Index: lib/xray/xray_buffer_queue.h
===================================================================
--- lib/xray/xray_buffer_queue.h
+++ lib/xray/xray_buffer_queue.h
@@ -17,8 +17,8 @@
 
 #include "sanitizer_common/sanitizer_atomic.h"
 #include "sanitizer_common/sanitizer_mutex.h"
-#include <deque>
-#include <unordered_set>
+#include <cstdint>
+#include <memory>
 #include <utility>
 
 namespace __xray {
@@ -36,15 +36,23 @@
   };
 
 private:
+  // Size of each individual Buffer.
   size_t BufferSize;
 
   // We use a bool to indicate whether the Buffer has been used in this
   // freelist implementation.
-  std::deque<std::tuple<Buffer, bool>> Buffers;
-  __sanitizer::BlockingMutex Mutex;
-  std::unordered_set<void *> OwnedBuffers;
+  std::unique_ptr<std::tuple<Buffer, bool>[]> Buffers;
+  size_t BufferCount;
+
+  __sanitizer::SpinMutex Mutex;
   __sanitizer::atomic_uint8_t Finalizing;
 
+  // Sorted buffer pointers, making it quick to find buffers that we own.
+  std::unique_ptr<void *[]> OwnedBuffers;
+
+  std::tuple<Buffer, bool> *Next;
+  std::tuple<Buffer, bool> *First;
+
 public:
   enum class ErrorCode : unsigned {
     Ok,
@@ -117,8 +125,9 @@
   /// Buffer is marked 'used' (i.e. has been the result of getBuffer(...) and a
   /// releaseBuffer(...) operation).
   template <class F> void apply(F Fn) {
-    __sanitizer::BlockingMutexLock G(&Mutex);
-    for (const auto &T : Buffers) {
+    __sanitizer::SpinMutexLock G(&Mutex);
+    for (auto I = Buffers.get(); I != Buffers.get() + BufferCount; ++I) {
+      const auto &T = *I;
       if (std::get<1>(T))
         Fn(std::get<0>(T));
     }
Index: lib/xray/xray_buffer_queue.cc
===================================================================
--- lib/xray/xray_buffer_queue.cc
+++ lib/xray/xray_buffer_queue.cc
@@ -16,6 +16,7 @@
 #include "sanitizer_common/sanitizer_common.h"
 #include "sanitizer_common/sanitizer_libc.h"
 
+#include <algorithm>
 #include <cstdlib>
 #include <tuple>
 
@@ -23,18 +24,20 @@
 using namespace __sanitizer;
 
 BufferQueue::BufferQueue(std::size_t B, std::size_t N, bool &Success)
-    : BufferSize(B), Buffers(N), Mutex(), OwnedBuffers(), Finalizing{0} {
-  for (auto &T : Buffers) {
+    : BufferSize(B), Buffers(new std::tuple<Buffer, bool>[N]()), BufferCount(N),
+      Mutex(), Finalizing{0}, OwnedBuffers(new void *[N]()),
+      Next(Buffers.get()), First(nullptr) {
+  for (size_t i = 0; i < BufferCount; ++i) {
+    auto &T = Buffers[i];
     void *Tmp = malloc(BufferSize);
     if (Tmp == nullptr) {
       Success = false;
       return;
     }
-
     auto &Buf = std::get<0>(T);
     Buf.Buffer = Tmp;
     Buf.Size = B;
-    OwnedBuffers.emplace(Tmp);
+    OwnedBuffers[i] = Tmp;
   }
   Success = true;
 }
@@ -42,27 +45,41 @@
 BufferQueue::ErrorCode BufferQueue::getBuffer(Buffer &Buf) {
   if (__sanitizer::atomic_load(&Finalizing, __sanitizer::memory_order_acquire))
     return ErrorCode::QueueFinalizing;
-  __sanitizer::BlockingMutexLock Guard(&Mutex);
-  if (Buffers.empty())
+  __sanitizer::SpinMutexLock Guard(&Mutex);
+
+  if (First != nullptr && Next == First)
     return ErrorCode::NotEnoughMemory;
-  auto &T = Buffers.front();
+  auto &T = *Next;
   auto &B = std::get<0>(T);
   Buf = B;
-  B.Buffer = nullptr;
-  B.Size = 0;
-  Buffers.pop_front();
+  std::get<1>(T) = true;
+  if (First == nullptr)
+    First = Next;
+  ++Next;
+  if (Next == Buffers.get() + BufferCount)
+    Next = Buffers.get();
   return ErrorCode::Ok;
 }
 
 BufferQueue::ErrorCode BufferQueue::releaseBuffer(Buffer &Buf) {
-  if (OwnedBuffers.count(Buf.Buffer) == 0)
+  // Blitz through the buffers array to find the buffer.
+  if (!std::any_of(OwnedBuffers.get(), OwnedBuffers.get() + BufferCount,
+                   [&Buf](void *P) { return P == Buf.Buffer; }))
     return ErrorCode::UnrecognizedBuffer;
-  __sanitizer::BlockingMutexLock Guard(&Mutex);
+  __sanitizer::SpinMutexLock Guard(&Mutex);
+
+  // This points to a semantic bug, we really ought to not be releasing more
+  // buffers than we actually get.
+  if (First == nullptr || First == Next)
+    return ErrorCode::NotEnoughMemory;
 
   // Now that the buffer has been released, we mark it as "used".
-  Buffers.emplace(Buffers.end(), Buf, true /* used */);
+  *First = std::make_tuple(Buf, true);
   Buf.Buffer = nullptr;
   Buf.Size = 0;
+  ++First;
+  if (First == Buffers.get() + BufferCount)
+    First = Buffers.get();
   return ErrorCode::Ok;
 }
 
@@ -74,7 +91,8 @@
 }
 
 BufferQueue::~BufferQueue() {
-  for (auto &T : Buffers) {
+  for (auto I = Buffers.get(); I != Buffers.get() + BufferCount; ++I) {
+    auto &T = *I;
     auto &Buf = std::get<0>(T);
     free(Buf.Buffer);
   }