core: introduce new Restart=on-abnormal setting
Restart=on-abnormal is similar to Restart=on-failure, but avoids restarts on unclean exit codes (but still doing restarts on all obviously unclean exits, such as timeouts, signals, coredumps, watchdog timeouts). Also see: https://fedorahosted.org/fpc/ticket/191
This commit is contained in:
Lennart Poettering
+124
-29
@@ -703,51 +703,146 @@ ExecStart=/bin/echo $ONE $TWO ${TWO}</programlisting>
|
||||
<option>no</option>,
|
||||
<option>on-success</option>,
|
||||
<option>on-failure</option>,
|
||||
<option>on-abnormal</option>,
|
||||
<option>on-watchdog</option>,
|
||||
<option>on-abort</option>, or
|
||||
<option>always</option>. If set to
|
||||
<option>no</option> (the default), the
|
||||
service will not be restarted. If set to
|
||||
<option>on-success</option>, it will be
|
||||
restarted only when the service process
|
||||
exits cleanly.
|
||||
In this context, a clean exit means
|
||||
an exit code of 0, or one of the signals
|
||||
service will not be restarted. If set
|
||||
to <option>on-success</option>, it
|
||||
will be restarted only when the
|
||||
service process exits cleanly. In
|
||||
this context, a clean exit means an
|
||||
exit code of 0, or one of the signals
|
||||
<constant>SIGHUP</constant>,
|
||||
<constant>SIGINT</constant>,
|
||||
<constant>SIGTERM</constant>,
|
||||
or <constant>SIGPIPE</constant>, and
|
||||
additionally, exit statuses and signals
|
||||
specified in <varname>SuccessExitStatus=</varname>.
|
||||
<constant>SIGTERM</constant> or
|
||||
<constant>SIGPIPE</constant>, and
|
||||
additionally, exit statuses and
|
||||
signals specified in
|
||||
<varname>SuccessExitStatus=</varname>.
|
||||
If set to <option>on-failure</option>,
|
||||
the service will be restarted when the
|
||||
process exits with a non-zero exit code,
|
||||
is terminated by a signal (including on
|
||||
core dump), when an operation (such as
|
||||
service reload) times out, and when the
|
||||
configured watchdog timeout is triggered.
|
||||
If set to
|
||||
<option>on-abort</option>, the service
|
||||
will be restarted only if the service
|
||||
process exits due to an uncaught
|
||||
signal not specified as a clean exit
|
||||
status.
|
||||
If set to
|
||||
<option>on-watchdog</option>, the service
|
||||
will be restarted only if the watchdog
|
||||
timeout for the service expires.
|
||||
If set to
|
||||
process exits with a non-zero exit
|
||||
code, is terminated by a signal
|
||||
(including on core dump, but excluding
|
||||
the aforementiond four signals), when
|
||||
an operation (such as service reload)
|
||||
times out, and when the configured
|
||||
watchdog timeout is triggered. If set
|
||||
to <option>on-abnormal</option>, the
|
||||
service will be restarted when the
|
||||
process is terminated by a signal
|
||||
(including on core dump, excluding the
|
||||
aforementioned four signals), when an
|
||||
operation times out, or when the
|
||||
watchdog timeout is triggered. If set
|
||||
to <option>on-abort</option>, the
|
||||
service will be restarted only if the
|
||||
service process exits due to an
|
||||
uncaught signal not specified as a
|
||||
clean exit status. If set to
|
||||
<option>on-watchdog</option>, the
|
||||
service will be restarted only if the
|
||||
watchdog timeout for the service
|
||||
expires. If set to
|
||||
<option>always</option>, the service
|
||||
will be restarted regardless of whether
|
||||
it exited cleanly or not, got
|
||||
will be restarted regardless of
|
||||
whether it exited cleanly or not, got
|
||||
terminated abnormally by a signal, or
|
||||
hit a timeout.</para>
|
||||
|
||||
<table>
|
||||
<title>Exit causes and the effect of the <varname>Restart=</varname> settings on them</title>
|
||||
|
||||
<tgroup cols='2'>
|
||||
<colspec colname='path' />
|
||||
<colspec colname='expl' />
|
||||
<thead>
|
||||
<row>
|
||||
<entry>Restart settings/Exit causes</entry>
|
||||
<entry><option>no</option></entry>
|
||||
<entry><option>always</option></entry>
|
||||
<entry><option>on-success</option></entry>
|
||||
<entry><option>on-failure</option></entry>
|
||||
<entry><option>on-abnormal</option></entry>
|
||||
<entry><option>on-abort</option></entry>
|
||||
<entry><option>on-watchdog</option></entry>
|
||||
</row>
|
||||
</thead>
|
||||
<tbody>
|
||||
<row>
|
||||
<entry>Clean exit code or signal</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry/>
|
||||
<entry/>
|
||||
<entry/>
|
||||
</row>
|
||||
<row>
|
||||
<entry>Unclean exit code</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry/>
|
||||
<entry/>
|
||||
</row>
|
||||
<row>
|
||||
<entry>Unclean signal</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry>X</entry>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
</row>
|
||||
<row>
|
||||
<entry>Timeout</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry/>
|
||||
</row>
|
||||
<row>
|
||||
<entry>Watchdog</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
<entry>X</entry>
|
||||
<entry/>
|
||||
<entry>X</entry>
|
||||
</row>
|
||||
</tbody>
|
||||
</tgroup>
|
||||
</table>
|
||||
|
||||
<para>In addition to the above settings,
|
||||
the service will not be restarted if the
|
||||
exit code or signal is specified in
|
||||
<varname>RestartPreventExitStatus=</varname>
|
||||
(see below).</para></listitem>
|
||||
(see below).</para>
|
||||
|
||||
<para>Setting this to
|
||||
<option>on-failure</option> is the
|
||||
recommended choice for long-running
|
||||
services, in order to increase
|
||||
reliability by attempting automatic
|
||||
recovery from errors. For services
|
||||
that shall be able to terminate on
|
||||
their own choice (and avoiding
|
||||
immediate restart)
|
||||
<option>on-abnormal</option> is an
|
||||
alternative choice.</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry>
|
||||
|
||||
+4
-3
@@ -1867,9 +1867,9 @@ static void service_enter_dead(Service *s, ServiceResult f, bool allow_restart)
|
||||
(s->restart == SERVICE_RESTART_ALWAYS ||
|
||||
(s->restart == SERVICE_RESTART_ON_SUCCESS && s->result == SERVICE_SUCCESS) ||
|
||||
(s->restart == SERVICE_RESTART_ON_FAILURE && s->result != SERVICE_SUCCESS) ||
|
||||
(s->restart == SERVICE_RESTART_ON_ABNORMAL && !IN_SET(s->result, SERVICE_SUCCESS, SERVICE_FAILURE_EXIT_CODE)) ||
|
||||
(s->restart == SERVICE_RESTART_ON_WATCHDOG && s->result == SERVICE_FAILURE_WATCHDOG) ||
|
||||
(s->restart == SERVICE_RESTART_ON_ABORT && (s->result == SERVICE_FAILURE_SIGNAL ||
|
||||
s->result == SERVICE_FAILURE_CORE_DUMP))) &&
|
||||
(s->restart == SERVICE_RESTART_ON_ABORT && IN_SET(s->result, SERVICE_FAILURE_SIGNAL, SERVICE_FAILURE_CORE_DUMP))) &&
|
||||
(s->result != SERVICE_FAILURE_EXIT_CODE ||
|
||||
!set_contains(s->restart_ignore_status.code, INT_TO_PTR(s->main_exec_status.status))) &&
|
||||
(s->result != SERVICE_FAILURE_SIGNAL ||
|
||||
@@ -3790,9 +3790,10 @@ static const char* const service_restart_table[_SERVICE_RESTART_MAX] = {
|
||||
[SERVICE_RESTART_NO] = "no",
|
||||
[SERVICE_RESTART_ON_SUCCESS] = "on-success",
|
||||
[SERVICE_RESTART_ON_FAILURE] = "on-failure",
|
||||
[SERVICE_RESTART_ON_ABNORMAL] = "on-abnormal",
|
||||
[SERVICE_RESTART_ON_WATCHDOG] = "on-watchdog",
|
||||
[SERVICE_RESTART_ON_ABORT] = "on-abort",
|
||||
[SERVICE_RESTART_ALWAYS] = "always"
|
||||
[SERVICE_RESTART_ALWAYS] = "always",
|
||||
};
|
||||
|
||||
DEFINE_STRING_TABLE_LOOKUP(service_restart, ServiceRestart);
|
||||
|
||||
@@ -53,6 +53,7 @@ typedef enum ServiceRestart {
|
||||
SERVICE_RESTART_NO,
|
||||
SERVICE_RESTART_ON_SUCCESS,
|
||||
SERVICE_RESTART_ON_FAILURE,
|
||||
SERVICE_RESTART_ON_ABNORMAL,
|
||||
SERVICE_RESTART_ON_WATCHDOG,
|
||||
SERVICE_RESTART_ON_ABORT,
|
||||
SERVICE_RESTART_ALWAYS,
|
||||
|
||||
Reference in New Issue
Block a user