[SYCL] persistent cache fix - directory creation and reporting improvements (#13019)

We have a report of persistent cache failures. Traced to the directory
creation so I switched it to use C++17 std::filesystem routines for
`OSUtil::makeDir`. Also improved trace reporting.

Author: cperkinsintel

sycl/include/sycl/detail/os_util.hpp

@@ -65,7 +65,7 @@ class __SYCL_EXPORT OSUtil {
   /// Deallocates the memory referenced by \p Ptr.
   static void alignedFree(void *Ptr);
 
-  /// Make directory recursively and returns zero code on success
+  /// Make all directories on the path, throws on error.
   static int makeDir(const char *Dir);
 
   /// Checks if specified path is present

sycl/source/detail/os_util.cpp

@@ -11,6 +11,12 @@
 #include <cassert>
 #include <limits>
 
+#if __GNUC__ && __GNUC__ < 8
+// Don't include <filesystem> for GCC versions less than 8
+#else
+#include <filesystem> // C++ 17 std::create_directories
+#endif
+
 #if defined(__SYCL_RT_OS_LINUX)
 
 #ifndef _GNU_SOURCE
@@ -32,7 +38,6 @@
 #include <detail/windows_os_utils.hpp>
 
 #include <Windows.h>
-#include <direct.h>
 #include <malloc.h>
 #include <shlwapi.h>
 
@@ -233,15 +238,14 @@ void OSUtil::alignedFree(void *Ptr) {
 #endif
 }
 
-/* This is temporary solution until std::filesystem is available when SYCL RT
- * is moved to c++17 standard*/
-
-/* Create directory recursively and return non zero code on success*/
+// Make all directories on the path, throws on error.
 int OSUtil::makeDir(const char *Dir) {
   assert((Dir != nullptr) && "Passed null-pointer as directory name.");
   if (isPathPresent(Dir))
     return 0;
 
+// older GCC doesn't have full C++ 17 support.
+#if __GNUC__ && __GNUC__ < 8
   std::string Path{Dir}, CurPath;
   size_t pos = 0;
 
@@ -254,8 +258,15 @@ int OSUtil::makeDir(const char *Dir) {
     auto Res = _mkdir(CurPath.c_str());
 #endif
     if (Res && errno != EEXIST)
-      return Res;
+      throw std::runtime_error("Failed to mkdir: " + CurPath + " (" +
+                               std::strerror(errno) + ")");
+
   } while (pos != std::string::npos);
+#else
+  // using filesystem is simpler, more reliable, works better on Win
+  std::filesystem::path path(Dir);
+  std::filesystem::create_directories(path.make_preferred());
+#endif
   return 0;
 }
 

sycl/source/detail/persistent_device_code_cache.cpp

@@ -11,6 +11,7 @@
 #include <detail/plugin.hpp>
 #include <detail/program_manager/program_manager.hpp>
 
+#include <cerrno>
 #include <cstdio>
 #include <fstream>
 #include <optional>
@@ -38,7 +39,10 @@ LockCacheItem::LockCacheItem(const std::string &Path)
     close(fd);
     Owned = true;
   } else {
-    PersistentDeviceCodeCache::trace("Failed to aquire lock file: " + FileName);
+    PersistentDeviceCodeCache::trace("Failed to acquire lock file: " +
+                                     FileName + " " + std::strerror(errno));
+    PersistentDeviceCodeCache::trace("Failed to acquire lock file: " +
+                                     FileName + " " + std::strerror(errno));
   }
 }
 
@@ -100,12 +104,6 @@ void PersistentDeviceCodeCache::putItemToDisc(
 
   auto Plugin = detail::getSyclObjImpl(Device)->getPlugin();
 
-  size_t i = 0;
-  std::string FileName;
-  do {
-    FileName = DirName + "/" + std::to_string(i++);
-  } while (OSUtil::isPathPresent(FileName + ".bin"));
-
   unsigned int DeviceNum = 0;
 
   Plugin->call<PiApiKind::piProgramGetInfo>(
@@ -127,6 +125,12 @@ void PersistentDeviceCodeCache::putItemToDisc(
   Plugin->call<PiApiKind::piProgramGetInfo>(NativePrg, PI_PROGRAM_INFO_BINARIES,
                                             sizeof(char *) * Pointers.size(),
                                             Pointers.data(), nullptr);
+  size_t i = 0;
+  std::string FileName;
+  do {
+    FileName = DirName + "/" + std::to_string(i++);
+  } while (OSUtil::isPathPresent(FileName + ".bin") ||
+           OSUtil::isPathPresent(FileName + ".lock"));
 
   try {
     OSUtil::makeDir(DirName.c_str());
@@ -137,9 +141,17 @@ void PersistentDeviceCodeCache::putItemToDisc(
       trace("device binary has been cached: " + FullFileName);
       writeSourceItem(FileName + ".src", Device, Img, SpecConsts,
                       BuildOptionsString);
+    } else {
+      PersistentDeviceCodeCache::trace("cache lock not owned " + FileName);
     }
+  } catch (std::exception &e) {
+    PersistentDeviceCodeCache::trace(
+        std::string("exception encountered making persistent cache: ") +
+        e.what());
   } catch (...) {
-    // If a problem happens on storing cache item, do nothing
+    PersistentDeviceCodeCache::trace(
+        std::string("error outputting persistent cache: ") +
+        std::strerror(errno));
   }
 }