tools/oxenstored: Set uncaught exception handler

Unhandled exceptions go to stderr by default, but this doesn't typically work
for oxenstored because:
 * daemonize reopens stderr as /dev/null
 * systemd redirects stderr to /dev/null too

Debugging an unhandled exception requires reproducing the issue locally when
using --no-fork, and is not conducive to figuring out what went wrong on a
remote system.

Install a custom handler which also tries to render the backtrace to the
configured syslog facility, and DAEMON|ERR otherwise.

Signed-off-by: Edwin Török <edvin.torok@citrix.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Christian Lindig <christian.lindig@citrix.com>
(cherry picked from commit ee7815f49faf743e960dac9e72809eb66393bc6d)

diff --git a/tools/ocaml/xenstored/logging.ml b/tools/ocaml/xenstored/logging.ml
index 39c3036155a2d111fb0205f018c42f946c3c66be..255051437d609a0bbb1ef2d5335b70ff5bf66d61 100644 (file)
--- a/tools/ocaml/xenstored/logging.ml
+++ b/tools/ocaml/xenstored/logging.ml
@@ -342,3 +342,32 @@ let xb_answer ~tid ~con ~ty data =
 let watch_not_fired ~con perms path =
        let data = Printf.sprintf "EPERM perms=[%s] path=%s" perms path in
        access_logging ~tid:0 ~con ~data Watch_not_fired ~level:Info
+
+let msg_of exn bt =
+       Printf.sprintf "Fatal exception: %s\n%s\n" (Printexc.to_string exn)
+               (Printexc.raw_backtrace_to_string bt)
+
+let fallback_exception_handler exn bt =
+       (* stderr goes to /dev/null, so use the logger where possible,
+          but always print to stderr too, in case everything else fails,
+          e.g. this can be used to debug with --no-fork
+
+          this function should try not to raise exceptions, but if it does
+          the ocaml runtime should still print the exception, both the original,
+          and the one from this function, but to stderr this time
+        *)
+       let msg = msg_of exn bt in
+       prerr_endline msg;
+       (* See Printexc.set_uncaught_exception_handler, need to flush,
+          so has to call stop and flush *)
+       match !xenstored_logger with
+       | Some l -> error "xenstored-fallback" "%s" msg; l.stop ()
+       | None ->
+               (* Too early, no logger set yet.
+                  We normally try to use the configured logger so we don't flood syslog
+                  during development for example, or if the user has a file set
+                *)
+               try Syslog.log Syslog.Daemon Syslog.Err msg
+               with e ->
+                       let bt = Printexc.get_raw_backtrace () in
+                       prerr_endline @@ msg_of e bt

diff --git a/tools/ocaml/xenstored/xenstored.ml b/tools/ocaml/xenstored/xenstored.ml
index 35b8cbd43fdcc25ad03dc66b129950bbee8633ad..4d5851c5cb681c6ff326df9a3eb70c307e4315ab 100644 (file)
--- a/tools/ocaml/xenstored/xenstored.ml
+++ b/tools/ocaml/xenstored/xenstored.ml
@@ -355,7 +355,8 @@ let tweak_gc () =
        Gc.set { (Gc.get ()) with Gc.max_overhead = !Define.gc_max_overhead }
 
 
-let _ =
+let () =
+       Printexc.set_uncaught_exception_handler Logging.fallback_exception_handler;
        let cf = do_argv in
        let pidfile =
                if Sys.file_exists (config_filename cf) then