[v4] testpmd: cleanup cleanly from signal
Checks
Commit Message
Do a clean shutdown of testpmd when a signal is received;
instead of having testpmd kill itself.
This fixes problem where a signal could be received
in the middle of a PMD and then the signal handler would call
PMD's close routine which could cause a deadlock.
Added benefit is it gets rid of Windows specific code.
Fixes: d9a191a00e81 ("app/testpmd: fix quitting in container")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
v4 - use select() because that is available on Windows; and other
functions poll() and sigaction() are not.
app/test-pmd/testpmd.c | 63 +++++++++++++++++++++++-------------------
1 file changed, 34 insertions(+), 29 deletions(-)
Comments
On 2022-11-09 05:10, Stephen Hemminger wrote:
> Do a clean shutdown of testpmd when a signal is received;
> instead of having testpmd kill itself.
> This fixes problem where a signal could be received
> in the middle of a PMD and then the signal handler would call
> PMD's close routine which could cause a deadlock.
>
> Added benefit is it gets rid of Windows specific code.
>
> Fixes: d9a191a00e81 ("app/testpmd: fix quitting in container")
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
> ---
> v4 - use select() because that is available on Windows; and other
> functions poll() and sigaction() are not.
>
> app/test-pmd/testpmd.c | 63 +++++++++++++++++++++++-------------------
> 1 file changed, 34 insertions(+), 29 deletions(-)
>
> diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
> index cf5942d0c422..274e96cac2d4 100644
> --- a/app/test-pmd/testpmd.c
> +++ b/app/test-pmd/testpmd.c
> @@ -12,6 +12,7 @@
> #ifndef RTE_EXEC_ENV_WINDOWS
> #include <sys/mman.h>
> #endif
> +#include <sys/select.h>
> #include <sys/types.h>
> #include <errno.h>
> #include <stdbool.h>
> @@ -4251,26 +4252,11 @@ print_stats(void)
> static void
> signal_handler(int signum)
> {
> - if (signum == SIGINT || signum == SIGTERM) {
> - fprintf(stderr, "\nSignal %d received, preparing to exit...\n",
> - signum);
> -#ifdef RTE_LIB_PDUMP
> - /* uninitialize packet capture framework */
> - rte_pdump_uninit();
> -#endif
> -#ifdef RTE_LIB_LATENCYSTATS
> - if (latencystats_enabled != 0)
> - rte_latencystats_uninit();
> -#endif
> - force_quit();
> - /* Set flag to indicate the force termination. */
> - f_quit = 1;
> - /* exit with the expected status */
> -#ifndef RTE_EXEC_ENV_WINDOWS
> - signal(signum, SIG_DFL);
> - kill(getpid(), signum);
> -#endif
> - }
> + fprintf(stderr, "\nSignal %d %s received, preparing to exit...\n",
> + signum, strsignal(signum));
fprintf() is not async signal safe, and neither is strsignal().
This is not a regression introduced by this patch, but I thought it
might be worth fixing.
> +
> + /* Set flag to indicate the force termination. */
> + f_quit = 1;
> }
>
> int
> @@ -4449,9 +4435,6 @@ main(int argc, char** argv)
> } else
> #endif
> {
> - char c;
> - int rc;
> -
> f_quit = 0;
>
> printf("No commandline core given, start packet forwarding\n");
> @@ -4476,15 +4459,37 @@ main(int argc, char** argv)
> prev_time = cur_time;
> rte_delay_us_sleep(US_PER_S);
> }
> - }
> + } else {
> + char c;
> + fd_set fds;
>
> - printf("Press enter to exit\n");
> - rc = read(0, &c, 1);
> - pmd_test_exit();
> - if (rc < 0)
> - return 1;
> + printf("Press enter to exit\n");
> +
> + FD_ZERO(&fds);
> + FD_SET(0, &fds);
> +
> + if (select(1, &fds, NULL, NULL, NULL) <= 0) {
> + fprintf(stderr, "Select failed: %s\n",
> + strerror(errno));
Why is select() needed? Wouldn't a blocking read suffice? Or getchar().
> + } else if (read(0, &c, 1) <= 0) {
> + fprintf(stderr,
> + "Read stdin failed: %s\n",
> + strerror(errno));
> + }
> + }
> + stop_packet_forwarding();
> + force_quit();
> }
>
> +#ifdef RTE_LIB_PDUMP
> + /* uninitialize packet capture framework */
> + rte_pdump_uninit();
> +#endif
> +#ifdef RTE_LIB_LATENCYSTATS
> + if (latencystats_enabled != 0)
> + rte_latencystats_uninit();
> +#endif
> +
> ret = rte_eal_cleanup();
> if (ret != 0)
> rte_exit(EXIT_FAILURE,
On Wed, 9 Nov 2022 22:46:55 +0100
Mattias Rönnblom <hofors@lysator.liu.se> wrote:
> On 2022-11-09 05:10, Stephen Hemminger wrote:
> > Do a clean shutdown of testpmd when a signal is received;
> > instead of having testpmd kill itself.
> > This fixes problem where a signal could be received
> > in the middle of a PMD and then the signal handler would call
> > PMD's close routine which could cause a deadlock.
> >
> > Added benefit is it gets rid of Windows specific code.
> >
> > Fixes: d9a191a00e81 ("app/testpmd: fix quitting in container")
> > Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
> > ---
> > v4 - use select() because that is available on Windows; and other
> > functions poll() and sigaction() are not.
> >
> > app/test-pmd/testpmd.c | 63 +++++++++++++++++++++++-------------------
> > 1 file changed, 34 insertions(+), 29 deletions(-)
> >
> > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
> > index cf5942d0c422..274e96cac2d4 100644
> > --- a/app/test-pmd/testpmd.c
> > +++ b/app/test-pmd/testpmd.c
> > @@ -12,6 +12,7 @@
> > #ifndef RTE_EXEC_ENV_WINDOWS
> > #include <sys/mman.h>
> > #endif
> > +#include <sys/select.h>
> > #include <sys/types.h>
> > #include <errno.h>
> > #include <stdbool.h>
> > @@ -4251,26 +4252,11 @@ print_stats(void)
> > static void
> > signal_handler(int signum)
> > {
> > - if (signum == SIGINT || signum == SIGTERM) {
> > - fprintf(stderr, "\nSignal %d received, preparing to exit...\n",
> > - signum);
> > -#ifdef RTE_LIB_PDUMP
> > - /* uninitialize packet capture framework */
> > - rte_pdump_uninit();
> > -#endif
> > -#ifdef RTE_LIB_LATENCYSTATS
> > - if (latencystats_enabled != 0)
> > - rte_latencystats_uninit();
> > -#endif
> > - force_quit();
> > - /* Set flag to indicate the force termination. */
> > - f_quit = 1;
> > - /* exit with the expected status */
> > -#ifndef RTE_EXEC_ENV_WINDOWS
> > - signal(signum, SIG_DFL);
> > - kill(getpid(), signum);
> > -#endif
> > - }
> > + fprintf(stderr, "\nSignal %d %s received, preparing to exit...\n",
> > + signum, strsignal(signum));
>
> fprintf() is not async signal safe, and neither is strsignal().
>
> This is not a regression introduced by this patch, but I thought it
> might be worth fixing.
>
> > +
> > + /* Set flag to indicate the force termination. */
> > + f_quit = 1;
> > }
> >
> > int
> > @@ -4449,9 +4435,6 @@ main(int argc, char** argv)
> > } else
> > #endif
> > {
> > - char c;
> > - int rc;
> > -
> > f_quit = 0;
> >
> > printf("No commandline core given, start packet forwarding\n");
> > @@ -4476,15 +4459,37 @@ main(int argc, char** argv)
> > prev_time = cur_time;
> > rte_delay_us_sleep(US_PER_S);
> > }
> > - }
> > + } else {
> > + char c;
> > + fd_set fds;
> >
> > - printf("Press enter to exit\n");
> > - rc = read(0, &c, 1);
> > - pmd_test_exit();
> > - if (rc < 0)
> > - return 1;
> > + printf("Press enter to exit\n");
> > +
> > + FD_ZERO(&fds);
> > + FD_SET(0, &fds);
> > +
> > + if (select(1, &fds, NULL, NULL, NULL) <= 0) {
> > + fprintf(stderr, "Select failed: %s\n",
> > + strerror(errno));
>
> Why is select() needed? Wouldn't a blocking read suffice? Or getchar().
On Linux, signal set SA_RESTART so a simple read is not interrupted.
One option was to use sigaction() which allows controlling flags, but that
won't work on Windows. Using select() works on both.
On 2022-11-09 23:53, Stephen Hemminger wrote:
> On Wed, 9 Nov 2022 22:46:55 +0100
> Mattias Rönnblom <hofors@lysator.liu.se> wrote:
>
>> On 2022-11-09 05:10, Stephen Hemminger wrote:
>>> Do a clean shutdown of testpmd when a signal is received;
>>> instead of having testpmd kill itself.
>>> This fixes problem where a signal could be received
>>> in the middle of a PMD and then the signal handler would call
>>> PMD's close routine which could cause a deadlock.
>>>
>>> Added benefit is it gets rid of Windows specific code.
>>>
>>> Fixes: d9a191a00e81 ("app/testpmd: fix quitting in container")
>>> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
>>> ---
>>> v4 - use select() because that is available on Windows; and other
>>> functions poll() and sigaction() are not.
>>>
>>> app/test-pmd/testpmd.c | 63 +++++++++++++++++++++++-------------------
>>> 1 file changed, 34 insertions(+), 29 deletions(-)
>>>
>>> diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
>>> index cf5942d0c422..274e96cac2d4 100644
>>> --- a/app/test-pmd/testpmd.c
>>> +++ b/app/test-pmd/testpmd.c
>>> @@ -12,6 +12,7 @@
>>> #ifndef RTE_EXEC_ENV_WINDOWS
>>> #include <sys/mman.h>
>>> #endif
>>> +#include <sys/select.h>
>>> #include <sys/types.h>
>>> #include <errno.h>
>>> #include <stdbool.h>
>>> @@ -4251,26 +4252,11 @@ print_stats(void)
>>> static void
>>> signal_handler(int signum)
>>> {
>>> - if (signum == SIGINT || signum == SIGTERM) {
>>> - fprintf(stderr, "\nSignal %d received, preparing to exit...\n",
>>> - signum);
>>> -#ifdef RTE_LIB_PDUMP
>>> - /* uninitialize packet capture framework */
>>> - rte_pdump_uninit();
>>> -#endif
>>> -#ifdef RTE_LIB_LATENCYSTATS
>>> - if (latencystats_enabled != 0)
>>> - rte_latencystats_uninit();
>>> -#endif
>>> - force_quit();
>>> - /* Set flag to indicate the force termination. */
>>> - f_quit = 1;
>>> - /* exit with the expected status */
>>> -#ifndef RTE_EXEC_ENV_WINDOWS
>>> - signal(signum, SIG_DFL);
>>> - kill(getpid(), signum);
>>> -#endif
>>> - }
>>> + fprintf(stderr, "\nSignal %d %s received, preparing to exit...\n",
>>> + signum, strsignal(signum));
>>
>> fprintf() is not async signal safe, and neither is strsignal().
>>
>> This is not a regression introduced by this patch, but I thought it
>> might be worth fixing.
>>
>>> +
>>> + /* Set flag to indicate the force termination. */
>>> + f_quit = 1;
>>> }
>>>
>>> int
>>> @@ -4449,9 +4435,6 @@ main(int argc, char** argv)
>>> } else
>>> #endif
>>> {
>>> - char c;
>>> - int rc;
>>> -
>>> f_quit = 0;
>>>
>>> printf("No commandline core given, start packet forwarding\n");
>>> @@ -4476,15 +4459,37 @@ main(int argc, char** argv)
>>> prev_time = cur_time;
>>> rte_delay_us_sleep(US_PER_S);
>>> }
>>> - }
>>> + } else {
>>> + char c;
>>> + fd_set fds;
>>>
>>> - printf("Press enter to exit\n");
>>> - rc = read(0, &c, 1);
>>> - pmd_test_exit();
>>> - if (rc < 0)
>>> - return 1;
>>> + printf("Press enter to exit\n");
>>> +
>>> + FD_ZERO(&fds);
>>> + FD_SET(0, &fds);
>>> +
>>> + if (select(1, &fds, NULL, NULL, NULL) <= 0) {
>>> + fprintf(stderr, "Select failed: %s\n",
>>> + strerror(errno));
>>
>> Why is select() needed? Wouldn't a blocking read suffice? Or getchar().
>
> On Linux, signal set SA_RESTART so a simple read is not interrupted.
> One option was to use sigaction() which allows controlling flags, but that
> won't work on Windows. Using select() works on both.
>
OK, so select() is used because a signal might interrupt read() on Windows?
while (read(0, &c, 1) == -1 && errno == EINTR)
;
Would that work?
(select() won't return 0 since you don't have a timeout.)
On Thu, 10 Nov 2022 08:50:40 +0100
Mattias Rönnblom <hofors@lysator.liu.se> wrote:
> >>
> >> Why is select() needed? Wouldn't a blocking read suffice? Or getchar().
> >
> > On Linux, signal set SA_RESTART so a simple read is not interrupted.
> > One option was to use sigaction() which allows controlling flags, but that
> > won't work on Windows. Using select() works on both.
> >
>
> OK, so select() is used because a signal might interrupt read() on Windows?
>
> while (read(0, &c, 1) == -1 && errno == EINTR)
> ;
>
> Would that work?
Try it. On Linux the read never gets interrupted.
On 2022-11-10 17:14, Stephen Hemminger wrote:
> On Thu, 10 Nov 2022 08:50:40 +0100
> Mattias Rönnblom <hofors@lysator.liu.se> wrote:
>
>>>>
>>>> Why is select() needed? Wouldn't a blocking read suffice? Or getchar().
>>>
>>> On Linux, signal set SA_RESTART so a simple read is not interrupted.
>>> One option was to use sigaction() which allows controlling flags, but that
>>> won't work on Windows. Using select() works on both.
>>>
>>
>> OK, so select() is used because a signal might interrupt read() on Windows?
>>
>> while (read(0, &c, 1) == -1 && errno == EINTR)
>> ;
>>
>> Would that work?
>
> Try it. On Linux the read never gets interrupted.
I had no doubts about that, but I misunderstood the code and thought
that was the required behavior.
@@ -12,6 +12,7 @@
#ifndef RTE_EXEC_ENV_WINDOWS
#include <sys/mman.h>
#endif
+#include <sys/select.h>
#include <sys/types.h>
#include <errno.h>
#include <stdbool.h>
@@ -4251,26 +4252,11 @@ print_stats(void)
static void
signal_handler(int signum)
{
- if (signum == SIGINT || signum == SIGTERM) {
- fprintf(stderr, "\nSignal %d received, preparing to exit...\n",
- signum);
-#ifdef RTE_LIB_PDUMP
- /* uninitialize packet capture framework */
- rte_pdump_uninit();
-#endif
-#ifdef RTE_LIB_LATENCYSTATS
- if (latencystats_enabled != 0)
- rte_latencystats_uninit();
-#endif
- force_quit();
- /* Set flag to indicate the force termination. */
- f_quit = 1;
- /* exit with the expected status */
-#ifndef RTE_EXEC_ENV_WINDOWS
- signal(signum, SIG_DFL);
- kill(getpid(), signum);
-#endif
- }
+ fprintf(stderr, "\nSignal %d %s received, preparing to exit...\n",
+ signum, strsignal(signum));
+
+ /* Set flag to indicate the force termination. */
+ f_quit = 1;
}
int
@@ -4449,9 +4435,6 @@ main(int argc, char** argv)
} else
#endif
{
- char c;
- int rc;
-
f_quit = 0;
printf("No commandline core given, start packet forwarding\n");
@@ -4476,15 +4459,37 @@ main(int argc, char** argv)
prev_time = cur_time;
rte_delay_us_sleep(US_PER_S);
}
- }
+ } else {
+ char c;
+ fd_set fds;
- printf("Press enter to exit\n");
- rc = read(0, &c, 1);
- pmd_test_exit();
- if (rc < 0)
- return 1;
+ printf("Press enter to exit\n");
+
+ FD_ZERO(&fds);
+ FD_SET(0, &fds);
+
+ if (select(1, &fds, NULL, NULL, NULL) <= 0) {
+ fprintf(stderr, "Select failed: %s\n",
+ strerror(errno));
+ } else if (read(0, &c, 1) <= 0) {
+ fprintf(stderr,
+ "Read stdin failed: %s\n",
+ strerror(errno));
+ }
+ }
+ stop_packet_forwarding();
+ force_quit();
}
+#ifdef RTE_LIB_PDUMP
+ /* uninitialize packet capture framework */
+ rte_pdump_uninit();
+#endif
+#ifdef RTE_LIB_LATENCYSTATS
+ if (latencystats_enabled != 0)
+ rte_latencystats_uninit();
+#endif
+
ret = rte_eal_cleanup();
if (ret != 0)
rte_exit(EXIT_FAILURE,