The following changes since commit ca0122d822ea7dd573f05ca4cf43c5d0ff9f4adb:
backend: if we can't grab stat_mutex, report a deadlock error and exit (2016-10-23 08:35:14 -0600)
are available in the git repository at:
git://git.kernel.dk/fio.git master
for you to fetch changes up to 43f248c4527a49d3de0cd758ce669f7736028ea4:
Use the POSIX `EDEADLK` instead of the Linux `EDEADLOCK` (2016-10-24 20:48:43 -0600)
----------------------------------------------------------------
Bruce Cran (1):
Use the POSIX `EDEADLK` instead of the Linux `EDEADLOCK`
Jens Axboe (3):
mutex: clear mutex when removed
fio: make job reap timeout 5 minutes
backend: end IO loop early, if the job is marked as terminated
backend.c | 10 +++++++++-
fio.h | 2 +-
mutex.c | 6 ++++++
3 files changed, 16 insertions(+), 2 deletions(-)
---
Diff of recent changes:
diff --git a/backend.c b/backend.c
index 093b6a3..ed4f1f0 100644
--- a/backend.c
+++ b/backend.c
@@ -1723,6 +1723,14 @@ static void *thread_main(void *data)
}
}
+ /*
+ * If we took too long to shut down, the main thread could
+ * already consider us reaped/exited. If that happens, break
+ * out and clean up.
+ */
+ if (td->runstate >= TD_EXITED)
+ break;
+
clear_state = 1;
/*
@@ -1740,7 +1748,7 @@ static void *thread_main(void *data)
usleep(1000);
if (deadlock_loop_cnt++ > 5000) {
log_err("fio seems to be stuck grabbing stat_mutex, forcibly exiting\n");
- td->error = EDEADLOCK;
+ td->error = EDEADLK;
goto err;
}
} while (1);
diff --git a/fio.h b/fio.h
index 080842a..74c1b30 100644
--- a/fio.h
+++ b/fio.h
@@ -588,7 +588,7 @@ extern const char *runstate_to_name(int runstate);
* Allow 60 seconds for a job to quit on its own, otherwise reap with
* a vengeance.
*/
-#define FIO_REAP_TIMEOUT 60
+#define FIO_REAP_TIMEOUT 300
#define TERMINATE_ALL (-1U)
extern void fio_terminate_threads(unsigned int);
diff --git a/mutex.c b/mutex.c
index 7580922..e5b045e 100644
--- a/mutex.c
+++ b/mutex.c
@@ -22,6 +22,12 @@ void __fio_mutex_remove(struct fio_mutex *mutex)
{
assert(mutex->magic == FIO_MUTEX_MAGIC);
pthread_cond_destroy(&mutex->cond);
+
+ /*
+ * Ensure any subsequent attempt to grab this mutex will fail
+ * with an assert, instead of just silently hanging.
+ */
+ memset(mutex, 0, sizeof(*mutex));
}
void fio_mutex_remove(struct fio_mutex *mutex)
--
To unsubscribe from this list: send the line "unsubscribe fio" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
