[llvm] r265209 - Add Cache Pruning support

Mehdi Amini via llvm-commits llvm-commits at lists.llvm.org
Fri Apr 1 20:28:27 PDT 2016


Author: mehdi_amini
Date: Fri Apr  1 22:28:26 2016
New Revision: 265209

URL: http://llvm.org/viewvc/llvm-project?rev=265209&view=rev
Log:
Add Cache Pruning support

Incremental LTO will usea cache to store object files.
This patch handles the pruning part of the cache, exposing
a few knobs:

- Pruning interval: the implementation keeps a "timestamp" file in the
  directory and will scan it only after a given interval since the
  last modification of the timestamp file. This is for performance
  purpose, we don't want to scan continuously the folder.
- Entry expiration: this is the time after which a file that hasn't
  been used is remove from the cache.
- Maximum size: expressed in percentage of the available disk space,
  it helps to avoid that we blow up the disk space.

http://reviews.llvm.org/D18422

From: Mehdi Amini <mehdi.amini at apple.com>

Added:
    llvm/trunk/include/llvm/Support/CachePruning.h
    llvm/trunk/lib/Support/CachePruning.cpp
Modified:
    llvm/trunk/lib/Support/CMakeLists.txt

Added: llvm/trunk/include/llvm/Support/CachePruning.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Support/CachePruning.h?rev=265209&view=auto
==============================================================================
--- llvm/trunk/include/llvm/Support/CachePruning.h (added)
+++ llvm/trunk/include/llvm/Support/CachePruning.h Fri Apr  1 22:28:26 2016
@@ -0,0 +1,69 @@
+//=- CachePruning.h - Helper to manage the pruning of a cache dir -*- C++ -*-=//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements pruning of a directory intended for cache storage, using
+// various policies.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_CACHE_PRUNING_H
+#define LLVM_SUPPORT_CACHE_PRUNING_H
+
+#include "llvm/ADT/StringRef.h"
+
+namespace llvm {
+
+/// Handle pruning a directory provided a path and some options to control what
+/// to prune.
+class CachePruning {
+public:
+  /// Prepare to prune \p Path.
+  CachePruning(StringRef Path) : Path(Path) {}
+
+  /// Define the pruning interval. This is intended to be used to avoid scanning
+  /// the directory too often. It does not impact the decision of which file to
+  /// prune. A value of 0 forces the scan to occurs.
+  CachePruning &setPruningInterval(int PruningInterval) {
+    Interval = PruningInterval;
+    return *this;
+  }
+
+  /// Define the expiration for a file. When a file hasn't been accessed for
+  /// \p ExpireAfter seconds, it is removed from the cache. A value of 0 disable
+  /// the expiration-based pruning.
+  CachePruning &setEntryExpiration(unsigned ExpireAfter) {
+    Expiration = ExpireAfter;
+    return *this;
+  }
+
+  /// Define the maximum size for the cache directory, in terms of percentage of
+  /// the available space on the the disk. Set to 100 to indicate no limit, 50
+  /// to indicate that the cache size will not be left over half the
+  /// available disk space. A value over 100 will be reduced to 100. A value of
+  /// 0 disable the size-based pruning.
+  CachePruning &setMaxSize(unsigned Percentage) {
+    PercentageOfAvailableSpace = std::min(100u, Percentage);
+    return *this;
+  }
+
+  /// Peform pruning using the supplied options, returns true if pruning
+  /// occured, i.e. if PruningInterval was expired.
+  bool prune();
+
+private:
+  // Options that matches the setters above.
+  std::string Path;
+  unsigned Expiration = 0;
+  unsigned Interval = 0;
+  unsigned PercentageOfAvailableSpace = 0;
+};
+
+} // namespace llvm
+
+#endif
\ No newline at end of file

Modified: llvm/trunk/lib/Support/CMakeLists.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/CMakeLists.txt?rev=265209&r1=265208&r2=265209&view=diff
==============================================================================
--- llvm/trunk/lib/Support/CMakeLists.txt (original)
+++ llvm/trunk/lib/Support/CMakeLists.txt Fri Apr  1 22:28:26 2016
@@ -35,6 +35,7 @@ add_llvm_library(LLVMSupport
   Allocator.cpp
   BlockFrequency.cpp
   BranchProbability.cpp
+  CachePruning.cpp
   circular_raw_ostream.cpp
   COM.cpp
   CommandLine.cpp

Added: llvm/trunk/lib/Support/CachePruning.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/CachePruning.cpp?rev=265209&view=auto
==============================================================================
--- llvm/trunk/lib/Support/CachePruning.cpp (added)
+++ llvm/trunk/lib/Support/CachePruning.cpp Fri Apr  1 22:28:26 2016
@@ -0,0 +1,130 @@
+//===-CachePruning.cpp - LLVM Cache Directory Pruning ---------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the pruning of a directory based on least recently used.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/CachePruning.h"
+
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/raw_ostream.h"
+
+#include <set>
+
+using namespace llvm;
+
+/// Write a new timestamp file with the given path. This is used for the pruning
+/// interval option.
+static void writeTimestampFile(StringRef TimestampFile) {
+  std::error_code EC;
+  raw_fd_ostream Out(TimestampFile.str(), EC, sys::fs::F_None);
+}
+
+/// Prune the cache of files that haven't been accessed in a long time.
+bool CachePruning::prune() {
+  SmallString<128> TimestampFile(Path);
+  sys::path::append(TimestampFile, "llvmcache.timestamp");
+
+  if (Expiration == 0 && PercentageOfAvailableSpace == 0)
+    // Nothing will be pruned, early exit
+    return false;
+
+  // Try to stat() the timestamp file.
+  sys::fs::file_status FileStatus;
+  sys::TimeValue CurrentTime = sys::TimeValue::now();
+  if (sys::fs::status(TimestampFile, FileStatus)) {
+    if (errno == ENOENT) {
+      // If the timestamp file wasn't there, create one now.
+      writeTimestampFile(TimestampFile);
+    } else {
+      // Unknown error?
+      return false;
+    }
+  } else {
+    if (Interval) {
+      // Check whether the time stamp is older than our pruning interval.
+      // If not, do nothing.
+      sys::TimeValue TimeStampModTime = FileStatus.getLastModificationTime();
+      auto TimeInterval = sys::TimeValue(sys::TimeValue::SecondsType(Interval));
+      if (CurrentTime - TimeStampModTime <= TimeInterval)
+        return false;
+    }
+    // Write a new timestamp file so that nobody else attempts to prune.
+    // There is a benign race condition here, if two processes happen to
+    // notice at the same time that the timestamp is out-of-date.
+    writeTimestampFile(TimestampFile);
+  }
+
+  bool ShouldComputeSize = (PercentageOfAvailableSpace > 0);
+
+  // Keep track of space
+  std::set<std::pair<uint64_t, std::string>> FileSizes;
+  uint64_t TotalSize = 0;
+  // Helper to add a path to the set of files to consider for size-based
+  // pruning, sorted by last accessed time.
+  auto AddToFileListForSizePruning =
+      [&](StringRef Path, sys::TimeValue FileAccessTime) {
+        if (!ShouldComputeSize)
+          return;
+        TotalSize += FileStatus.getSize();
+        FileSizes.insert(
+            std::make_pair(FileAccessTime.seconds(), std::string(Path)));
+      };
+
+  // Walk the entire directory cache, looking for unused files.
+  std::error_code EC;
+  SmallString<128> CachePathNative;
+  sys::path::native(Path, CachePathNative);
+  auto TimeExpiration = sys::TimeValue(sys::TimeValue::SecondsType(Expiration));
+  // Walk all of the files within this directory.
+  for (sys::fs::directory_iterator File(CachePathNative, EC), FileEnd;
+       File != FileEnd && !EC; File.increment(EC)) {
+    // Do not touch the timestamp.
+    if (File->path() == TimestampFile)
+      continue;
+
+    // Look at this file. If we can't stat it, there's nothing interesting
+    // there.
+    if (sys::fs::status(File->path(), FileStatus))
+      continue;
+
+    // If the file hasn't been used recently enough, delete it
+    sys::TimeValue FileAccessTime = FileStatus.getLastAccessedTime();
+    if (CurrentTime - FileAccessTime > TimeExpiration) {
+      sys::fs::remove(File->path());
+      continue;
+    }
+
+    // Leave it here for now, but add it to the list of size-based pruning.
+    AddToFileListForSizePruning(File->path(), FileAccessTime);
+  }
+
+  // Prune for size now if needed
+  if (ShouldComputeSize) {
+    auto ErrOrSpaceInfo = sys::fs::disk_space(Path);
+    if (!ErrOrSpaceInfo) {
+      report_fatal_error("Can't get available size");
+    }
+    sys::fs::space_info SpaceInfo = ErrOrSpaceInfo.get();
+    auto AvailableSpace = TotalSize + SpaceInfo.free;
+    auto FileAndSize = FileSizes.rbegin();
+    // Remove the oldest accessed files first, till we get below the threshold
+    while (((100 * TotalSize) / AvailableSpace) > PercentageOfAvailableSpace &&
+           FileAndSize != FileSizes.rend()) {
+      // Remove the file.
+      sys::fs::remove(FileAndSize->second);
+      // Update size
+      TotalSize -= FileAndSize->first;
+      ++FileAndSize;
+    }
+  }
+  return true;
+}




More information about the llvm-commits mailing list