I am very, very memory careful as I have to write programs that need to cope with massive datasets.
Currently my application quickly reaches 32GB of memory, starts swapping, and then gets killed by the system.
I do not understand how this can be since all variables are collectable (in functions and quickly released) except TokensStruct and TokensCount in the Trainer struct. TokensCount is just a uint. TokensStruct is a 1,000,000 row slice of [5]uint32 and string, so that means 20 bytes + string, which we could call a maximum of 50 bytes per record. 50*1000000 = 50MB of memory required. So this script should therefore not use much more than 50MB + overhead + temporary collectable variables in the functions (maybe another 50MB max.) The maximum potential size of TokensStruct is 5,000,000, as this is the size of dictionary, but even then it would be only 250MB of memory. dictionary is a map and apparently uses around 600MB of memory, as that is how the app starts, but this is not an issue because dictionary is only loaded once and never written to again.
Instead it uses 32GB of memory then dies. By the speed that it does this I expect it would happily get to 1TB of memory if it could. The memory appears to increase in a linear fashion with the size of the files being loaded, meaning that it appears to never clear any memory at all. Everything that enters the app is allocated more memory and memory is never freed.
I tried implementing runtime.GC() in case the garbage collection wasn't running often enough, but this made no difference.
Since the memory usage increases in a linear fashion then this would imply that there is a memory leak in GetTokens() or LoadZip(). I don't know how this could be, since they are both functions and only do one task and then close. Or it could be that the tokens variable in Start() is the cause of the leak. Basically it looks like every file that is loaded and parsed is never released from memory, as that is the only way that the memory could fill up in a linear fashion and keep on rising up to 32GB++.
Absolute nightmare! What's wrong with Go? Any way to fix this?
package main
import (
"bytes"
"code.google.com/p/go.text/transform"
"code.google.com/p/go.text/unicode/norm"
"compress/zlib"
"encoding/gob"
"fmt"
"github.com/AlasdairF/BinSearch"
"io/ioutil"
"os"
"regexp"
"runtime"
"strings"
"unicode"
"unicode/utf8"
)
type TokensStruct struct {
binsearch.Key_string
Value [][5]uint32
}
type Trainer struct {
Tokens TokensStruct
TokensCount uint
}
func checkErr(err error) {
if err == nil {
return
}
fmt.Println(`Some Error:`, err)
panic(err)
}
// Local helper function for normalization of UTF8 strings.
func isMn(r rune) bool {
return unicode.Is(unicode.Mn, r) // Mn: nonspacing marks
}
// This map is used by RemoveAccents function to convert non-accented characters.
var transliterations = map[rune]string{'Æ': "E", 'Ð': "D", 'Ł': "L", 'Ø': "OE", 'Þ': "Th", 'ß': "ss", 'æ': "e", 'ð': "d", 'ł': "l", 'ø': "oe", 'þ': "th", 'Œ': "OE", 'œ': "oe"}
// removeAccentsBytes converts accented UTF8 characters into their non-accented equivalents, from a []byte.
func removeAccentsBytesDashes(b []byte) ([]byte, error) {
mnBuf := make([]byte, len(b))
t := transform.Chain(norm.NFD, transform.RemoveFunc(isMn), norm.NFC)
n, _, err := t.Transform(mnBuf, b, true)
if err != nil {
return nil, err
}
mnBuf = mnBuf[:n]
tlBuf := bytes.NewBuffer(make([]byte, 0, len(mnBuf)*2))
for i, w := 0, 0; i < len(mnBuf); i += w {
r, width := utf8.DecodeRune(mnBuf[i:])
if r == '-' {
tlBuf.WriteByte(' ')
} else {
if d, ok := transliterations[r]; ok {
tlBuf.WriteString(d)
} else {
tlBuf.WriteRune(r)
}
}
w = width
}
return tlBuf.Bytes(), nil
}
func LoadZip(filename string) ([]byte, error) {
// Open file for reading
fi, err := os.Open(filename)
if err != nil {
return nil, err
}
defer fi.Close()
// Attach ZIP reader
fz, err := zlib.NewReader(fi)
if err != nil {
return nil, err
}
defer fz.Close()
// Pull
data, err := ioutil.ReadAll(fz)
if err != nil {
return nil, err
}
return norm.NFC.Bytes(data), nil // return normalized
}
func getTokens(pibn string) []string {
var data []byte
var err error
data, err = LoadZip(`/storedir/` + pibn + `/text.zip`)
checkErr(err)
data, err = removeAccentsBytesDashes(data)
checkErr(err)
data = bytes.ToLower(data)
data = reg2.ReplaceAll(data, []byte("$2")) // remove contractions
data = reg.ReplaceAllLiteral(data, nil)
tokens := strings.Fields(string(data))
return tokens
}
func (t *Trainer) Start() {
data, err := ioutil.ReadFile(`list.txt`)
checkErr(err)
pibns := bytes.Fields(data)
for i, pibn := range pibns {
tokens := getTokens(string(pibn))
t.addTokens(tokens)
if i%100 == 0 {
runtime.GC() // I added this just to try to stop the memory craziness, but it makes no difference
}
}
}
func (t *Trainer) addTokens(tokens []string) {
for _, tok := range tokens {
if _, ok := dictionary[tok]; ok {
if indx, ok2 := t.Tokens.Find(tok); ok2 {
ar := t.Tokens.Value[indx]
ar[0]++
t.Tokens.Value[indx] = ar
t.TokensCount++
} else {
t.Tokens.AddKeyAt(tok, indx)
t.Tokens.Value = append(t.Tokens.Value, [5]uint32{0, 0, 0, 0, 0})
copy(t.Tokens.Value[indx+1:], t.Tokens.Value[indx:])
t.Tokens.Value[indx] = [5]uint32{1, 0, 0, 0, 0}
t.TokensCount++
}
}
}
return
}
func LoadDictionary() {
dictionary = make(map[string]bool)
data, err := ioutil.ReadFile(`dictionary`)
checkErr(err)
words := bytes.Fields(data)
for _, word := range words {
strword := string(word)
dictionary[strword] = false
}
}
var reg = regexp.MustCompile(`[^a-z0-9\s]`)
var reg2 = regexp.MustCompile(`\b(c|l|all|dall|dell|nell|sull|coll|pell|gl|agl|dagl|degl|negl|sugl|un|m|t|s|v|d|qu|n|j)'([a-z])`) //contractions
var dictionary map[string]bool
func main() {
trainer := new(Trainer)
LoadDictionary()
trainer.Start()
}
