Merge #13039: Add logging and error handling for file syncing

cf02779 Add logging and error handling for file syncing (Wladimir J. van der Laan)

Pull request description:

  Add logging and error handling inside, and outside of FileCommit.
  Functions such as fsync, fdatasync will return error in case of hardware I/O errors, and ignoring this means it can silently continue through data corruption.
  (c.f. https://lwn.net/SubscriberLink/752063/12b232ab5039efbe/)

  EINVAL is handled specially to avoid crashing out on (network, fuse) filesystems that don't handle `f[data]sync`.

  I checked that the syncing inside leveldb is already generating an I/O error as appropriate.

Tree-SHA512: 64cc9bbedca3ecc97ff4bac0a7b7ac6526a7ed763c66f6786d03ca4f2e9e366e42b152cb908299c060448d98ca39ff03395280bffaca51d592e728aa2516f5dd

src/addrdb.cpp

@@ -49,7 +49,8 @@ bool SerializeFileDB(const std::string& prefix, const fs::path& path, const Data
 
     // Serialize
     if (!SerializeDB(fileout, data)) return false;
-    FileCommit(fileout.Get());
+    if (!FileCommit(fileout.Get()))
+        return error("%s: Failed to flush file %s", __func__, pathTmp.string());
     fileout.fclose();
 
     // replace existing file, if any, with new file

src/util.cpp

@@ -788,21 +788,37 @@ bool TryCreateDirectories(const fs::path& p)
     return false;
 }
 
-void FileCommit(FILE *file)
+bool FileCommit(FILE *file)
 {
-    fflush(file); // harmless if redundantly called
+    if (fflush(file) != 0) { // harmless if redundantly called
+        LogPrintf("%s: fflush failed: %d\n", __func__, errno);
+        return false;
+    }
 #ifdef WIN32
     HANDLE hFile = (HANDLE)_get_osfhandle(_fileno(file));
-    FlushFileBuffers(hFile);
+    if (FlushFileBuffers(hFile) == 0) {
+        LogPrintf("%s: FlushFileBuffers failed: %d\n", __func__, GetLastError());
+        return false;
+    }
 #else
     #if defined(__linux__) || defined(__NetBSD__)
-    fdatasync(fileno(file));
+    if (fdatasync(fileno(file)) != 0 && errno != EINVAL) { // Ignore EINVAL for filesystems that don't support sync
+        LogPrintf("%s: fdatasync failed: %d\n", __func__, errno);
+        return false;
+    }
     #elif defined(__APPLE__) && defined(F_FULLFSYNC)
-    fcntl(fileno(file), F_FULLFSYNC, 0);
+    if (fcntl(fileno(file), F_FULLFSYNC, 0) == -1) { // Manpage says "value other than -1" is returned on success
+        LogPrintf("%s: fcntl F_FULLFSYNC failed: %d\n", __func__, errno);
+        return false;
+    }
     #else
-    fsync(fileno(file));
+    if (fsync(fileno(file)) != 0 && errno != EINVAL) {
+        LogPrintf("%s: fsync failed: %d\n", __func__, errno);
+        return false;
+    }
     #endif
 #endif
+    return true;
 }
 
 bool TruncateFile(FILE *file, unsigned int length) {

src/util.h

@@ -71,7 +71,7 @@ bool error(const char* fmt, const Args&... args)
 }
 
 void PrintExceptionContinue(const std::exception *pex, const char* pszThread);
-void FileCommit(FILE *file);
+bool FileCommit(FILE *file);
 bool TruncateFile(FILE *file, unsigned int length);
 int RaiseFileDescriptorLimit(int nMinFD);
 void AllocateFileRange(FILE *file, unsigned int offset, unsigned int length);

src/validation.cpp

@@ -1615,22 +1615,27 @@ void static FlushBlockFile(bool fFinalize = false)
     LOCK(cs_LastBlockFile);
 
     CDiskBlockPos posOld(nLastBlockFile, 0);
+    bool status = true;
 
     FILE *fileOld = OpenBlockFile(posOld);
     if (fileOld) {
         if (fFinalize)
-            TruncateFile(fileOld, vinfoBlockFile[nLastBlockFile].nSize);
+            status &= TruncateFile(fileOld, vinfoBlockFile[nLastBlockFile].nSize);
-        FileCommit(fileOld);
+        status &= FileCommit(fileOld);
         fclose(fileOld);
     }
 
     fileOld = OpenUndoFile(posOld);
     if (fileOld) {
         if (fFinalize)
-            TruncateFile(fileOld, vinfoBlockFile[nLastBlockFile].nUndoSize);
+            status &= TruncateFile(fileOld, vinfoBlockFile[nLastBlockFile].nUndoSize);
-        FileCommit(fileOld);
+        status &= FileCommit(fileOld);
         fclose(fileOld);
     }
+
+    if (!status) {
+        AbortNode("Flushing block file to disk failed. This is likely the result of an I/O error.");
+    }
 }
 
 static bool FindUndoPos(CValidationState &state, int nFile, CDiskBlockPos &pos, unsigned int nAddSize);
@@ -4760,7 +4765,8 @@ bool DumpMempool(void)
         }
 
         file << mapDeltas;
-        FileCommit(file.Get());
+        if (!FileCommit(file.Get()))
+            throw std::runtime_error("FileCommit failed");
         file.fclose();
         RenameOver(GetDataDir() / "mempool.dat.new", GetDataDir() / "mempool.dat");
         int64_t last = GetTimeMicros();