test_os_open in SocketEINTRTest hangs indefinitely on NetBSD #137397
Description
Bug report
Bug description:
The SocketEINTRTest.test_os_open test in test_eintr hangs indefinitely on NetBSD 10.0(x86_64). This appears to be a NetBSD-specific issue with FIFO operations under frequent signal interruption, similar to the issue described here.
Configuration
./configure --with-pydebugTest Output
Warning -- files was modified by test_eintr
Warning -- Before: []
Warning -- After: ['@test_16354_tmpæ']
test test_eintr failed -- Traceback (most recent call last):
File "/home/blue/Desktop/cpython/Lib/test/test_eintr.py", line 17, in test_all
script_helper.run_test_script(script)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
File "/home/blue/Desktop/cpython/Lib/test/support/script_helper.py", line 324, in run_test_script
assert_python_ok("-u", script, "-v")
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^
File "/home/blue/Desktop/cpython/Lib/test/support/script_helper.py", line 182, in assert_python_ok
return _assert_python(True, *args, **env_vars)
File "/home/blue/Desktop/cpython/Lib/test/support/script_helper.py", line 167, in _assert_python
res.fail(cmd_line)
~~~~~~~~^^^^^^^^^^
File "/home/blue/Desktop/cpython/Lib/test/support/script_helper.py", line 80, in fail
raise AssertionError(f"Process return code is {exitcode}\n"
...<10 lines>...
f"---")
AssertionError: Process return code is 1
command line: ['/home/blue/Desktop/cpython/python', '-X', 'faulthandler', '-I', '-u', '/home/blue/Desktop/cpython/Lib/test/_test_eintr.py', '-v']
stdout:
---
---
stderr:
---
test_flock (__main__.FCNTLEINTRTest.test_flock) ... ok
test_lockf (__main__.FCNTLEINTRTest.test_lockf) ... ok
test_read (__main__.OSEINTRTest.test_read) ... ok
test_readinto (__main__.OSEINTRTest.test_readinto) ... ok
test_wait (__main__.OSEINTRTest.test_wait) ... ok
test_wait3 (__main__.OSEINTRTest.test_wait3) ... ok
test_wait4 (__main__.OSEINTRTest.test_wait4) ... ok
test_waitpid (__main__.OSEINTRTest.test_waitpid) ... ok
test_write (__main__.OSEINTRTest.test_write) ... ok
test_devpoll (__main__.SelectEINTRTest.test_devpoll) ... skipped 'need select.devpoll'
test_epoll (__main__.SelectEINTRTest.test_epoll) ... skipped 'need select.epoll'
test_kqueue (__main__.SelectEINTRTest.test_kqueue) ... ok
test_poll (__main__.SelectEINTRTest.test_poll) ... ok
test_select (__main__.SelectEINTRTest.test_select) ... ok
test_sigtimedwait (__main__.SignalEINTRTest.test_sigtimedwait) ... ok
test_sigwaitinfo (__main__.SignalEINTRTest.test_sigwaitinfo) ... ERROR
test_accept (__main__.SocketEINTRTest.test_accept) ... ok
test_open (__main__.SocketEINTRTest.test_open) ... ok
test_os_open (__main__.SocketEINTRTest.test_os_open) ... Timeout (0:10:00)!
Thread 0x00007c47bfed2800 (most recent call first):
File "/home/blue/Desktop/cpython/Lib/test/_test_eintr.py", line 378 in os_open
File "/home/blue/Desktop/cpython/Lib/test/_test_eintr.py", line 364 in _test_open
File "/home/blue/Desktop/cpython/Lib/test/_test_eintr.py", line 384 in test_os_open
File "/home/blue/Desktop/cpython/Lib/unittest/case.py", line 613 in _callTestMethod
File "/home/blue/Desktop/cpython/Lib/unittest/case.py", line 667 in run
File "/home/blue/Desktop/cpython/Lib/unittest/case.py", line 723 in __call__
File "/home/blue/Desktop/cpython/Lib/unittest/suite.py", line 122 in run
File "/home/blue/Desktop/cpython/Lib/unittest/suite.py", line 84 in __call__
File "/home/blue/Desktop/cpython/Lib/unittest/suite.py", line 122 in run
File "/home/blue/Desktop/cpython/Lib/unittest/suite.py", line 84 in __call__
File "/home/blue/Desktop/cpython/Lib/unittest/runner.py", line 257 in run
File "/home/blue/Desktop/cpython/Lib/unittest/main.py", line 270 in runTests
File "/home/blue/Desktop/cpython/Lib/unittest/main.py", line 104 in __init__
File "/home/blue/Desktop/cpython/Lib/test/_test_eintr.py", line 552 in <module>
---Reproduction
I created a minimal C program that reproduces the same issue.
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>
volatile sig_atomic_t signal_count = 0;
/**
* Signal handler for SIGALRM.
*/
void handle_signal(int sig) {
(void)sig;
signal_count++;
}
/**
* Retry open() if it's interrupted by a signal (EINTR).
*/
int safe_open(const char *path, int flags) {
int fd;
while ((fd = open(path, flags)) < 0) {
if (errno != EINTR) {
perror("open");
exit(EXIT_FAILURE);
}
write(STDOUT_FILENO, ".", 1);
}
return fd;
}
/**
* Retry close() if it's interrupted by a signal (EINTR).
*/
int safe_close(int fd) {
int ret;
while ((ret = close(fd)) < 0) {
if (errno != EINTR) {
perror("close");
return ret;
}
write(STDOUT_FILENO, "C", 1);
}
return ret;
}
/**
* Sleep for a specified number of milliseconds.
*/
void sleep_ms(long ms) {
struct timespec ts;
ts.tv_sec = ms / 1000;
ts.tv_nsec = (ms % 1000) * 1000000L;
nanosleep(&ts, NULL);
}
/**
* Set up a timer to send SIGALRM every 10 milliseconds.
*/
void setup_timer(void) {
struct sigaction sa = {0};
sa.sa_handler = handle_signal;
sigaction(SIGALRM, &sa, NULL);
struct itimerval timer = {
.it_value = {0, 10000}, // Start after 10ms
.it_interval = {0, 10000} // Repeat every 10ms
};
if (setitimer(ITIMER_REAL, &timer, NULL) < 0) {
perror("setitimer");
exit(EXIT_FAILURE);
}
}
int main() {
printf("EINTR test - Ctrl+C to stop\n");
setup_timer();
for (int i = 1; i <= 50; ++i) {
char fifo[64];
snprintf(fifo, sizeof(fifo), "/tmp/test_fifo_%d", i);
unlink(fifo);
if (mkfifo(fifo, 0666) < 0) {
perror("mkfifo");
exit(EXIT_FAILURE);
}
pid_t pid = fork();
if (pid < 0) {
perror("fork");
exit(EXIT_FAILURE);
}
if (pid == 0) {
// Child opens FIFO for reading
sleep_ms(50); // 50ms delay to let parent open writer
int fd = safe_open(fifo, O_RDONLY);
safe_close(fd);
exit(EXIT_SUCCESS);
}
else {
// Parent opens FIFO for writing
int fd = safe_open(fifo, O_WRONLY);
safe_close(fd);
wait(NULL);
unlink(fifo);
printf("Loop %d OK (signals: %d)\n", i, signal_count);
signal_count = 0;
}
sleep_ms(1); // Small pause before next iteration
}
printf("Test complete.\n");
return EXIT_SUCCESS;
}Output:
╭─blue@home ~
╰─$ gcc reproducer.c -o reproducer
╭─blue@home ~
╰─$ ./reproducer
EINTR test - Ctrl+C to stop
...................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................^CSimilar output as expected:
╰─$ ./reproducer
EINTR test - Ctrl+C to stop
.....Loop 1 OK (signals: 5)
.....Loop 2 OK (signals: 5)
.....Loop 3 OK (signals: 5)
.....Loop 4 OK (signals: 5)
.....Loop 5 OK (signals: 5)
.....Loop 6 OK (signals: 5)
.....Loop 7 OK (signals: 6)
.....Loop 8 OK (signals: 5)
.....Loop 9 OK (signals: 5)
.....Loop 10 OK (signals: 5)
.....Loop 11 OK (signals: 5)
.....Loop 12 OK (signals: 5)
.....Loop 13 OK (signals: 5)
.....Loop 14 OK (signals: 6)
.....Loop 15 OK (signals: 5)
.....Loop 16 OK (signals: 5)
.....Loop 17 OK (signals: 5)
.....Loop 18 OK (signals: 5)
.....Loop 19 OK (signals: 5)
.....Loop 20 OK (signals: 5)
.....Loop 21 OK (signals: 6)
.....Loop 22 OK (signals: 5)
.....Loop 23 OK (signals: 5)
.....Loop 24 OK (signals: 5)
.....Loop 25 OK (signals: 5)
.....Loop 26 OK (signals: 5)
.....Loop 27 OK (signals: 5)
.....Loop 28 OK (signals: 6)
.....Loop 29 OK (signals: 5)
.....Loop 30 OK (signals: 5)
.....Loop 31 OK (signals: 5)
.....Loop 32 OK (signals: 5)
.....Loop 33 OK (signals: 5)
.....Loop 34 OK (signals: 5)
.....Loop 35 OK (signals: 6)
.....Loop 36 OK (signals: 5)
.....Loop 37 OK (signals: 5)
.....Loop 38 OK (signals: 5)
.....Loop 39 OK (signals: 5)
.....Loop 40 OK (signals: 5)
.....Loop 41 OK (signals: 5)
.....Loop 42 OK (signals: 6)
.....Loop 43 OK (signals: 5)
.....Loop 44 OK (signals: 5)
.....Loop 45 OK (signals: 5)
.....Loop 46 OK (signals: 5)
.....Loop 47 OK (signals: 5)
.....Loop 48 OK (signals: 5)
.....Loop 49 OK (signals: 6)
.....Loop 50 OK (signals: 5)
Test complete.
╰─$ ktrace -f ktrace.out ./reproducer
EINTR test - Ctrl+C to stop
...............................................................................................................................^C
╰─$ kdump -f ktrace.out | tail -50
17368 17368 reproducer CALL setcontext(0x7f7fff444000)
17368 17368 reproducer RET setcontext JUSTRETURN
17368 17368 reproducer CALL write(1,0x401173,1)
17368 17368 reproducer GIO fd 1 wrote 1 bytes
"."
17368 17368 reproducer RET write 1
17368 17368 reproducer CALL open(0x7f7fff4443d0,1,1)
17368 17368 reproducer NAMI "/tmp/test_fifo_1"
17368 17368 reproducer RET open -1 errno 4 Interrupted system call
17368 17368 reproducer PSIG SIGALRM caught handler=0x400dba mask=(): code=SI_TIMER sent by pid=0, uid=0 with sigval 0x0)
17368 17368 reproducer CALL setcontext(0x7f7fff444000)
17368 17368 reproducer RET setcontext JUSTRETURN
17368 17368 reproducer CALL write(1,0x401173,1)
17368 17368 reproducer GIO fd 1 wrote 1 bytes
"."
17368 17368 reproducer RET write 1
17368 17368 reproducer CALL open(0x7f7fff4443d0,1,1)
17368 17368 reproducer NAMI "/tmp/test_fifo_1"
17368 17368 reproducer RET open -1 errno 4 Interrupted system call
17368 17368 reproducer PSIG SIGALRM caught handler=0x400dba mask=(): code=SI_TIMER sent by pid=0, uid=0 with sigval 0x0)
17368 17368 reproducer CALL setcontext(0x7f7fff444000)
17368 17368 reproducer RET setcontext JUSTRETURN
17368 17368 reproducer CALL write(1,0x401173,1)
17368 17368 reproducer GIO fd 1 wrote 1 bytes
"."
17368 17368 reproducer RET write 1
17368 17368 reproducer CALL open(0x7f7fff4443d0,1,1)
17368 17368 reproducer NAMI "/tmp/test_fifo_1"
17368 17368 reproducer RET open -1 errno 4 Interrupted system call
17368 17368 reproducer PSIG SIGALRM caught handler=0x400dba mask=(): code=SI_TIMER sent by pid=0, uid=0 with sigval 0x0)
17368 17368 reproducer CALL setcontext(0x7f7fff444000)
17368 17368 reproducer RET setcontext JUSTRETURN
17368 17368 reproducer CALL write(1,0x401173,1)
17368 17368 reproducer GIO fd 1 wrote 1 bytes
"."
17368 17368 reproducer RET write 1
17368 17368 reproducer CALL open(0x7f7fff4443d0,1,1)
17368 17368 reproducer NAMI "/tmp/test_fifo_1"
17368 17368 reproducer RET open -1 errno 4 Interrupted system call
17368 17368 reproducer PSIG SIGALRM caught handler=0x400dba mask=(): code=SI_TIMER sent by pid=0, uid=0 with sigval 0x0)
17368 17368 reproducer CALL setcontext(0x7f7fff444000)
17368 17368 reproducer RET setcontext JUSTRETURN
17368 17368 reproducer CALL write(1,0x401173,1)
17368 17368 reproducer GIO fd 1 wrote 1 bytes
"."
17368 17368 reproducer RET write 1
17368 17368 reproducer CALL open(0x7f7fff4443d0,1,1)
17368 17368 reproducer NAMI "/tmp/test_fifo_1"
17368 17368 reproducer RET open RESTART
17368 17368 reproducer PSIG SIGINT SIG_DFL: code=SI_NOINFO
╭─blue@home ~CPython versions tested on:
CPython main branch, 3.15, 3.14, 3.13
Operating systems tested on:
Other