[pve-devel] [PATCH ha-manager 2/3] watchdog: warn when about to expire

[Maximiliano Sandoval]

Signed-off-by: Maximiliano Sandoval <m.sandoval at proxmox.com>
---
 src/watchdog-mux.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/src/watchdog-mux.c b/src/watchdog-mux.c
index a9017b3..e14c768 100644
--- a/src/watchdog-mux.c
+++ b/src/watchdog-mux.c
@@ -29,15 +29,24 @@
 
 #define JOURNALCTL_BIN "/bin/journalctl"
 
+#define CLIENT_WATCHDOG_TIMEOUT_WARNING 50
+
 int watchdog_fd = -1;
 int watchdog_timeout = 10;
 int client_watchdog_timeout = 60;
 int update_watchdog = 1;
 
+enum warning_state_t {
+   NONE,
+   WARNING_ISSUED,
+   CRISIS_AVERTED,
+};
+
 typedef struct {
     int fd;
     time_t time;
     int magic_close;
+    enum warning_state_t warning_state;
 } wd_client_t;
 
 #define MAX_CLIENTS 100
@@ -54,6 +63,7 @@ alloc_client(int fd, time_t time)
             client_list[i].fd = fd;
             client_list[i].time = time;
             client_list[i].magic_close = 0;
+            client_list[i].warning_state = NONE;
             return &client_list[i];
         }
     }
@@ -244,6 +254,22 @@ main(void)
                 time_t ctime = time(NULL);
                 for (i = 0; i < MAX_CLIENTS; i++) {
                     if (client_list[i].fd != 0 && client_list[i].time != 0) {
+                        if (
+                            client_list[i].warning_state == WARNING_ISSUED
+                            && (ctime - client_list[i].time) <= CLIENT_WATCHDOG_TIMEOUT_WARNING
+                        ) {
+                            client_list[i].warning_state = CRISIS_AVERTED;
+                            fprintf(stderr, "phew, client watchdog was updated before expiring\n");
+                        }
+
+                        if (
+                            client_list[i].warning_state != WARNING_ISSUED
+                            && (ctime - client_list[i].time) > CLIENT_WATCHDOG_TIMEOUT_WARNING
+                        ) {
+                            client_list[i].warning_state = WARNING_ISSUED;
+                            fprintf(stderr, "client watchdog is about to expire\n");
+                        }
+
                         if ((ctime - client_list[i].time) > client_watchdog_timeout) {
                             update_watchdog = 0;
                             fprintf(stderr, "client watchdog expired - disable watchdog updates\n");
-- 
2.39.5