Merge pull request #8895 from hercules-ci/gc-before-stats

eval: Run a full GC before printing stats

(cherry picked from commit aeea49609be014b1928c95b7ec28dbedeb4f032a)
Change-Id: I47a23d3a7a47ea61d9a2b5727b638f879f3aaf1e

src/libcmd/command.cc

@@ -98,7 +98,7 @@ EvalCommand::EvalCommand()
 EvalCommand::~EvalCommand()
 {
     if (evalState)
-        evalState->printStats();
+        evalState->maybePrintStats();
 }
 
 ref<Store> EvalCommand::getEvalStore()

src/libexpr/eval.cc

@@ -2477,10 +2477,37 @@ bool EvalState::eqValues(Value & v1, Value & v2, const PosIdx pos, std::string_v
     }
 }
 
-void EvalState::printStats()
+bool EvalState::fullGC() {
+#if HAVE_BOEHMGC
+    GC_gcollect();
+    // Check that it ran. We might replace this with a version that uses more
+    // of the boehm API to get this reliably, at a maintenance cost.
+    // We use a 1K margin because technically this has a race condtion, but we
+    // probably won't encounter it in practice, because the CLI isn't concurrent
+    // like that.
+    return GC_get_bytes_since_gc() < 1024;
+#else
+    return false;
+#endif
+}
+
+void EvalState::maybePrintStats()
 {
     bool showStats = getEnv("NIX_SHOW_STATS").value_or("0") != "0";
 
+    if (showStats) {
+        // Make the final heap size more deterministic.
+#if HAVE_BOEHMGC
+        if (!fullGC()) {
+            warn("failed to perform a full GC before reporting stats");
+        }
+#endif
+        printStatistics();
+    }
+}
+
+void EvalState::printStatistics()
+{
     struct rusage buf;
     getrusage(RUSAGE_SELF, &buf);
     float cpuTime = buf.ru_utime.tv_sec + ((float) buf.ru_utime.tv_usec / 1000000);
@@ -2494,7 +2521,7 @@ void EvalState::printStats()
     GC_word heapSize, totalBytes;
     GC_get_heap_usage_safe(&heapSize, 0, 0, 0, &totalBytes);
 #endif
-    if (showStats) {
+
     auto outPath = getEnv("NIX_SHOW_STATS_PATH").value_or("-");
     std::fstream fs;
     if (outPath != "-")
@@ -2594,7 +2621,6 @@ void EvalState::printStats()
         fs << topObj.dump(2) << std::endl;
     }
 }
-}
 
 
 std::string ExternalValueBase::coerceToString(const Pos & pos, NixStringContext & context, bool copyMore, bool copyToStore) const

src/libexpr/eval.hh

@@ -709,9 +709,25 @@ public:
     void concatLists(Value & v, size_t nrLists, Value * * lists, const PosIdx pos, std::string_view errorCtx);
 
     /**
-     * Print statistics.
+     * Print statistics, if enabled.
+     *
+     * Performs a full memory GC before printing the statistics, so that the
+     * GC statistics are more accurate.
      */
-    void printStats();
+    void maybePrintStats();
+
+    /**
+     * Print statistics, unconditionally, cheaply, without performing a GC first.
+     */
+    void printStatistics();
+
+    /**
+     * Perform a full memory garbage collection - not incremental.
+     *
+     * @return true if Nix was built with GC and a GC was performed, false if not.
+     *              The return value is currently not thread safe - just the return value.
+     */
+    bool fullGC();
 
     /**
      * Realise the given context, and return a mapping from the placeholders

src/nix-build/nix-build.cc

@@ -344,7 +344,7 @@ static void main_nix_build(int argc, char * * argv)
         }
     }
 
-    state->printStats();
+    state->maybePrintStats();
 
     auto buildPaths = [&](const std::vector<DerivedPath> & paths) {
         /* Note: we do this even when !printMissing to efficiently

src/nix-env/nix-env.cc

@@ -1531,7 +1531,7 @@ static int main_nix_env(int argc, char * * argv)
 
         op(globals, std::move(opFlags), std::move(opArgs));
 
-        globals.state->printStats();
+        globals.state->maybePrintStats();
 
         return 0;
     }

src/nix-instantiate/nix-instantiate.cc

@@ -189,7 +189,7 @@ static int main_nix_instantiate(int argc, char * * argv)
                 evalOnly, outputKind, xmlOutputSourceLocation, e);
         }
 
-        state->printStats();
+        state->maybePrintStats();
 
         return 0;
     }