Add a ThinLTO cache policy for controlling the maximum cache size in bytes.

This is useful when an upper limit on the cache size needs to be
controlled independently of the amount of the amount of free space.

One use case is a machine with a large number of cache directories
(e.g. a buildbot slave hosting a large number of independent build
jobs). By imposing an upper size limit on each cache directory,
users can more easily estimate the server's capacity.

Differential Revision: https://reviews.llvm.org/D34547

llvm-svn: 306126

6 files changed, 107 insertions, 22 deletions

diff --git a/clang/docs/ThinLTO.rst b/clang/docs/ThinLTO.rst
index 71a23380efb..31fff51a61e 100644
--- a/clang/docs/ThinLTO.rst
+++ b/clang/docs/ThinLTO.rst
@@ -146,6 +146,18 @@ Possible key-value pairs are:
   disk space. A value over 100 is invalid. A value of 0 disables the percentage
   size-based pruning. The default is 75%.
 
+- ``cache_size_bytes=X``, ``cache_size_bytes=Xk``, ``cache_size_bytes=Xm``,
+  ``cache_size_bytes=Xg``:
+  Sets the maximum size for the cache directory to ``X`` bytes (or KB, MB,
+  GB respectively). A value over the amount of available space on the disk
+  will be reduced to the amount of available space. A value of 0 disables
+  the byte size-based pruning. The default is no byte size-based pruning.
+
+  Note that ThinLTO will apply both size-based pruning policies simultaneously,
+  and changing one does not affect the other. For example, a policy of
+  ``cache_size_bytes=1g`` on its own will cause both the 1GB and default 75%
+  policies to be applied unless the default ``cache_size`` is overridden.
+
 - ``prune_after=Xs``, ``prune_after=Xm``, ``prune_after=Xh``: Sets the
   expiration time for cache files to ``X`` seconds (or minutes, hours
   respectively).  When a file hasn't been accessed for ``prune_after`` seconds,
diff --git a/lld/test/ELF/lto/cache.ll b/lld/test/ELF/lto/cache.ll
index 55e3a3d6f6c..8ad992b22a6 100644
--- a/lld/test/ELF/lto/cache.ll
+++ b/lld/test/ELF/lto/cache.ll
@@ -12,6 +12,17 @@
 ; Two cached objects, plus a timestamp file and "foo", minus the file we removed.
 ; RUN: ls %t.cache | count 4
 
+; Create a file of size 64KB.
+; RUN: %python -c "print ' ' * 65536" > %t.cache/llvmcache-foo
+
+; This should leave the file in place.
+; RUN: ld.lld --thinlto-cache-dir=%t.cache --thinlto-cache-policy cache_size_bytes=128k -o %t3 %t2.o %t.o
+; RUN: ls %t.cache | count 5
+
+; This should remove it.
+; RUN: ld.lld --thinlto-cache-dir=%t.cache --thinlto-cache-policy cache_size_bytes=32k -o %t3 %t2.o %t.o
+; RUN: ls %t.cache | count 4
+
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
diff --git a/llvm/include/llvm/LTO/legacy/ThinLTOCodeGenerator.h b/llvm/include/llvm/LTO/legacy/ThinLTOCodeGenerator.h
index f9545333aab..14f0c48266f 100644
--- a/llvm/include/llvm/LTO/legacy/ThinLTOCodeGenerator.h
+++ b/llvm/include/llvm/LTO/legacy/ThinLTOCodeGenerator.h
@@ -177,7 +177,7 @@ public:
    */
   void setMaxCacheSizeRelativeToAvailableSpace(unsigned Percentage) {
     if (Percentage)
-      CacheOptions.Policy.PercentageOfAvailableSpace = Percentage;
+      CacheOptions.Policy.MaxSizePercentageOfAvailableSpace = Percentage;
   }
 
   /**@}*/
diff --git a/llvm/include/llvm/Support/CachePruning.h b/llvm/include/llvm/Support/CachePruning.h
index e826938878e..46e34358573 100644
--- a/llvm/include/llvm/Support/CachePruning.h
+++ b/llvm/include/llvm/Support/CachePruning.h
@@ -39,8 +39,13 @@ struct CachePruningPolicy {
   /// 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 disables the
-  /// size-based pruning.
-  unsigned PercentageOfAvailableSpace = 75;
+  /// percentage size-based pruning.
+  unsigned MaxSizePercentageOfAvailableSpace = 75;
+
+  /// The maximum size for the cache directory in bytes. A value over the amount
+  /// of available space on the disk will be reduced to the amount of available
+  /// space. A value of 0 disables the absolute size-based pruning.
+  uint64_t MaxSizeBytes = 0;
 };
 
 /// Parse the given string as a cache pruning policy. Defaults are taken from a
diff --git a/llvm/lib/Support/CachePruning.cpp b/llvm/lib/Support/CachePruning.cpp
index aca12363956..303ad219746 100644
--- a/llvm/lib/Support/CachePruning.cpp
+++ b/llvm/lib/Support/CachePruning.cpp
@@ -79,10 +79,10 @@ llvm::parseCachePruningPolicy(StringRef PolicyStr) {
         return DurationOrErr.takeError();
       Policy.Expiration = *DurationOrErr;
     } else if (Key == "cache_size") {
-      if (Value.back() != '%')
-        return make_error<StringError>("'" + Value + "' must be a percentage",
-                                       inconvertibleErrorCode());
-      StringRef SizeStr = Value.slice(0, Value.size() - 1);
+    if (Value.back() != '%')
+      return make_error<StringError>("'" + Value + "' must be a percentage",
+                                     inconvertibleErrorCode());
+      StringRef SizeStr = Value.drop_back();
       uint64_t Size;
       if (SizeStr.getAsInteger(0, Size))
         return make_error<StringError>("'" + SizeStr + "' not an integer",
@@ -91,7 +91,28 @@ llvm::parseCachePruningPolicy(StringRef PolicyStr) {
         return make_error<StringError>("'" + SizeStr +
                                            "' must be between 0 and 100",
                                        inconvertibleErrorCode());
-      Policy.PercentageOfAvailableSpace = Size;
+      Policy.MaxSizePercentageOfAvailableSpace = Size;
+    } else if (Key == "cache_size_bytes") {
+      uint64_t Mult = 1;
+      switch (Value.back()) {
+      case 'k':
+        Mult = 1024;
+        Value = Value.drop_back();
+        break;
+      case 'm':
+        Mult = 1024 * 1024;
+        Value = Value.drop_back();
+        break;
+      case 'g':
+        Mult = 1024 * 1024 * 1024;
+        Value = Value.drop_back();
+        break;
+      }
+      uint64_t Size;
+      if (Value.getAsInteger(0, Size))
+        return make_error<StringError>("'" + Value + "' not an integer",
+                                       inconvertibleErrorCode());
+      Policy.MaxSizeBytes = Size * Mult;
     } else {
       return make_error<StringError>("Unknown key: '" + Key + "'",
                                      inconvertibleErrorCode());
@@ -115,11 +136,12 @@ bool llvm::pruneCache(StringRef Path, CachePruningPolicy Policy) {
   if (!isPathDir)
     return false;
 
-  Policy.PercentageOfAvailableSpace =
-      std::min(Policy.PercentageOfAvailableSpace, 100u);
+  Policy.MaxSizePercentageOfAvailableSpace =
+      std::min(Policy.MaxSizePercentageOfAvailableSpace, 100u);
 
   if (Policy.Expiration == seconds(0) &&
-      Policy.PercentageOfAvailableSpace == 0) {
+      Policy.MaxSizePercentageOfAvailableSpace == 0 &&
+      Policy.MaxSizeBytes == 0) {
     DEBUG(dbgs() << "No pruning settings set, exit early\n");
     // Nothing will be pruned, early exit
     return false;
@@ -157,7 +179,8 @@ bool llvm::pruneCache(StringRef Path, CachePruningPolicy Policy) {
     writeTimestampFile(TimestampFile);
   }
 
-  bool ShouldComputeSize = (Policy.PercentageOfAvailableSpace > 0);
+  bool ShouldComputeSize =
+      (Policy.MaxSizePercentageOfAvailableSpace > 0 || Policy.MaxSizeBytes > 0);
 
   // Keep track of space
   std::set<std::pair<uint64_t, std::string>> FileSizes;
@@ -216,14 +239,22 @@ bool llvm::pruneCache(StringRef Path, CachePruningPolicy Policy) {
     }
     sys::fs::space_info SpaceInfo = ErrOrSpaceInfo.get();
     auto AvailableSpace = TotalSize + SpaceInfo.free;
-    auto FileAndSize = FileSizes.rbegin();
+
+    if (Policy.MaxSizePercentageOfAvailableSpace == 0)
+      Policy.MaxSizePercentageOfAvailableSpace = 100;
+    if (Policy.MaxSizeBytes == 0)
+      Policy.MaxSizeBytes = AvailableSpace;
+    auto TotalSizeTarget = std::min<uint64_t>(
+        AvailableSpace * Policy.MaxSizePercentageOfAvailableSpace / 100ull,
+        Policy.MaxSizeBytes);
+
     DEBUG(dbgs() << "Occupancy: " << ((100 * TotalSize) / AvailableSpace)
-                 << "% target is: " << Policy.PercentageOfAvailableSpace
-                 << "\n");
+                 << "% target is: " << Policy.MaxSizePercentageOfAvailableSpace
+                 << "%, " << Policy.MaxSizeBytes << " bytes\n");
+
+    auto FileAndSize = FileSizes.rbegin();
     // Remove the oldest accessed files first, till we get below the threshold
-    while (((100 * TotalSize) / AvailableSpace) >
-               Policy.PercentageOfAvailableSpace &&
-           FileAndSize != FileSizes.rend()) {
+    while (TotalSize > TotalSizeTarget && FileAndSize != FileSizes.rend()) {
       // Remove the file.
       sys::fs::remove(FileAndSize->second);
       // Update size
diff --git a/llvm/unittests/Support/CachePruningTest.cpp b/llvm/unittests/Support/CachePruningTest.cpp
index 04ac0d09b49..97d554eabc3 100644
--- a/llvm/unittests/Support/CachePruningTest.cpp
+++ b/llvm/unittests/Support/CachePruningTest.cpp
@@ -18,7 +18,7 @@ TEST(CachePruningPolicyParser, Empty) {
   ASSERT_TRUE(bool(P));
   EXPECT_EQ(std::chrono::seconds(1200), P->Interval);
   EXPECT_EQ(std::chrono::hours(7 * 24), P->Expiration);
-  EXPECT_EQ(75u, P->PercentageOfAvailableSpace);
+  EXPECT_EQ(75u, P->MaxSizePercentageOfAvailableSpace);
 }
 
 TEST(CachePruningPolicyParser, Interval) {
@@ -39,10 +39,30 @@ TEST(CachePruningPolicyParser, Expiration) {
   EXPECT_EQ(std::chrono::seconds(1), P->Expiration);
 }
 
-TEST(CachePruningPolicyParser, PercentageOfAvailableSpace) {
+TEST(CachePruningPolicyParser, MaxSizePercentageOfAvailableSpace) {
   auto P = parseCachePruningPolicy("cache_size=100%");
   ASSERT_TRUE(bool(P));
-  EXPECT_EQ(100u, P->PercentageOfAvailableSpace);
+  EXPECT_EQ(100u, P->MaxSizePercentageOfAvailableSpace);
+  EXPECT_EQ(0u, P->MaxSizeBytes);
+}
+
+TEST(CachePruningPolicyParser, MaxSizeBytes) {
+  auto P = parseCachePruningPolicy("cache_size_bytes=1");
+  ASSERT_TRUE(bool(P));
+  EXPECT_EQ(75u, P->MaxSizePercentageOfAvailableSpace);
+  EXPECT_EQ(1u, P->MaxSizeBytes);
+  P = parseCachePruningPolicy("cache_size_bytes=2k");
+  ASSERT_TRUE(bool(P));
+  EXPECT_EQ(75u, P->MaxSizePercentageOfAvailableSpace);
+  EXPECT_EQ(2u * 1024u, P->MaxSizeBytes);
+  P = parseCachePruningPolicy("cache_size_bytes=3m");
+  ASSERT_TRUE(bool(P));
+  EXPECT_EQ(75u, P->MaxSizePercentageOfAvailableSpace);
+  EXPECT_EQ(3u * 1024u * 1024u, P->MaxSizeBytes);
+  P = parseCachePruningPolicy("cache_size_bytes=4g");
+  ASSERT_TRUE(bool(P));
+  EXPECT_EQ(75u, P->MaxSizePercentageOfAvailableSpace);
+  EXPECT_EQ(4ull * 1024ull * 1024ull * 1024ull, P->MaxSizeBytes);
 }
 
 TEST(CachePruningPolicyParser, Multiple) {
@@ -50,7 +70,7 @@ TEST(CachePruningPolicyParser, Multiple) {
   ASSERT_TRUE(bool(P));
   EXPECT_EQ(std::chrono::seconds(1200), P->Interval);
   EXPECT_EQ(std::chrono::seconds(1), P->Expiration);
-  EXPECT_EQ(50u, P->PercentageOfAvailableSpace);
+  EXPECT_EQ(50u, P->MaxSizePercentageOfAvailableSpace);
 }
 
 TEST(CachePruningPolicyParser, Errors) {
@@ -66,6 +86,12 @@ TEST(CachePruningPolicyParser, Errors) {
             toString(parseCachePruningPolicy("cache_size=foo%").takeError()));
   EXPECT_EQ("'101' must be between 0 and 100",
             toString(parseCachePruningPolicy("cache_size=101%").takeError()));
+  EXPECT_EQ(
+      "'foo' not an integer",
+      toString(parseCachePruningPolicy("cache_size_bytes=foo").takeError()));
+  EXPECT_EQ(
+      "'foo' not an integer",
+      toString(parseCachePruningPolicy("cache_size_bytes=foom").takeError()));
   EXPECT_EQ("Unknown key: 'foo'",
             toString(parseCachePruningPolicy("foo=bar").takeError()));
 }