM_H_ + +#include <stdint.h> + +namespace leveldb { + +// A very simple random number generator. Not especially good at +// generating truly random bits, but good enough for our needs in this +// package. +class Random { + private: + uint32_t seed_; + public: + explicit Random(uint32_t s) : seed_(s & 0x7fffffffu) { } + uint32_t Next() { + static const uint32_t M = 2147483647L; // 2^31-1 + static const uint64_t A = 16807; // bits 14, 8, 7, 5, 2, 1, 0 + // We are computing + // seed_ = (seed_ * A) % M, where M = 2^31-1 + // + // seed_ must not be zero or M, or else all subsequent computed values + // will be zero or M respectively. For all other values, seed_ will end + // up cycling through every number in [1,M-1] + uint64_t product = seed_ * A; + + // Compute (product % M) using the fact that ((x << 31) % M) == x. + seed_ = static_cast<uint32_t>((product >> 31) + (product & M)); + // The first reduction may overflow by 1 bit, so we may need to + // repeat. mod == M is not possible; using > allows the faster + // sign-bit-based test. + if (seed_ > M) { + seed_ -= M; + } + return seed_; + } + // Returns a uniformly distributed value in the range [0..n-1] + // REQUIRES: n > 0 + uint32_t Uniform(int n) { return Next() % n; } + + // Randomly returns true ~"1/n" of the time, and false otherwise. + // REQUIRES: n > 0 + bool OneIn(int n) { return (Next() % n) == 0; } + + // Skewed: pick "base" uniformly from range [0,max_log] and then + // return "base" random bits. The effect is to pick a number in the + // range [0,2^max_log-1] with exponential bias towards smaller numbers. + uint32_t Skewed(int max_log) { + return Uniform(1 << Uniform(max_log + 1)); + } + + // Shuffle the array into random order + void Shuffle(int *array, int n) { + if (n > 1) { + int i; + for (i=0; i<n-1; i++) { + int j = i + Next() / (2147483647 / (n-i) + 1); + int t = array[j]; + array[j] = array[i]; + array[i] = t; + } + } + } +}; + +} // namespace leveldb + +#endif // STORAGE_LEVELDB_UTIL_RANDOM_H_ diff --git a/api/leveldb/util/status.cc b/api/leveldb/util/status.cc new file mode 100644 index 00000000000..51a8210b679 --- /dev/null +++ b/api/leveldb/util/status.cc @@ -0,0 +1,74 @@ +// Copyright (c) 2011 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 <stdio.h> +#include "leveldb_wt.h" + +namespace leveldb { + +const char* Status::CopyState(const char* state) { + uint32_t size; + memcpy(&size, state, sizeof(size)); + char* result = new char[size + 5]; + memcpy(result, state, size + 5); + return result; +} + +Status::Status(Code code, const Slice& msg, const Slice& msg2) { + assert(code != kOk); + const uint32_t len1 = msg.size(); + const uint32_t len2 = msg2.size(); + const uint32_t size = len1 + (len2 ? (2 + len2) : 0); + char* result = new char[size + 5]; + memcpy(result, &size, sizeof(size)); + result[4] = static_cast<char>(code); + memcpy(result + 5, msg.data(), len1); + if (len2) { + result[5 + len1] = ':'; + result[6 + len1] = ' '; + memcpy(result + 7 + len1, msg2.data(), len2); + } + state_ = result; +} + +std::string Status::ToString() const { + if (state_ == NULL) { + return "OK"; + } else { + char tmp[30]; + const char* type; + switch (code()) { + case kOk: + type = "OK"; + break; + case kNotFound: + type = "NotFound: "; + break; + case kCorruption: + type = "Corruption: "; + break; + case kNotSupported: + type = "Not implemented: "; + break; + case kInvalidArgument: + type = "Invalid argument: "; + break; + case kIOError: + type = "IO error: "; + break; + default: + snprintf(tmp, sizeof(tmp), "Unknown code(%d): ", + static_cast<int>(code())); + type = tmp; + break; + } + std::string result(type); + uint32_t length; + memcpy(&length, state_, sizeof(length)); + result.append(state_ + 5, length); + return result; + } +} + +} // namespace leveldb |