pkg / profile

Simple profiling for Go
BSD 2-Clause "Simplified" License
1.99k stars 124 forks source link

Source of memory increase #34

Open beatscode opened 7 years ago

beatscode commented 7 years ago

I've written a program that reads a csv (2.1m records) and builds sql insert statements into mariadb instance. It takes about 7minutes to complete the cpu level on my macbook pro (sierra) go to about 65% and the activity monitor shows upwards of 1GB to even 3.7 GB sometimes. I added the profiler to my project and tried to analyze the results but it seems to show that the program used about 25MB. I'm not sure what to read from this. here is a contrived version of my code and some pictures of the activity monitor.

func main(){
    //Setup and Connect to database 
    //Set variables
    //Read CSV File
    dbConnect()
    defer db.Close()
    db.DB().SetMaxOpenConns(90)
    db.DB().SetMaxIdleConns(10)
    db.DB().SetConnMaxLifetime(time.Second * 14400)
    filehandle, err := os.Open(physicianCSV)
    checkErr(err)
    defer filehandle.Close()

    reader := csv.NewReader(filehandle)
    _, err = reader.Read()
    checkErr(err)

    for i := 0; i <= readLimit; i++ {
        record, err := reader.Read()
        if err != nil {
            if err == io.EOF {
                break
            }
            panic(err)
        }
        physician = convertCSVRecordToPhysician(record)
        //..Do stuff with physician, edit object properties via pointer

        physicians = append(physicians, physician)

        if math.Mod(float64(i), float64(bulkAmount)) == 0 && i != 0 {
            fmt.Println(i, "Records: From ", i-bulkAmount, "to", i)
            wg.Add(1)
            sliceOfPhys := make([]Physician, bulkAmount)
            copy(sliceOfPhys, physicians)
            go bulkSavePhysicians(sliceOfPhys)
            physicians = physicians[:0]

        }
    }

    fmt.Println(readLimit, "records inserted")
    wg.Wait()
}

func bulkSavePhysicians(_physicians []Physician) {
    defer func() {
        if x := recover(); x != nil {
            fmt.Println(x)
        }
    }()
    defer wg.Done()

    sqlStringArray := buildSQLStatements(_physicians)
    batchSQL := fmt.Sprintf("insert into physicians values %s ;", strings.Join(sqlStringArray, ","))
    tx := db.Begin()
    errors := tx.Exec(batchSQL).GetErrors()
    if len(errors) > 0 {
        panic(errors)
    }
    tx.Commit()
}

func buildSQLStatements(_physicians []Physician) []string {

    var valueStr string
    var valueArr []string
    for _, phys := range _physicians {

        valueStr = fmt.Sprintf(`( "%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s" )`, phys.NPI,
            phys.PACID,
            phys.ProfessionalEnrollmentID,
            strings.Replace(phys.LastName, "'", "\\'", -1),
            phys.FirstName,
            phys.MiddleName,
            phys.Suffix,
            phys.Gender,
            phys.Credential,
            strings.Replace(phys.MedicalSchoolName, "'", "\\'", -1),
            phys.GraduationYear,
            phys.PrimarySpecialty,
            phys.SecondarySpecialty1,
            phys.SecondarySpecialty2,
            phys.SecondarySpecialty3,
            phys.SecondarySpecialty4,
            phys.AllSecondarySpecialties,
            strings.Replace(phys.OrganizationLegalName, "'", "\\'", -1),
            phys.GroupPracticePACID,
            phys.NumberOfGroupPracticeMembers,
            strings.Replace(phys.Line1StreetAddress, "'", "\\'", -1),
            phys.Line2StreetAddress,
            phys.MarkerOfAddressLine2Suppression,
            phys.City,
            phys.State,
            phys.ZipCode,
            phys.PhoneNumber,
            phys.HospitalAffiliationCCN1,
            phys.HospitalAffiliationLBN1,
            phys.HospitalAffiliationCCN2,
            phys.HospitalAffiliationLBN2,
            phys.HospitalAffiliationCCN3,
            phys.HospitalAffiliationLBN3,
            phys.HospitalAffiliationCCN4,
            phys.HospitalAffiliationLBN4,
            phys.HospitalAffiliationCCN5,
            phys.HospitalAffiliationLBN5,
            phys.ProfessionalAcceptsMedicareAssignment,
            phys.ReportedQualityMeasures,
            phys.UsedElectronicHealthRecords,
            phys.ParticipatedInTheMedicareMaintenance,
            phys.CommittedToHeartHealth,
            phys.SpecialtyID)

        valueArr = append(valueArr, valueStr)
    }
    return valueArr
}

Here is zip of mem.pprof and cpu.pprof proffs.zip

An image of activity monitor taken without the profiler inclusion. 36999fa9-22bc-42d6-99e0-056200051aea

I watched your talk and you mentioned that heapSys is the correct value to indicate the amount of memory used in bytes. Am I correct in saying this? 203751424 bytes = 203MB Calling web from go tool pprof mem.pprof renders the following image

I'm confused as to which values to trust.