[v2,16/27] fsm-health-win32: add polling framework to monitor daemon health

Commit Message

Jeff Hostetler March 8, 2022, 10:15 p.m. UTC

From: Jeff Hostetler <[e-mail]>

Extend the Windows version of the "health" thread to periodically
inspect the system and shutdown if warranted.

This commit updates the thread's wait loop to use a timeout and
defines a (currently empty) table of functions to poll the system.

A later commit will add functions to the table to actually
inspect the system.

Signed-off-by: Jeff Hostetler <[e-mail]>
---
 compat/fsmonitor/fsm-health-win32.c | 65 ++++++++++++++++++++++++++++-
 1 file changed, 64 insertions(+), 1 deletion(-)

Patch

diff --git a/compat/fsmonitor/fsm-health-win32.c b/compat/fsmonitor/fsm-health-win32.c
index 94b1d020f25..24fc612bf02 100644
--- a/compat/fsmonitor/fsm-health-win32.c
+++ b/compat/fsmonitor/fsm-health-win32.c
@@ -4,6 +4,24 @@ 
 #include "fsm-health.h"
 #include "fsmonitor--daemon.h"
 
+/*
+ * Every minute wake up and test our health.
+ */
+#define WAIT_FREQ_MS (60 * 1000)
+
+/*
+ * State machine states for each of the interval functions
+ * used for polling our health.
+ */
+enum interval_fn_ctx {
+	CTX_INIT = 0,
+	CTX_TERM,
+	CTX_TIMER
+};
+
+typedef int (interval_fn)(struct fsmonitor_daemon_state *state,
+			  enum interval_fn_ctx ctx);
+
 struct fsm_health_data
 {
 	HANDLE hEventShutdown;
@@ -42,18 +60,61 @@  void fsm_health__dtor(struct fsmonitor_daemon_state *state)
 	FREE_AND_NULL(state->health_data);
 }
 
+/*
+ * A table of the polling functions.
+ */
+static interval_fn *table[] = {
+	NULL, /* must be last */
+};
+
+/*
+ * Call all of the polling functions in the table.
+ * Shortcut and return first error.
+ *
+ * Return 0 if all succeeded.
+ */
+static int call_all(struct fsmonitor_daemon_state *state,
+		    enum interval_fn_ctx ctx)
+{
+	int k;
+
+	for (k = 0; table[k]; k++) {
+		int r = table[k](state, ctx);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
 void fsm_health__loop(struct fsmonitor_daemon_state *state)
 {
 	struct fsm_health_data *data = state->health_data;
+	int r;
+
+	r = call_all(state, CTX_INIT);
+	if (r < 0)
+		goto force_error_stop;
+	if (r > 0)
+		goto force_shutdown;
 
 	for (;;) {
 		DWORD dwWait = WaitForMultipleObjects(data->nr_handles,
 						      data->hHandles,
-						      FALSE, INFINITE);
+						      FALSE, WAIT_FREQ_MS);
 
 		if (dwWait == WAIT_OBJECT_0 + HEALTH_SHUTDOWN)
 			goto clean_shutdown;
 
+		if (dwWait == WAIT_TIMEOUT) {
+			r = call_all(state, CTX_TIMER);
+			if (r < 0)
+				goto force_error_stop;
+			if (r > 0)
+				goto force_shutdown;
+			continue;
+		}
+
 		error(_("health thread wait failed [GLE %ld]"),
 		      GetLastError());
 		goto force_error_stop;
@@ -61,8 +122,10 @@  void fsm_health__loop(struct fsmonitor_daemon_state *state)
 
 force_error_stop:
 	state->health_error_code = -1;
+force_shutdown:
 	ipc_server_stop_async(state->ipc_server_data);
 clean_shutdown:
+	call_all(state, CTX_TERM);
 	return;
 }