MINOR: wdt: also consider that waiting in the thread dumper is normal
It happens that upon looping threads the watchdog fires, starts a dump,
and other threads expire their budget while waiting for the other threads
to get dumped and trigger a watchdog event again, adding some confusion
to the traces. With this patch the situation becomes clearer as we export
the list of threads being dumped so that the watchdog can check it before
deciding to trigger. This way such threads in queue for being dumped are
not attempted to be reported in turn.
This should be backported to 2.0 as it helps understand stack traces.
(cherry picked from commit a37cb1880c81b1f038e575d88ba7210aea0b7b8f)
Signed-off-by: Willy Tarreau <w@1wt.eu>
diff --git a/include/common/debug.h b/include/common/debug.h
index 333203d..f43258e 100644
--- a/include/common/debug.h
+++ b/include/common/debug.h
@@ -70,6 +70,7 @@
struct task;
struct buffer;
+extern volatile unsigned long threads_to_dump;
void ha_task_dump(struct buffer *buf, const struct task *task, const char *pfx);
void ha_thread_dump(struct buffer *buf, int thr, int calling_tid);
void ha_thread_dump_all_to_trash();
diff --git a/src/debug.c b/src/debug.c
index 07624ca..3077e97 100644
--- a/src/debug.c
+++ b/src/debug.c
@@ -29,6 +29,11 @@
#include <proto/stream_interface.h>
#include <proto/task.h>
+/* mask of threads still having to dump, used to respect ordering. Only used
+ * when USE_THREAD_DUMP is set.
+ */
+volatile unsigned long threads_to_dump = 0;
+
/* Dumps to the buffer some known information for the desired thread, and
* optionally extra info for the current thread. The dump will be appended to
* the buffer, so the caller is responsible for preliminary initializing it.
@@ -405,9 +410,6 @@
*/
#define DEBUGSIG SIGURG
-/* mask of threads still having to dump, used to respect ordering */
-static volatile unsigned long threads_to_dump;
-
/* ID of the thread requesting the dump */
static unsigned int thread_dump_tid;
diff --git a/src/wdt.c b/src/wdt.c
index 19d36c3..aa89fd4 100644
--- a/src/wdt.c
+++ b/src/wdt.c
@@ -75,7 +75,7 @@
if (n - p < 1000000000UL)
goto update_and_leave;
- if ((threads_harmless_mask|sleeping_thread_mask) & (1UL << thr)) {
+ if ((threads_harmless_mask|sleeping_thread_mask|threads_to_dump) & (1UL << thr)) {
/* This thread is currently doing exactly nothing
* waiting in the poll loop (unlikely but possible),
* waiting for all other threads to join the rendez-vous