pid1: add unit file settings to control memory pressure logic

4 files changed, 153 insertions, 0 deletions

diff --git a/man/org.freedesktop.systemd1.xml b/man/org.freedesktop.systemd1.xml
index 3f19d2f56a..141fde05b4 100644
--- a/man/org.freedesktop.systemd1.xml
+++ b/man/org.freedesktop.systemd1.xml
@@ -529,6 +529,10 @@ node /org/freedesktop/systemd1 {
       readonly t DefaultLimitRTTIMESoft = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly t DefaultTasksMax = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t DefaultMemoryPressureThresholdUSec = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s DefaultMemoryPressureWatch = '...';
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
       readonly t TimerSlackNSec = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
@@ -782,6 +786,10 @@ node /org/freedesktop/systemd1 {
 
     <!--property DefaultTasksMax is not documented!-->
 
+    <!--property DefaultMemoryPressureThresholdUSec is not documented!-->
+
+    <!--property DefaultMemoryPressureWatch is not documented!-->
+
     <!--property TimerSlackNSec is not documented!-->
 
     <!--property DefaultOOMPolicy is not documented!-->
@@ -1208,6 +1216,10 @@ node /org/freedesktop/systemd1 {
 
     <variablelist class="dbus-property" generated="True" extra-ref="DefaultTasksMax"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="DefaultMemoryPressureThresholdUSec"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="DefaultMemoryPressureWatch"/>
+
     <variablelist class="dbus-property" generated="True" extra-ref="TimerSlackNSec"/>
 
     <variablelist class="dbus-property" generated="True" extra-ref="DefaultOOMPolicy"/>
@@ -2803,6 +2815,10 @@ node /org/freedesktop/systemd1/unit/avahi_2ddaemon_2eservice {
       readonly a(iiqq) SocketBindDeny = [...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly (bas) RestrictNetworkInterfaces = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s MemoryPressureWatch = '...';
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t MemoryPressureThresholdUSec = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
       readonly as Environment = ['...', ...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
@@ -3395,6 +3411,10 @@ node /org/freedesktop/systemd1/unit/avahi_2ddaemon_2eservice {
 
     <!--property RestrictNetworkInterfaces is not documented!-->
 
+    <!--property MemoryPressureWatch is not documented!-->
+
+    <!--property MemoryPressureThresholdUSec is not documented!-->
+
     <!--property EnvironmentFiles is not documented!-->
 
     <!--property PassEnvironment is not documented!-->
@@ -3995,6 +4015,10 @@ node /org/freedesktop/systemd1/unit/avahi_2ddaemon_2eservice {
 
     <variablelist class="dbus-property" generated="True" extra-ref="RestrictNetworkInterfaces"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureWatch"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureThresholdUSec"/>
+
     <variablelist class="dbus-property" generated="True" extra-ref="Environment"/>
 
     <variablelist class="dbus-property" generated="True" extra-ref="EnvironmentFiles"/>
@@ -4747,6 +4771,10 @@ node /org/freedesktop/systemd1/unit/avahi_2ddaemon_2esocket {
       readonly a(iiqq) SocketBindDeny = [...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly (bas) RestrictNetworkInterfaces = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s MemoryPressureWatch = '...';
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t MemoryPressureThresholdUSec = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
       readonly as Environment = ['...', ...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
@@ -5359,6 +5387,10 @@ node /org/freedesktop/systemd1/unit/avahi_2ddaemon_2esocket {
 
     <!--property RestrictNetworkInterfaces is not documented!-->
 
+    <!--property MemoryPressureWatch is not documented!-->
+
+    <!--property MemoryPressureThresholdUSec is not documented!-->
+
     <!--property EnvironmentFiles is not documented!-->
 
     <!--property PassEnvironment is not documented!-->
@@ -5949,6 +5981,10 @@ node /org/freedesktop/systemd1/unit/avahi_2ddaemon_2esocket {
 
     <variablelist class="dbus-property" generated="True" extra-ref="RestrictNetworkInterfaces"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureWatch"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureThresholdUSec"/>
+
     <variablelist class="dbus-property" generated="True" extra-ref="Environment"/>
 
     <variablelist class="dbus-property" generated="True" extra-ref="EnvironmentFiles"/>
@@ -6590,6 +6626,10 @@ node /org/freedesktop/systemd1/unit/home_2emount {
       readonly a(iiqq) SocketBindDeny = [...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly (bas) RestrictNetworkInterfaces = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s MemoryPressureWatch = '...';
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t MemoryPressureThresholdUSec = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
       readonly as Environment = ['...', ...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
@@ -7130,6 +7170,10 @@ node /org/freedesktop/systemd1/unit/home_2emount {
 
     <!--property RestrictNetworkInterfaces is not documented!-->
 
+    <!--property MemoryPressureWatch is not documented!-->
+
+    <!--property MemoryPressureThresholdUSec is not documented!-->
+
     <!--property EnvironmentFiles is not documented!-->
 
     <!--property PassEnvironment is not documented!-->
@@ -7638,6 +7682,10 @@ node /org/freedesktop/systemd1/unit/home_2emount {
 
     <variablelist class="dbus-property" generated="True" extra-ref="RestrictNetworkInterfaces"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureWatch"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureThresholdUSec"/>
+
     <variablelist class="dbus-property" generated="True" extra-ref="Environment"/>
 
     <variablelist class="dbus-property" generated="True" extra-ref="EnvironmentFiles"/>
@@ -8406,6 +8454,10 @@ node /org/freedesktop/systemd1/unit/dev_2dsda3_2eswap {
       readonly a(iiqq) SocketBindDeny = [...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly (bas) RestrictNetworkInterfaces = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s MemoryPressureWatch = '...';
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t MemoryPressureThresholdUSec = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
       readonly as Environment = ['...', ...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
@@ -8932,6 +8984,10 @@ node /org/freedesktop/systemd1/unit/dev_2dsda3_2eswap {
 
     <!--property RestrictNetworkInterfaces is not documented!-->
 
+    <!--property MemoryPressureWatch is not documented!-->
+
+    <!--property MemoryPressureThresholdUSec is not documented!-->
+
     <!--property EnvironmentFiles is not documented!-->
 
     <!--property PassEnvironment is not documented!-->
@@ -9426,6 +9482,10 @@ node /org/freedesktop/systemd1/unit/dev_2dsda3_2eswap {
 
     <variablelist class="dbus-property" generated="True" extra-ref="RestrictNetworkInterfaces"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureWatch"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureThresholdUSec"/>
+
     <variablelist class="dbus-property" generated="True" extra-ref="Environment"/>
 
     <variablelist class="dbus-property" generated="True" extra-ref="EnvironmentFiles"/>
@@ -10053,6 +10113,10 @@ node /org/freedesktop/systemd1/unit/system_2eslice {
       readonly a(iiqq) SocketBindDeny = [...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly (bas) RestrictNetworkInterfaces = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s MemoryPressureWatch = '...';
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t MemoryPressureThresholdUSec = ...;
   };
   interface org.freedesktop.DBus.Peer { ... };
   interface org.freedesktop.DBus.Introspectable { ... };
@@ -10219,6 +10283,10 @@ node /org/freedesktop/systemd1/unit/system_2eslice {
 
     <!--property RestrictNetworkInterfaces is not documented!-->
 
+    <!--property MemoryPressureWatch is not documented!-->
+
+    <!--property MemoryPressureThresholdUSec is not documented!-->
+
     <!--Autogenerated cross-references for systemd.directives, do not edit-->
 
     <variablelist class="dbus-interface" generated="True" extra-ref="org.freedesktop.systemd1.Unit"/>
@@ -10391,6 +10459,10 @@ node /org/freedesktop/systemd1/unit/system_2eslice {
 
     <variablelist class="dbus-property" generated="True" extra-ref="RestrictNetworkInterfaces"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureWatch"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureThresholdUSec"/>
+
     <!--End of Autogenerated section-->
 
     <refsect2>
@@ -10586,6 +10658,10 @@ node /org/freedesktop/systemd1/unit/session_2d1_2escope {
       readonly a(iiqq) SocketBindDeny = [...];
       @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
       readonly (bas) RestrictNetworkInterfaces = ...;
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly s MemoryPressureWatch = '...';
+      @org.freedesktop.DBus.Property.EmitsChangedSignal("false")
+      readonly t MemoryPressureThresholdUSec = ...;
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
       readonly s KillMode = '...';
       @org.freedesktop.DBus.Property.EmitsChangedSignal("const")
@@ -10772,6 +10848,10 @@ node /org/freedesktop/systemd1/unit/session_2d1_2escope {
 
     <!--property RestrictNetworkInterfaces is not documented!-->
 
+    <!--property MemoryPressureWatch is not documented!-->
+
+    <!--property MemoryPressureThresholdUSec is not documented!-->
+
     <!--property KillMode is not documented!-->
 
     <!--property KillSignal is not documented!-->
@@ -10974,6 +11054,10 @@ node /org/freedesktop/systemd1/unit/session_2d1_2escope {
 
     <variablelist class="dbus-property" generated="True" extra-ref="RestrictNetworkInterfaces"/>
 
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureWatch"/>
+
+    <variablelist class="dbus-property" generated="True" extra-ref="MemoryPressureThresholdUSec"/>
+
     <variablelist class="dbus-property" generated="True" extra-ref="KillMode"/>
 
     <variablelist class="dbus-property" generated="True" extra-ref="KillSignal"/>
diff --git a/man/systemd-system.conf.xml b/man/systemd-system.conf.xml
index 82a52e2150..71d403db8d 100644
--- a/man/systemd-system.conf.xml
+++ b/man/systemd-system.conf.xml
@@ -556,6 +556,18 @@
         to configure the rate limit window, and <varname>ReloadLimitBurst=</varname> takes a positive integer to
         configure the maximum allowed number of reloads within the configured time window.</para></listitem>
       </varlistentry>
+
+      <varlistentry>
+        <term><varname>DefaultMemoryPressureWatch=</varname></term>
+        <term><varname>DefaultMemoryPressureThresholdSec=</varname></term>
+
+        <listitem><para>Configures the default settings for the per-unit
+        <varname>MemoryPressureWatch=</varname> and <varname>MemoryPressureThresholdSec=</varname>
+        settings. See
+        <citerefentry><refentrytitle>systemd.resource-control</refentrytitle><manvolnum>5</manvolnum></citerefentry>
+        for details. Defaults to <literal>auto</literal> and <literal>100ms</literal>, respectively. This
+        also sets the memory pressure monitoring threshold for the service manager itself.</para></listitem>
+      </varlistentry>
     </variablelist>
   </refsect1>
 
diff --git a/man/systemd.exec.xml b/man/systemd.exec.xml
index e696941682..795e2f0671 100644
--- a/man/systemd.exec.xml
+++ b/man/systemd.exec.xml
@@ -3779,6 +3779,16 @@ StandardInputData=V2XigLJyZSBubyBzdHJhbmdlcnMgdG8gbG92ZQpZb3Uga25vdyB0aGUgcnVsZX
           </para></listitem>
         </varlistentry>
 
+        <varlistentry>
+          <term><varname>$MEMORY_PRESSURE_WATCH</varname></term>
+          <term><varname>$MEMORY_PRESSURE_WRITE</varname></term>
+
+          <listitem><para>If memory pressure monitoring is enabled for this service unit, the path to watch
+          and the data to write into it. See <ulink url="https://systemd.io/MEMORY_PRESSURE">Memory Pressure
+          Handling</ulink> for details about these variables and the service protocol data they
+          convey.</para></listitem>
+        </varlistentry>
+
       </variablelist>
 
       <para>For system services, when <varname>PAMName=</varname> is enabled and <command>pam_systemd</command> is part
diff --git a/man/systemd.resource-control.xml b/man/systemd.resource-control.xml
index 27e29e853a..f057433973 100644
--- a/man/systemd.resource-control.xml
+++ b/man/systemd.resource-control.xml
@@ -1169,6 +1169,53 @@ DeviceAllow=/dev/loop-control
           </para>
         </listitem>
       </varlistentry>
+
+      <varlistentry>
+        <term><varname>MemoryPressureWatch=</varname></term>
+
+        <listitem><para>Controls memory pressure monitoring for invoked processes. Takes one of
+        <literal>off</literal>, <literal>on</literal>, <literal>auto</literal> or <literal>skip</literal>. If
+        <literal>off</literal> tells the service not to watch for memory pressure events, by setting the
+        <varname>$MEMORY_PRESSURE_WATCH</varname> environment variable to the literal string
+        <filename>/dev/null</filename>. If <literal>on</literal> tells the service to watch for memory
+        pressure events. This enables memory accounting for the service, and ensures the
+        <filename>memory.pressure</filename> cgroup attribute files is accessible for read and write to the
+        service's user. It then sets the <varname>$MEMORY_PRESSURE_WATCH</varname> environment variable for
+        processes invoked by the unit to the file system path to this file. The threshold information
+        configured with <varname>MemoryPressureThresholdSec=</varname> is encoded in the
+        <varname>$MEMORY_PRESSURE_WRITE</varname> environment variable. If the <literal>auto</literal> value
+        is set the protocol is enabled if memory accounting is anyway enabled for the unit, and disabled
+        otherwise. If set to <literal>skip</literal> the logic is neither enabled, nor disabled and the two
+        environment variables are not set.</para>
+
+        <para>Note that services are free to use the two environment variables, but it's unproblematic if
+        they ignore them. Memory pressure handling must be implemented individually in each service, and
+        usually means different things for different software. For further details on memory pressure
+        handling see <ulink url="https://systemd.io/MEMORY_PRESSURE">Memory Pressure Handling in
+        systemd</ulink>.</para>
+
+        <para>Services implemented using
+        <citerefentry><refentrytitle>sd-event</refentrytitle><manvolnum>3</manvolnum></citerefentry> may use
+        <citerefentry><refentrytitle>sd_event_add_memory_pressure</refentrytitle><manvolnum>3</manvolnum></citerefentry>
+        to watch for and handle memory pressure events.</para>
+
+        <para>If not explicit set, defaults to the <varname>DefaultMemoryPressureWatch=</varname> setting in
+        <citerefentry><refentrytitle>systemd-system.conf</refentrytitle><manvolnum>5</manvolnum></citerefentry>.</para></listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><varname>MemoryPressureThresholdSec=</varname></term>
+
+        <listitem><para>Sets the memory pressure threshold time for memory pressure monitor as configured via
+        <varname>MemoryPressureWatch=</varname>. Specifies the maximum allocation latency before a memory
+        pressure event is signalled to the service, per 1s window. If not specified defaults to the
+        <varname>DefaultMemoryPressureThresholdSec=</varname> setting in
+        <citerefentry><refentrytitle>systemd-system.conf</refentrytitle><manvolnum>5</manvolnum></citerefentry>
+        (which in turn defaults to 100ms). The specified value expects a time unit such as
+        <literal>ms</literal> or <literal>µs</literal>, see
+        <citerefentry><refentrytitle>systemd.time</refentrytitle><manvolnum>7</manvolnum></citerefentry> for
+        details on the permitted syntax.</para></listitem>
+      </varlistentry>
     </variablelist>
   </refsect1>