Improved ThreadAlloc::get API

Made the API so that get always returns an initialised Alloc*.  Added
new fast path that doesn't perform checking, but can lead to very slow
behaviour if called and reused.
This commit is contained in:
Matthew Parkinson
2019-07-15 15:02:47 +01:00
parent 4ce371f936
commit df1896d55f
6 changed files with 44 additions and 21 deletions

View File

@@ -127,10 +127,11 @@ namespace snmalloc
*/
static void inner_release()
{
if (get() != &GlobalPlaceHolder)
Alloc*& a = get_noncachable();
if (a != &GlobalPlaceHolder)
{
current_alloc_pool()->release(get());
get() = &GlobalPlaceHolder;
current_alloc_pool()->release(a);
a = &GlobalPlaceHolder;
}
}
@@ -152,13 +153,38 @@ namespace snmalloc
/**
* Public interface, returns the allocator for this thread, constructing
* one if necessary.
*
* If no operations have been performed on an allocator returned by either
* `get()` nor `get_noncachable`, then the value contained in the return
* will be an Alloc* that will always use the slow path. The Alloc*& will
* be updated, and is performant to use for subsequent calls.
*
* Only use this API if you intend to use the returned allocator just once
* per call, you store the indirection (Alloc*&) rather than (Alloc*), or if
* you know other calls have already been made to the allocator.
*/
static inline Alloc*& get()
static inline Alloc*& get_noncachable()
{
static thread_local Alloc* alloc = &GlobalPlaceHolder;
return alloc;
}
/**
* Public interface, returns the allocator for this thread, constructing
* one if necessary.
*
* The returned Alloc* is guaranteed to be initialised. This incurs a cost,
* so use `get_noncachable` if you can meet its criteria.
*/
static SNMALLOC_FAST_PATH Alloc* get()
{
auto alloc = get_noncachable();
auto new_alloc = lazy_replacement(alloc);
return (likely(new_alloc == nullptr)) ?
alloc :
reinterpret_cast<Alloc*>(new_alloc);
}
static void register_cleanup()
{
static thread_local OnDestruct<ThreadAllocThreadDestructor::inner_release>
@@ -195,7 +221,7 @@ namespace snmalloc
*/
SNMALLOC_SLOW_PATH inline void* lazy_replacement_slow()
{
auto*& local_alloc = ThreadAlloc::get();
auto*& local_alloc = ThreadAlloc::get_noncachable();
if ((local_alloc != nullptr) && (local_alloc != &GlobalPlaceHolder))
{
return local_alloc;

View File

@@ -37,7 +37,7 @@ int main()
oe_end = (uint8_t*)oe_base + size;
std::cout << "Allocated region " << oe_base << " - " << oe_end << std::endl;
auto& a = ThreadAlloc::get();
auto a = ThreadAlloc::get();
for (size_t i = 0; i < 1000; i++)
{

View File

@@ -7,7 +7,7 @@ using namespace snmalloc;
void test_alloc_dealloc_64k()
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
constexpr size_t count = 1 << 12;
constexpr size_t outer_count = 12;
@@ -39,7 +39,7 @@ void test_alloc_dealloc_64k()
void test_random_allocation()
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
std::unordered_set<void*> allocated;
constexpr size_t count = 10000;
@@ -91,7 +91,7 @@ void test_random_allocation()
void test_calloc()
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
for (size_t size = 16; size <= (1 << 24); size <<= 1)
{
@@ -162,7 +162,7 @@ void test_double_alloc()
void test_external_pointer()
{
// Malloc does not have an external pointer querying mechanism.
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
for (uint8_t sc = 0; sc < NUM_SIZECLASSES; sc++)
{
@@ -208,7 +208,7 @@ void test_external_pointer_large()
{
xoroshiro::p128r64 r;
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
constexpr size_t count_log = snmalloc::bits::is64() ? 5 : 3;
constexpr size_t count = 1 << count_log;
@@ -244,7 +244,7 @@ void test_external_pointer_large()
void test_external_pointer_dealloc_bug()
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
constexpr size_t count = (SUPERSLAB_SIZE / SLAB_SIZE) * 2;
void* allocs[count];
@@ -268,7 +268,7 @@ void test_external_pointer_dealloc_bug()
void test_alloc_16M()
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
// sizes >= 16M use large_alloc
const size_t size = 16'000'000;
@@ -279,7 +279,7 @@ void test_alloc_16M()
void test_calloc_16M()
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
// sizes >= 16M use large_alloc
const size_t size = 16'000'000;

View File

@@ -75,7 +75,7 @@ size_t swapcount;
void test_tasks_f(size_t id)
{
Alloc*& a = ThreadAlloc::get();
Alloc* a = ThreadAlloc::get();
xoroshiro::p128r32 r(id + 5000);
for (size_t n = 0; n < swapcount; n++)
@@ -100,7 +100,7 @@ void test_tasks_f(size_t id)
void test_tasks(size_t num_tasks, size_t count, size_t size)
{
Alloc*& a = ThreadAlloc::get();
Alloc* a = ThreadAlloc::get();
contention = new std::atomic<size_t*>[size];
xoroshiro::p128r32 r;

View File

@@ -49,7 +49,7 @@ namespace test
void test_external_pointer(xoroshiro::p128r64& r)
{
auto& alloc = ThreadAlloc::get();
auto alloc = ThreadAlloc::get();
#ifdef NDEBUG
static constexpr size_t iterations = 10000000;
#else
@@ -79,9 +79,6 @@ namespace test
int main(int, char**)
{
xoroshiro::p128r64 r;
// Force a per-thread allocator to actually exist.
void* p = ThreadAlloc::get()->alloc(16);
ThreadAlloc::get()->dealloc(p);
#if NDEBUG
size_t nn = 30;
#else

View File

@@ -7,7 +7,7 @@ using namespace snmalloc;
template<ZeroMem zero_mem>
void test_alloc_dealloc(size_t count, size_t size, bool write)
{
auto*& alloc = ThreadAlloc::get();
auto* alloc = ThreadAlloc::get();
DO_TIME(
"Count: " << std::setw(6) << count << ", Size: " << std::setw(6) << size