Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[probabilisticsamplerprocessor] Support consistent intermediate span sampling (OTEP 226) #22058

Closed
wants to merge 10 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
100 changes: 100 additions & 0 deletions pkg/sampling/common.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,100 @@
package sampling

import (
"errors"
"strings"

"go.uber.org/multierr"
)

type KV struct {
Key string
Value string
}

var (
ErrTraceStateSize = errors.New("invalid tracestate size")
ErrTraceStateCount = errors.New("invalid tracestate item count")
)

// keyValueScanner defines distinct scanner behaviors for lists of
// key-values.
type keyValueScanner struct {
// maxItems is 32 or -1
maxItems int
// trim is set if OWS (optional whitespace) should be removed
trim bool
// separator is , or ;
separator byte
// equality is = or :
equality byte
}

type commonTraceState struct {
kvs []KV
}

func (cts commonTraceState) HasExtraValues() bool {
return len(cts.kvs) != 0
}

func (cts commonTraceState) ExtraValues() []KV {
return cts.kvs
}

// trimOws removes optional whitespace on both ends of a string.
func trimOws(input string) string {
// Hard-codes the value of owsCharset
for len(input) > 0 && input[0] == ' ' || input[0] == '\t' {
input = input[1:]
}
for len(input) > 0 && input[len(input)-1] == ' ' || input[len(input)-1] == '\t' {
input = input[:len(input)-1]
}
return input
}

func (s keyValueScanner) scanKeyValues(input string, f func(key, value string) error) error {
var rval error
items := 0
for input != "" {
items++
if s.maxItems > 0 && items >= s.maxItems {
// W3C specifies max 32 entries, tested here
// instead of via the regexp.
return ErrTraceStateCount
}

sep := strings.IndexByte(input, s.separator)

var member string
if sep < 0 {
member = input
input = ""
} else {
member = input[:sep]
input = input[sep+1:]
}

if s.trim {
// Trim only required for W3C; OTel does not
// specify whitespace for its value encoding.
member = trimOws(member)
}

if member == "" {
// W3C allows empty list members.
continue
}

eq := strings.IndexByte(member, s.equality)
if eq < 0 {
// A regexp should have rejected this input.
continue
}
if err := f(member[:eq], member[eq+1:]); err != nil {
rval = multierr.Append(rval, err)
}
}
return rval
}
23 changes: 23 additions & 0 deletions pkg/sampling/go.mod
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
module github.com/open-telemetry/opentelemetry-collector-contrib/pkg/sampling

go 1.20

require (
github.com/stretchr/testify v1.8.2
go.opentelemetry.io/collector/pdata v1.0.0-rcv0011
go.uber.org/multierr v1.11.0
)

require (
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/gogo/protobuf v1.3.2 // indirect
github.com/golang/protobuf v1.5.2 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
golang.org/x/net v0.9.0 // indirect
golang.org/x/sys v0.7.0 // indirect
golang.org/x/text v0.9.0 // indirect
google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f // indirect
google.golang.org/grpc v1.54.0 // indirect
google.golang.org/protobuf v1.30.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
)
71 changes: 71 additions & 0 deletions pkg/sampling/go.sum

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

172 changes: 172 additions & 0 deletions pkg/sampling/oteltracestate.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,172 @@
package sampling

import (
"fmt"
"io"
"regexp"
"strconv"
)

type OTelTraceState struct {
commonTraceState

// sampling r, s, and t-values
ru uint64 // r value parsed, as unsigned
r string // 14 ASCII hex digits
sf float64 // s value parsed, as a probability
s string // original float syntax preserved
tf float64 // t value parsed, as a probability
t string // original float syntax preserved
}

const (
// hardMaxOTelLength is the maximum encoded size of an OTel
// tracestate value.
hardMaxOTelLength = 256

// chr = ucalpha / lcalpha / DIGIT / "." / "_" / "-"
// ucalpha = %x41-5A ; A-Z
// lcalpha = %x61-7A ; a-z
// key = lcalpha *(lcalpha / DIGIT )
// value = *(chr)
// list-member = key ":" value
// list = list-member *( ";" list-member )
otelKeyRegexp = lcAlphaRegexp + lcDigitRegexp + `*`
otelValueRegexp = `[a-zA-Z0-9._\-]*`
otelMemberRegexp = `(?:` + otelKeyRegexp + `:` + otelValueRegexp + `)`
otelSemicolonMemberRegexp = `(?:` + `;` + otelMemberRegexp + `)`
otelTracestateRegexp = `^` + otelMemberRegexp + otelSemicolonMemberRegexp + `*$`
)

var (
otelTracestateRe = regexp.MustCompile(otelTracestateRegexp)

ErrRandomValueRange = fmt.Errorf("r-value out of range")

otelSyntax = keyValueScanner{
maxItems: -1,
trim: false,
separator: ';',
equality: ':',
}
)

func NewOTelTraceState(input string) (otts OTelTraceState, _ error) {
if len(input) > hardMaxOTelLength {
return otts, ErrTraceStateSize
}

if !otelTracestateRe.MatchString(input) {
return OTelTraceState{}, strconv.ErrSyntax
}

err := otelSyntax.scanKeyValues(input, func(key, value string) error {
var err error
switch key {
case "r":
var unsigned uint64
unsigned, err = strconv.ParseUint(value, 16, 64)
if err == nil {
if unsigned >= 0x1p56 {
err = ErrRandomValueRange
} else {
otts.r = value
otts.ru = unsigned
}
}
case "s":
var prob float64
prob, _, err = EncodedToProbabilityAndAdjustedCount(value)
if err == nil {
otts.s = value
otts.sf = prob
}
case "t":
var prob float64
prob, _, err = EncodedToProbabilityAndAdjustedCount(value)
if err == nil {
otts.t = value
otts.tf = prob
}
default:
otts.kvs = append(otts.kvs, KV{
Key: key,
Value: value,
})
}
return err
})

return otts, err
}

func (otts OTelTraceState) HasRValue() bool {
return otts.r != ""
}

func (otts OTelTraceState) RValue() string {
return otts.r
}

func (otts OTelTraceState) RValueUnsigned() uint64 {
return otts.ru
}

func (otts OTelTraceState) HasSValue() bool {
return otts.s != ""
}

func (otts OTelTraceState) SValue() string {
return otts.s
}

func (otts OTelTraceState) SValueProbability() float64 {
return otts.sf
}

func (otts OTelTraceState) HasTValue() bool {
return otts.t != ""
}

func (otts OTelTraceState) TValue() string {
return otts.t
}

func (otts OTelTraceState) TValueProbability() float64 {
return otts.tf
}

func (otts OTelTraceState) HasAnyValue() bool {
return otts.HasRValue() || otts.HasSValue() || otts.HasTValue() || otts.HasExtraValues()
}

func (otts OTelTraceState) Serialize(w io.StringWriter) {
cnt := 0
sep := func() {
if cnt != 0 {
w.WriteString(";")
}
cnt++
}
if otts.HasRValue() {
sep()
w.WriteString("r:")
w.WriteString(otts.RValue())
}
if otts.HasSValue() {
sep()
w.WriteString("s:")
w.WriteString(otts.SValue())
}
if otts.HasTValue() {
sep()
w.WriteString("t:")
w.WriteString(otts.TValue())
}
for _, kv := range otts.ExtraValues() {
sep()
w.WriteString(kv.Key)
w.WriteString(":")
w.WriteString(kv.Value)
}
}
Loading