0
0
Fork 0
bleve/search/pool.go

77 lines
2.6 KiB
Go
Raw Normal View History

// Copyright (c) 2014 Couchbase, Inc.
2016-10-02 16:13:14 +02:00
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package search
// DocumentMatchPoolTooSmall is a callback function that can be executed
// when the DocumentMatchPool does not have sufficient capacity
// By default we just perform just-in-time allocation, but you could log
// a message, or panic, etc.
type DocumentMatchPoolTooSmall func(p *DocumentMatchPool) *DocumentMatch
// DocumentMatchPool manages use/re-use of DocumentMatch instances
// it pre-allocates space from a single large block with the expected
// number of instances. It is not thread-safe as currently all
// aspects of search take place in a single goroutine.
type DocumentMatchPool struct {
avail DocumentMatchCollection
TooSmall DocumentMatchPoolTooSmall
}
func defaultDocumentMatchPoolTooSmall(p *DocumentMatchPool) *DocumentMatch {
return &DocumentMatch{}
}
// NewDocumentMatchPool will build a DocumentMatchPool with memory
// pre-allocated to accomodate the requested number of DocumentMatch
// instances
func NewDocumentMatchPool(size, sortsize int) *DocumentMatchPool {
avail := make(DocumentMatchCollection, 0, size)
// pre-allocate the expected number of instances
startBlock := make([]DocumentMatch, size)
// make these initial instances available
for i := range startBlock {
improved implementation to address perf regressions primary change is going back to sort values be []string and not []interface{}, this avoid allocatiosn converting into the interface{} that sounds obvious, so why didn't we just do that first? because a common (default) sort is score, which is naturally a number, not a string (like terms). converting into the number was also expensive, and the common case. so, this solution also makes the change to NOT put the score into the sort value list. instead you see the dummy value "_score". this is just a placeholder, the actual sort impl knows that field of the sort is the score, and will sort using the actual score. also, several other aspets of the benchmark were cleaned up so that unnecessary allocations do not pollute the cpu profiles Here are the updated benchmarks: $ go test -run=xxx -bench=. -benchmem -cpuprofile=cpu.out BenchmarkTop10of100000Scores-4 3000 465809 ns/op 2548 B/op 33 allocs/op BenchmarkTop100of100000Scores-4 2000 626488 ns/op 21484 B/op 213 allocs/op BenchmarkTop10of1000000Scores-4 300 5107658 ns/op 2560 B/op 33 allocs/op BenchmarkTop100of1000000Scores-4 300 5275403 ns/op 21624 B/op 213 allocs/op PASS ok github.com/blevesearch/bleve/search/collectors 7.188s Prior to this PR, master reported: $ go test -run=xxx -bench=. -benchmem BenchmarkTop10of100000Scores-4 3000 453269 ns/op 360161 B/op 42 allocs/op BenchmarkTop100of100000Scores-4 2000 519131 ns/op 388275 B/op 219 allocs/op BenchmarkTop10of1000000Scores-4 200 7459004 ns/op 4628236 B/op 52 allocs/op BenchmarkTop100of1000000Scores-4 200 8064864 ns/op 4656596 B/op 232 allocs/op PASS ok github.com/blevesearch/bleve/search/collectors 7.385s So, we're pretty close on the smaller datasets, and we scale better on the larger datasets. We also show fewer allocations and bytes in all cases (some of this is artificial due to test cleanup).
2016-08-25 21:47:07 +02:00
startBlock[i].Sort = make([]string, 0, sortsize)
avail = append(avail, &startBlock[i])
}
return &DocumentMatchPool{
avail: avail,
TooSmall: defaultDocumentMatchPoolTooSmall,
}
}
// Get returns an available DocumentMatch from the pool
// if the pool was not allocated with sufficient size, an allocation will
// occur to satisfy this request. As a side-effect this will grow the size
// of the pool.
func (p *DocumentMatchPool) Get() *DocumentMatch {
var rv *DocumentMatch
if len(p.avail) > 0 {
rv, p.avail = p.avail[len(p.avail)-1], p.avail[:len(p.avail)-1]
} else {
rv = p.TooSmall(p)
}
return rv
}
// Put returns a DocumentMatch to the pool
func (p *DocumentMatchPool) Put(d *DocumentMatch) {
if d == nil {
return
}
// reset DocumentMatch before returning it to available pool
d.Reset()
p.avail = append(p.avail, d)
}