llvm-project/compiler-rt/lib/scudo/scudo_tsd.h

67 lines
1.6 KiB
C
Raw Normal View History

//===-- scudo_tsd.h ---------------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
///
/// Scudo thread specific data definition.
/// Implementation will differ based on the thread local storage primitives
/// offered by the underlying platform.
///
//===----------------------------------------------------------------------===//
#ifndef SCUDO_TSD_H_
#define SCUDO_TSD_H_
#include "scudo_allocator.h"
#include "scudo_utils.h"
#include <pthread.h>
namespace __scudo {
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
struct ALIGNED(SANITIZER_CACHE_LINE_SIZE) ScudoTSD {
AllocatorCacheT Cache;
uptr QuarantineCachePlaceHolder[4];
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
void init();
void commitBack();
INLINE bool tryLock() {
if (Mutex.TryLock()) {
atomic_store_relaxed(&Precedence, 0);
return true;
}
if (atomic_load_relaxed(&Precedence) == 0)
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
atomic_store_relaxed(&Precedence, static_cast<uptr>(
MonotonicNanoTime() >> FIRST_32_SECOND_64(16, 0)));
return false;
}
INLINE void lock() {
atomic_store_relaxed(&Precedence, 0);
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
Mutex.Lock();
}
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
INLINE void unlock() { Mutex.Unlock(); }
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
INLINE uptr getPrecedence() { return atomic_load_relaxed(&Precedence); }
private:
StaticSpinMutex Mutex;
[scudo] Improve the scalability of the shared TSD model Summary: The shared TSD model in its current form doesn't scale. Here is an example of rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core machines (defaulting to a `CompactSizeClassMap` and no Quarantine): - with tcmalloc: 337K reqs/sec, peak RSS of 338MB; - with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB; - with scudo (shared): 241K reqs/sec, peak RSS of 324MB. This isn't great, since the exclusive model uses a lot of memory, while the shared model doesn't even come close to be competitive. This is mostly due to the fact that we are consistently scanning the TSD pool starting at index 0 for an available TSD, which can result in a lot of failed lock attempts, and touching some memory that needs not be touched. This CL attempts to make things better in most situations: - first, use a thread local variable on Linux (intead of pthread APIs) to store the current TSD in the shared model; - move the locking boolean out of the TSD: this allows the compiler to use a register and potentially optimize out a branch instead of reading it from the TSD everytime (we also save a tiny bit of memory per TSD); - 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so store the `Precedence` in a `uptr` instead of a `u64`. We lose some nanoseconds of precision and we'll wrap around at some point, but the benefit is worth it; - change a `CHECK` to a `DCHECK`: this should never happen, but if something is ever terribly wrong, we'll crash on a near null AV if the TSD happens to be null; - based on an idea by dvyukov@, we are implementing a bound random scan for an available TSD. This requires computing the coprimes for the number of TSDs, and attempting to lock up to 4 TSDs in an random order before falling back to the current one. This is obviously slightly more expansive when we have just 2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still basically corresponds to the moment of the first contention on a TSD. To seed on random choice, we use the precedence of the current TSD since it is very likely to be non-zero (since we are in the slow path after a failed `tryLock`) With those modifications, the benchmark yields to: - with scudo (shared): 330K reqs/sec, peak RSS of 327MB. So the shared model for this specific situation not only becomes competitive but outperforms the exclusive model. I experimented with some values greater than 4 for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just sticking with the current TSD is also a tad slower. Numbers on platforms with less cores (eg: Android) remain similar. Reviewers: alekseyshl, dvyukov, javed.absar Reviewed By: alekseyshl, dvyukov Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers Differential Revision: https://reviews.llvm.org/D47289 llvm-svn: 334410
2018-06-11 22:50:31 +08:00
atomic_uintptr_t Precedence;
};
void initThread(bool MinimalInit);
// TSD model specific fastpath functions definitions.
#include "scudo_tsd_exclusive.inc"
#include "scudo_tsd_shared.inc"
} // namespace __scudo
#endif // SCUDO_TSD_H_