diff options
Diffstat (limited to 'src/sync/pool.go')
-rw-r--r-- | src/sync/pool.go | 297 |
1 files changed, 297 insertions, 0 deletions
diff --git a/src/sync/pool.go b/src/sync/pool.go new file mode 100644 index 0000000..cf01e2e --- /dev/null +++ b/src/sync/pool.go @@ -0,0 +1,297 @@ +// Copyright 2013 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license that can be found in the LICENSE file. + +package sync + +import ( + "internal/race" + "runtime" + "sync/atomic" + "unsafe" +) + +// A Pool is a set of temporary objects that may be individually saved and +// retrieved. +// +// Any item stored in the Pool may be removed automatically at any time without +// notification. If the Pool holds the only reference when this happens, the +// item might be deallocated. +// +// A Pool is safe for use by multiple goroutines simultaneously. +// +// Pool's purpose is to cache allocated but unused items for later reuse, +// relieving pressure on the garbage collector. That is, it makes it easy to +// build efficient, thread-safe free lists. However, it is not suitable for all +// free lists. +// +// An appropriate use of a Pool is to manage a group of temporary items +// silently shared among and potentially reused by concurrent independent +// clients of a package. Pool provides a way to amortize allocation overhead +// across many clients. +// +// An example of good use of a Pool is in the fmt package, which maintains a +// dynamically-sized store of temporary output buffers. The store scales under +// load (when many goroutines are actively printing) and shrinks when +// quiescent. +// +// On the other hand, a free list maintained as part of a short-lived object is +// not a suitable use for a Pool, since the overhead does not amortize well in +// that scenario. It is more efficient to have such objects implement their own +// free list. +// +// A Pool must not be copied after first use. +// +// In the terminology of the Go memory model, a call to Put(x) “synchronizes before” +// a call to Get returning that same value x. +// Similarly, a call to New returning x “synchronizes before” +// a call to Get returning that same value x. +type Pool struct { + noCopy noCopy + + local unsafe.Pointer // local fixed-size per-P pool, actual type is [P]poolLocal + localSize uintptr // size of the local array + + victim unsafe.Pointer // local from previous cycle + victimSize uintptr // size of victims array + + // New optionally specifies a function to generate + // a value when Get would otherwise return nil. + // It may not be changed concurrently with calls to Get. + New func() any +} + +// Local per-P Pool appendix. +type poolLocalInternal struct { + private any // Can be used only by the respective P. + shared poolChain // Local P can pushHead/popHead; any P can popTail. +} + +type poolLocal struct { + poolLocalInternal + + // Prevents false sharing on widespread platforms with + // 128 mod (cache line size) = 0 . + pad [128 - unsafe.Sizeof(poolLocalInternal{})%128]byte +} + +// from runtime +func fastrandn(n uint32) uint32 + +var poolRaceHash [128]uint64 + +// poolRaceAddr returns an address to use as the synchronization point +// for race detector logic. We don't use the actual pointer stored in x +// directly, for fear of conflicting with other synchronization on that address. +// Instead, we hash the pointer to get an index into poolRaceHash. +// See discussion on golang.org/cl/31589. +func poolRaceAddr(x any) unsafe.Pointer { + ptr := uintptr((*[2]unsafe.Pointer)(unsafe.Pointer(&x))[1]) + h := uint32((uint64(uint32(ptr)) * 0x85ebca6b) >> 16) + return unsafe.Pointer(&poolRaceHash[h%uint32(len(poolRaceHash))]) +} + +// Put adds x to the pool. +func (p *Pool) Put(x any) { + if x == nil { + return + } + if race.Enabled { + if fastrandn(4) == 0 { + // Randomly drop x on floor. + return + } + race.ReleaseMerge(poolRaceAddr(x)) + race.Disable() + } + l, _ := p.pin() + if l.private == nil { + l.private = x + } else { + l.shared.pushHead(x) + } + runtime_procUnpin() + if race.Enabled { + race.Enable() + } +} + +// Get selects an arbitrary item from the Pool, removes it from the +// Pool, and returns it to the caller. +// Get may choose to ignore the pool and treat it as empty. +// Callers should not assume any relation between values passed to Put and +// the values returned by Get. +// +// If Get would otherwise return nil and p.New is non-nil, Get returns +// the result of calling p.New. +func (p *Pool) Get() any { + if race.Enabled { + race.Disable() + } + l, pid := p.pin() + x := l.private + l.private = nil + if x == nil { + // Try to pop the head of the local shard. We prefer + // the head over the tail for temporal locality of + // reuse. + x, _ = l.shared.popHead() + if x == nil { + x = p.getSlow(pid) + } + } + runtime_procUnpin() + if race.Enabled { + race.Enable() + if x != nil { + race.Acquire(poolRaceAddr(x)) + } + } + if x == nil && p.New != nil { + x = p.New() + } + return x +} + +func (p *Pool) getSlow(pid int) any { + // See the comment in pin regarding ordering of the loads. + size := runtime_LoadAcquintptr(&p.localSize) // load-acquire + locals := p.local // load-consume + // Try to steal one element from other procs. + for i := 0; i < int(size); i++ { + l := indexLocal(locals, (pid+i+1)%int(size)) + if x, _ := l.shared.popTail(); x != nil { + return x + } + } + + // Try the victim cache. We do this after attempting to steal + // from all primary caches because we want objects in the + // victim cache to age out if at all possible. + size = atomic.LoadUintptr(&p.victimSize) + if uintptr(pid) >= size { + return nil + } + locals = p.victim + l := indexLocal(locals, pid) + if x := l.private; x != nil { + l.private = nil + return x + } + for i := 0; i < int(size); i++ { + l := indexLocal(locals, (pid+i)%int(size)) + if x, _ := l.shared.popTail(); x != nil { + return x + } + } + + // Mark the victim cache as empty for future gets don't bother + // with it. + atomic.StoreUintptr(&p.victimSize, 0) + + return nil +} + +// pin pins the current goroutine to P, disables preemption and +// returns poolLocal pool for the P and the P's id. +// Caller must call runtime_procUnpin() when done with the pool. +func (p *Pool) pin() (*poolLocal, int) { + pid := runtime_procPin() + // In pinSlow we store to local and then to localSize, here we load in opposite order. + // Since we've disabled preemption, GC cannot happen in between. + // Thus here we must observe local at least as large localSize. + // We can observe a newer/larger local, it is fine (we must observe its zero-initialized-ness). + s := runtime_LoadAcquintptr(&p.localSize) // load-acquire + l := p.local // load-consume + if uintptr(pid) < s { + return indexLocal(l, pid), pid + } + return p.pinSlow() +} + +func (p *Pool) pinSlow() (*poolLocal, int) { + // Retry under the mutex. + // Can not lock the mutex while pinned. + runtime_procUnpin() + allPoolsMu.Lock() + defer allPoolsMu.Unlock() + pid := runtime_procPin() + // poolCleanup won't be called while we are pinned. + s := p.localSize + l := p.local + if uintptr(pid) < s { + return indexLocal(l, pid), pid + } + if p.local == nil { + allPools = append(allPools, p) + } + // If GOMAXPROCS changes between GCs, we re-allocate the array and lose the old one. + size := runtime.GOMAXPROCS(0) + local := make([]poolLocal, size) + atomic.StorePointer(&p.local, unsafe.Pointer(&local[0])) // store-release + runtime_StoreReluintptr(&p.localSize, uintptr(size)) // store-release + return &local[pid], pid +} + +func poolCleanup() { + // This function is called with the world stopped, at the beginning of a garbage collection. + // It must not allocate and probably should not call any runtime functions. + + // Because the world is stopped, no pool user can be in a + // pinned section (in effect, this has all Ps pinned). + + // Drop victim caches from all pools. + for _, p := range oldPools { + p.victim = nil + p.victimSize = 0 + } + + // Move primary cache to victim cache. + for _, p := range allPools { + p.victim = p.local + p.victimSize = p.localSize + p.local = nil + p.localSize = 0 + } + + // The pools with non-empty primary caches now have non-empty + // victim caches and no pools have primary caches. + oldPools, allPools = allPools, nil +} + +var ( + allPoolsMu Mutex + + // allPools is the set of pools that have non-empty primary + // caches. Protected by either 1) allPoolsMu and pinning or 2) + // STW. + allPools []*Pool + + // oldPools is the set of pools that may have non-empty victim + // caches. Protected by STW. + oldPools []*Pool +) + +func init() { + runtime_registerPoolCleanup(poolCleanup) +} + +func indexLocal(l unsafe.Pointer, i int) *poolLocal { + lp := unsafe.Pointer(uintptr(l) + uintptr(i)*unsafe.Sizeof(poolLocal{})) + return (*poolLocal)(lp) +} + +// Implemented in runtime. +func runtime_registerPoolCleanup(cleanup func()) +func runtime_procPin() int +func runtime_procUnpin() + +// The below are implemented in runtime/internal/atomic and the +// compiler also knows to intrinsify the symbol we linkname into this +// package. + +//go:linkname runtime_LoadAcquintptr runtime/internal/atomic.LoadAcquintptr +func runtime_LoadAcquintptr(ptr *uintptr) uintptr + +//go:linkname runtime_StoreReluintptr runtime/internal/atomic.StoreReluintptr +func runtime_StoreReluintptr(ptr *uintptr, val uintptr) uintptr |