core/vm: less allocations for various call variants (#21222)

* core/vm/runtime/tests: add more benchmarks

* core/vm: initial work on improving alloc count for calls to precompiles

name                                  old time/op    new time/op    delta
SimpleLoop/identity-precompile-10M-6     117ms ±75%      43ms ± 1%  -63.09%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   79.6ms ± 4%    70.5ms ± 1%  -11.42%  (p=0.008 n=5+5)

name                                  old alloc/op   new alloc/op   delta
SimpleLoop/identity-precompile-10M-6    24.4MB ± 0%     4.9MB ± 0%  -79.94%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   13.2kB ± 0%    13.2kB ± 0%     ~     (p=0.357 n=5+5)

name                                  old allocs/op  new allocs/op  delta
SimpleLoop/identity-precompile-10M-6      382k ± 0%      153k ± 0%  -59.99%  (p=0.000 n=5+4)
SimpleLoop/loop-10M-6                     40.0 ± 0%      40.0 ± 0%     ~     (all equal)

* core/vm: don't allocate big.int for touch

name                                  old time/op    new time/op    delta
SimpleLoop/identity-precompile-10M-6    43.3ms ± 1%    42.4ms ± 7%     ~     (p=0.151 n=5+5)
SimpleLoop/loop-10M-6                   70.5ms ± 1%    76.7ms ± 1%   +8.67%  (p=0.008 n=5+5)

name                                  old alloc/op   new alloc/op   delta
SimpleLoop/identity-precompile-10M-6    4.90MB ± 0%    2.46MB ± 0%  -49.83%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   13.2kB ± 0%    13.2kB ± 1%     ~     (p=0.571 n=5+5)

name                                  old allocs/op  new allocs/op  delta
SimpleLoop/identity-precompile-10M-6      153k ± 0%       76k ± 0%  -49.98%  (p=0.029 n=4+4)
SimpleLoop/loop-10M-6                     40.0 ± 0%      40.0 ± 0%     ~     (all equal)

* core/vm: reduce allocs in staticcall

name                                  old time/op    new time/op    delta
SimpleLoop/identity-precompile-10M-6    42.4ms ± 7%    37.5ms ± 6%  -11.68%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   76.7ms ± 1%    69.1ms ± 1%   -9.82%  (p=0.008 n=5+5)

name                                  old alloc/op   new alloc/op   delta
SimpleLoop/identity-precompile-10M-6    2.46MB ± 0%    0.02MB ± 0%  -99.35%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   13.2kB ± 1%    13.2kB ± 0%     ~     (p=0.143 n=5+5)

name                                  old allocs/op  new allocs/op  delta
SimpleLoop/identity-precompile-10M-6     76.4k ± 0%      0.1k ± 0%     ~     (p=0.079 n=4+5)
SimpleLoop/loop-10M-6                     40.0 ± 0%      40.0 ± 0%     ~     (all equal)

* trie: better use of hasher keccakState

* core/state/statedb: reduce allocations in getDeletedStateObject

* core/vm: reduce allocations in all call derivates

* core/vm: reduce allocations in call variants

- Make returnstack `uint32`
- Use a `sync.Pool` of `stack`s

* core/vm: fix tests

* core/vm: goimports

* core/vm: tracer fix + staticcall gas fix

* core/vm: add back snapshot to staticcall

* core/vm: review concerns + make returnstack pooled + enable returndata in traces

* core/vm: fix some test tracer method signatures

* core/vm: run gencodec, minor comment polish

Co-authored-by: Péter Szilágyi <peterke@gmail.com>
This commit is contained in:
Martin Holst Swende
2020-07-16 14:06:19 +02:00
committed by GitHub
parent 240d1851db
commit 295693759e
21 changed files with 447 additions and 188 deletions

View File

@ -47,11 +47,12 @@ func (s Storage) Copy() Storage {
// LogConfig are the configuration options for structured logger the EVM
type LogConfig struct {
DisableMemory bool // disable memory capture
DisableStack bool // disable stack capture
DisableStorage bool // disable storage capture
Debug bool // print output during capture end
Limit int // maximum length of output, but zero means unlimited
DisableMemory bool // disable memory capture
DisableStack bool // disable stack capture
DisableStorage bool // disable storage capture
DisableReturnData bool // disable return data capture
Debug bool // print output during capture end
Limit int // maximum length of output, but zero means unlimited
}
//go:generate gencodec -type StructLog -field-override structLogMarshaling -out gen_structlog.go
@ -66,7 +67,8 @@ type StructLog struct {
Memory []byte `json:"memory"`
MemorySize int `json:"memSize"`
Stack []*big.Int `json:"stack"`
ReturnStack []uint64 `json:"returnStack"`
ReturnStack []uint32 `json:"returnStack"`
ReturnData []byte `json:"returnData"`
Storage map[common.Hash]common.Hash `json:"-"`
Depth int `json:"depth"`
RefundCounter uint64 `json:"refund"`
@ -104,7 +106,7 @@ func (s *StructLog) ErrorString() string {
// if you need to retain them beyond the current call.
type Tracer interface {
CaptureStart(from common.Address, to common.Address, create bool, input []byte, gas uint64, value *big.Int) error
CaptureState(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, contract *Contract, depth int, err error) error
CaptureState(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, rData []byte, contract *Contract, depth int, err error) error
CaptureFault(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, contract *Contract, depth int, err error) error
CaptureEnd(output []byte, gasUsed uint64, t time.Duration, err error) error
}
@ -142,7 +144,7 @@ func (l *StructLogger) CaptureStart(from common.Address, to common.Address, crea
// CaptureState logs a new structured log message and pushes it out to the environment
//
// CaptureState also tracks SLOAD/SSTORE ops to track storage change.
func (l *StructLogger) CaptureState(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, contract *Contract, depth int, err error) error {
func (l *StructLogger) CaptureState(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, rData []byte, contract *Contract, depth int, err error) error {
// check if already accumulated the specified number of logs
if l.cfg.Limit != 0 && l.cfg.Limit <= len(l.logs) {
return errTraceLimitReached
@ -161,9 +163,9 @@ func (l *StructLogger) CaptureState(env *EVM, pc uint64, op OpCode, gas, cost ui
stck[i] = new(big.Int).Set(item.ToBig())
}
}
var rstack []uint64
var rstack []uint32
if !l.cfg.DisableStack && rStack != nil {
rstck := make([]uint64, len(rStack.data))
rstck := make([]uint32, len(rStack.data))
copy(rstck, rStack.data)
}
// Copy a snapshot of the current storage to a new container
@ -192,8 +194,13 @@ func (l *StructLogger) CaptureState(env *EVM, pc uint64, op OpCode, gas, cost ui
}
storage = l.storage[contract.Address()].Copy()
}
var rdata []byte
if !l.cfg.DisableReturnData {
rdata = make([]byte, len(rData))
copy(rdata, rData)
}
// create a new snapshot of the EVM.
log := StructLog{pc, op, gas, cost, mem, memory.Len(), stck, rstack, storage, depth, env.StateDB.GetRefund(), err}
log := StructLog{pc, op, gas, cost, mem, memory.Len(), stck, rstack, rdata, storage, depth, env.StateDB.GetRefund(), err}
l.logs = append(l.logs, log)
return nil
}
@ -257,6 +264,10 @@ func WriteTrace(writer io.Writer, logs []StructLog) {
fmt.Fprintf(writer, "%x: %x\n", h, item)
}
}
if len(log.ReturnData) > 0 {
fmt.Fprintln(writer, "ReturnData:")
fmt.Fprint(writer, hex.Dump(log.ReturnData))
}
fmt.Fprintln(writer)
}
}
@ -308,7 +319,7 @@ func (t *mdLogger) CaptureStart(from common.Address, to common.Address, create b
return nil
}
func (t *mdLogger) CaptureState(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, contract *Contract, depth int, err error) error {
func (t *mdLogger) CaptureState(env *EVM, pc uint64, op OpCode, gas, cost uint64, memory *Memory, stack *Stack, rStack *ReturnStack, rData []byte, contract *Contract, depth int, err error) error {
fmt.Fprintf(t.out, "| %4d | %10v | %3d |", pc, op, cost)
if !t.cfg.DisableStack { // format stack