From: "agentzh at gmail dot com" <sourceware-bugzilla@sourceware.org>
To: systemtap@sourceware.org
Subject: [Bug uprobes/27260] New: uprobes is unstable on centos6 x86_64 when running the same script repeatedly against the same target process
Date: Thu, 28 Jan 2021 02:07:49 +0000 [thread overview]
Message-ID: <bug-27260-6586@http.sourceware.org/bugzilla/> (raw)
https://sourceware.org/bugzilla/show_bug.cgi?id=27260
Bug ID: 27260
Summary: uprobes is unstable on centos6 x86_64 when running the
same script repeatedly against the same target process
Product: systemtap
Version: unspecified
Status: UNCONFIRMED
Severity: normal
Priority: P2
Component: uprobes
Assignee: systemtap at sourceware dot org
Reporter: agentzh at gmail dot com
Target Milestone: ---
We noted that use of uprobes on centos6 x86_64 is very unstable even with the
simplest script and the simplest target C program. Below is a minimal example
that can reliably reproduce the issue:
First of all, we create a simple C program as the target:
```
#include <stdio.h>
void foo(int i) {
printf("hello %d\n", i);
}
int main(void) {
int i = 0;
while (1) {
foo(i++);
}
return 0;
}
```
And then compile this C program without inlining:
```
gcc -O -fno-inline -g a.c
```
Run the target program forever:
```
./a.out > /dev/null
```
Finally, run a stap oneliner in a bash loop:
```
$ while true; do /opt/stap/bin/stap -d ~/a.out -e 'probe
process("/home/agentzh/a.out").function("foo") { println("Hit"); exit() }';
done
Hit
Hit
Hit
Hit
Hit
Hit
Hit
Hit
Hit
```
This loop will quickly hang sooner or later. Some times after 3 Hits, some
times after about 10.
And in the terminal running the ./a.out, we can see the target is already
killed:
```
[agentzh@centos6-pkg ~]$ ./a.out > /dev/null
Trace/breakpoint trap
[agentzh@centos6-pkg ~]$
```
I'm using the latest stap master (commit a790dc64a9d8d9):
```
[agentzh@centos6-pkg systemtap]$ /opt/stap/bin/stap -V
Systemtap translator/driver (version 4.5/0.177, commit
release-4.4-74-ga790dc64a9d8 + changes)
Copyright (C) 2005-2020 Red Hat, Inc. and others
This is free software; see the source for copying conditions.
tested kernel versions: 2.6.32 ... 5.10.0-rc
enabled features: JAVA LIBXML2 READLINE
```
Using the following centos6 stock kernel:
```
[agentzh@centos6-pkg systemtap]$ uname -r
2.6.32-754.18.2.el6.x86_64
```
Tested all the centos 6 kernels in the official repo. Same thing.
--
You are receiving this mail because:
You are the assignee for the bug.
next reply other threads:[~2021-01-28 2:07 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-28 2:07 agentzh at gmail dot com [this message]
2023-10-30 15:26 ` [Bug uprobes/27260] " wcohen at redhat dot com
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bug-27260-6586@http.sourceware.org/bugzilla/ \
--to=sourceware-bugzilla@sourceware.org \
--cc=systemtap@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).