Skip to content

Fix crash for non-utf8 thread names #324

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix crash for non-utf8 thread names #324

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
37 changes: 28 additions & 9 deletions collector/process_collector.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@ package collector
import (
"log"
"time"
"unicode/utf8"

common "github.com/ncabatoff/process-exporter"
"github.com/ncabatoff/process-exporter/proc"
Expand Down Expand Up @@ -318,33 +319,34 @@ func (p *NamedProcessCollector) scrape(ch chan<- prometheus.Metric) {

if p.threads {
for _, thr := range gcounts.Threads {
threadName := filterNonutf8Characters(thr.Name)
Copy link
Owner

@ncabatoff ncabatoff Apr 21, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
threadName := filterNonutf8Characters(thr.Name)
threadName := strings.ToValidUTF8(thr.Name, "\uFFFD")

I believe this is the "replacement character" that's commonly used for invalid utf-8.

ch <- prometheus.MustNewConstMetric(threadCountDesc,
prometheus.GaugeValue, float64(thr.NumThreads),
gname, thr.Name)
gname, threadName)
ch <- prometheus.MustNewConstMetric(threadCpuSecsDesc,
prometheus.CounterValue, float64(thr.CPUUserTime),
gname, thr.Name, "user")
gname, threadName, "user")
ch <- prometheus.MustNewConstMetric(threadCpuSecsDesc,
prometheus.CounterValue, float64(thr.CPUSystemTime),
gname, thr.Name, "system")
gname, threadName, "system")
ch <- prometheus.MustNewConstMetric(threadIoBytesDesc,
prometheus.CounterValue, float64(thr.ReadBytes),
gname, thr.Name, "read")
gname, threadName, "read")
ch <- prometheus.MustNewConstMetric(threadIoBytesDesc,
prometheus.CounterValue, float64(thr.WriteBytes),
gname, thr.Name, "write")
gname, threadName, "write")
ch <- prometheus.MustNewConstMetric(threadMajorPageFaultsDesc,
prometheus.CounterValue, float64(thr.MajorPageFaults),
gname, thr.Name)
gname, threadName)
ch <- prometheus.MustNewConstMetric(threadMinorPageFaultsDesc,
prometheus.CounterValue, float64(thr.MinorPageFaults),
gname, thr.Name)
gname, threadName)
ch <- prometheus.MustNewConstMetric(threadContextSwitchesDesc,
prometheus.CounterValue, float64(thr.CtxSwitchVoluntary),
gname, thr.Name, "voluntary")
gname, threadName, "voluntary")
ch <- prometheus.MustNewConstMetric(threadContextSwitchesDesc,
prometheus.CounterValue, float64(thr.CtxSwitchNonvoluntary),
gname, thr.Name, "nonvoluntary")
gname, threadName, "nonvoluntary")
}
}
}
Expand All @@ -356,3 +358,20 @@ func (p *NamedProcessCollector) scrape(ch chan<- prometheus.Metric) {
ch <- prometheus.MustNewConstMetric(scrapePartialErrorsDesc,
prometheus.CounterValue, float64(p.scrapePartialErrors))
}

func filterNonutf8Characters(s string) string {
if !utf8.ValidString(s) {
v := make([]rune, 0, len(s))
for i, r := range s {
if r == utf8.RuneError {
_, size := utf8.DecodeRuneInString(s[i:])
if size == 1 {
continue
}
}
v = append(v, r)
}
s = string(v)
}
return s
}