Release LevelDB 1.15v1.15

- switched from mmap based writing to simpler stdio based writing. Has a
  minor impact (0.5 microseconds) on microbenchmarks for asynchronous
  writes. Synchronous writes speed up from 30ms to 10ms on linux/ext4.
  Should be much more reliable on diverse platforms.
- compaction errors now immediately put the database into a read-only
  mode (until it is re-opened). As a downside, a disk going out of
  space and then space being created will require a re-open to recover
  from, whereas previously that would happen automatically. On the
  plus side, many corruption possibilities go away.
- force the DB to enter an error-state so that all future writes fail
  when a synchronous log write succeeds but the sync fails.
- repair now regenerates sstables that exhibit problems
- fix issue 218 - Use native memory barriers on OSX
- fix issue 212 - QNX build is broken
- fix build on iOS with xcode 5
- make tests compile and pass on windows

8 files changed, 40 insertions, 161 deletions

diff --git a/util/arena.h b/util/arena.h
index 8f7dde2..73bbf1c 100644
--- a/util/arena.h
+++ b/util/arena.h
@@ -5,9 +5,9 @@
 #ifndef STORAGE_LEVELDB_UTIL_ARENA_H_
 #define STORAGE_LEVELDB_UTIL_ARENA_H_
 
-#include <cstddef>
 #include <vector>
 #include <assert.h>
+#include <stddef.h>
 #include <stdint.h>
 
 namespace leveldb {
diff --git a/util/arena_test.cc b/util/arena_test.cc
index 63d1778..58e870e 100644
--- a/util/arena_test.cc
+++ b/util/arena_test.cc
@@ -40,7 +40,7 @@ TEST(ArenaTest, Simple) {
       r = arena.Allocate(s);
     }
 
-    for (int b = 0; b < s; b++) {
+    for (size_t b = 0; b < s; b++) {
       // Fill the "i"th allocation with a known bit pattern
       r[b] = i % 256;
     }
@@ -51,10 +51,10 @@ TEST(ArenaTest, Simple) {
       ASSERT_LE(arena.MemoryUsage(), bytes * 1.10);
     }
   }
-  for (int i = 0; i < allocated.size(); i++) {
+  for (size_t i = 0; i < allocated.size(); i++) {
     size_t num_bytes = allocated[i].first;
     const char* p = allocated[i].second;
-    for (int b = 0; b < num_bytes; b++) {
+    for (size_t b = 0; b < num_bytes; b++) {
       // Check the "i"th allocation for the known bit pattern
       ASSERT_EQ(int(p[b]) & 0xff, i % 256);
     }
diff --git a/util/bloom_test.cc b/util/bloom_test.cc
index 0bf8e8d..77fb1b3 100644
--- a/util/bloom_test.cc
+++ b/util/bloom_test.cc
@@ -126,7 +126,8 @@ TEST(BloomTest, VaryingLengths) {
     }
     Build();
 
-    ASSERT_LE(FilterSize(), (length * 10 / 8) + 40) << length;
+    ASSERT_LE(FilterSize(), static_cast<size_t>((length * 10 / 8) + 40))
+        << length;
 
     // All added keys must match
     for (int i = 0; i < length; i++) {
diff --git a/util/coding_test.cc b/util/coding_test.cc
index fb5726e..521541e 100644
--- a/util/coding_test.cc
+++ b/util/coding_test.cc
@@ -112,13 +112,13 @@ TEST(Coding, Varint64) {
   }
 
   std::string s;
-  for (int i = 0; i < values.size(); i++) {
+  for (size_t i = 0; i < values.size(); i++) {
     PutVarint64(&s, values[i]);
   }
 
   const char* p = s.data();
   const char* limit = p + s.size();
-  for (int i = 0; i < values.size(); i++) {
+  for (size_t i = 0; i < values.size(); i++) {
     ASSERT_TRUE(p < limit);
     uint64_t actual;
     const char* start = p;
@@ -143,7 +143,7 @@ TEST(Coding, Varint32Truncation) {
   std::string s;
   PutVarint32(&s, large_value);
   uint32_t result;
-  for (int len = 0; len < s.size() - 1; len++) {
+  for (size_t len = 0; len < s.size() - 1; len++) {
     ASSERT_TRUE(GetVarint32Ptr(s.data(), s.data() + len, &result) == NULL);
   }
   ASSERT_TRUE(GetVarint32Ptr(s.data(), s.data() + s.size(), &result) != NULL);
@@ -162,7 +162,7 @@ TEST(Coding, Varint64Truncation) {
   std::string s;
   PutVarint64(&s, large_value);
   uint64_t result;
-  for (int len = 0; len < s.size() - 1; len++) {
+  for (size_t len = 0; len < s.size() - 1; len++) {
     ASSERT_TRUE(GetVarint64Ptr(s.data(), s.data() + len, &result) == NULL);
   }
   ASSERT_TRUE(GetVarint64Ptr(s.data(), s.data() + s.size(), &result) != NULL);
diff --git a/util/env_posix.cc b/util/env_posix.cc
index 3e2925d..e1cbebd 100644
--- a/util/env_posix.cc
+++ b/util/env_posix.cc
@@ -175,147 +175,43 @@ class PosixMmapReadableFile: public RandomAccessFile {
   }
 };
 
-// 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 {
+class PosixWritableFile : 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;
-  }
+  FILE* file_;
 
  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();
+  PosixWritableFile(const std::string& fname, FILE* f)
+      : filename_(fname), file_(f) { }
+
+  ~PosixWritableFile() {
+    if (file_ != NULL) {
+      // Ignoring any potential errors
+      fclose(file_);
     }
   }
 
   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;
+    size_t r = fwrite_unlocked(data.data(), 1, data.size(), file_);
+    if (r != data.size()) {
+      return IOError(filename_, errno);
     }
     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);
-      }
+    Status result;
+    if (fclose(file_) != 0) {
+      result = IOError(filename_, errno);
     }
-
-    fd_ = -1;
-    base_ = NULL;
-    limit_ = NULL;
-    return s;
+    file_ = NULL;
+    return result;
   }
 
   virtual Status Flush() {
+    if (fflush_unlocked(file_) != 0) {
+      return IOError(filename_, errno);
+    }
     return Status::OK();
   }
 
@@ -352,26 +248,10 @@ class PosixMmapFile : public WritableFile {
     if (!s.ok()) {
       return s;
     }
-
-    if (pending_sync_) {
-      // Some unmapped data was not synced
-      pending_sync_ = false;
-      if (fdatasync(fd_) < 0) {
-        s = IOError(filename_, errno);
-      }
+    if (fflush_unlocked(file_) != 0 ||
+        fdatasync(fileno(file_)) != 0) {
+      s = Status::IOError(filename_, strerror(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;
   }
 };
@@ -462,12 +342,12 @@ class PosixEnv : public Env {
   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) {
+    FILE* f = fopen(fname.c_str(), "w");
+    if (f == NULL) {
       *result = NULL;
       s = IOError(fname, errno);
     } else {
-      *result = new PosixMmapFile(fname, fd, page_size_);
+      *result = new PosixWritableFile(fname, f);
     }
     return s;
   }
@@ -630,7 +510,6 @@ class PosixEnv : public Env {
     return NULL;
   }
 
-  size_t page_size_;
   pthread_mutex_t mu_;
   pthread_cond_t bgsignal_;
   pthread_t bgthread_;
@@ -645,8 +524,7 @@ class PosixEnv : public Env {
   MmapLimiter mmap_limit_;
 };
 
-PosixEnv::PosixEnv() : page_size_(getpagesize()),
-                       started_bgthread_(false) {
+PosixEnv::PosixEnv() : started_bgthread_(false) {
   PthreadCall("mutex_init", pthread_mutex_init(&mu_, NULL));
   PthreadCall("cvar_init", pthread_cond_init(&bgsignal_, NULL));
 }
diff --git a/util/testharness.cc b/util/testharness.cc
index eb1bdd5..402fab3 100644
--- a/util/testharness.cc
+++ b/util/testharness.cc
@@ -38,7 +38,7 @@ int RunAllTests() {
 
   int num = 0;
   if (tests != NULL) {
-    for (int i = 0; i < tests->size(); i++) {
+    for (size_t i = 0; i < tests->size(); i++) {
       const Test& t = (*tests)[i];
       if (matcher != NULL) {
         std::string name = t.base;
diff --git a/util/testutil.cc b/util/testutil.cc
index 538d095..bee56bf 100644
--- a/util/testutil.cc
+++ b/util/testutil.cc
@@ -32,7 +32,7 @@ std::string RandomKey(Random* rnd, int len) {
 
 
 extern Slice CompressibleString(Random* rnd, double compressed_fraction,
-                                int len, std::string* dst) {
+                                size_t len, std::string* dst) {
   int raw = static_cast<int>(len * compressed_fraction);
   if (raw < 1) raw = 1;
   std::string raw_data;
diff --git a/util/testutil.h b/util/testutil.h
index 824e655..adad3fc 100644
--- a/util/testutil.h
+++ b/util/testutil.h
@@ -24,7 +24,7 @@ extern std::string RandomKey(Random* rnd, int len);
 // "N*compressed_fraction" bytes and return a Slice that references
 // the generated data.
 extern Slice CompressibleString(Random* rnd, double compressed_fraction,
-                                int len, std::string* dst);
+                                size_t len, std::string* dst);
 
 // A wrapper that allows injection of errors.
 class ErrorEnv : public EnvWrapper {