You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mesos.apache.org by gi...@apache.org on 2019/01/08 00:17:50 UTC
[mesos] branch 1.6.x updated: Sent SIGKILL to I/O switchboard
server as a safeguard.
This is an automated email from the ASF dual-hosted git repository.
gilbert pushed a commit to branch 1.6.x
in repository https://gitbox.apache.org/repos/asf/mesos.git
The following commit(s) were added to refs/heads/1.6.x by this push:
new a092c2c Sent SIGKILL to I/O switchboard server as a safeguard.
a092c2c is described below
commit a092c2c9e13914b248e07749c107ed65f088af79
Author: Qian Zhang <zh...@gmail.com>
AuthorDate: Mon Jan 7 16:16:12 2019 -0800
Sent SIGKILL to I/O switchboard server as a safeguard.
Review: https://reviews.apache.org/r/69667/
(cherry picked from commit 3478e344fb77d931f6122980c6e94cd3913c441d)
---
src/slave/containerizer/mesos/io/switchboard.cpp | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/src/slave/containerizer/mesos/io/switchboard.cpp b/src/slave/containerizer/mesos/io/switchboard.cpp
index d96a4de..ceb2140 100644
--- a/src/slave/containerizer/mesos/io/switchboard.cpp
+++ b/src/slave/containerizer/mesos/io/switchboard.cpp
@@ -819,6 +819,23 @@ Future<Nothing> IOSwitchboard::cleanup(
<< " is being destroyed";
os::kill(pid.get(), SIGTERM);
+
+ Clock::timer(Seconds(60), [pid, status, containerId]() {
+ if (status.isPending()) {
+ // If we are here, something really bad must have happened for I/O
+ // switchboard server to not exit after SIGTERM has been sent. We
+ // have seen this happen due to FD leak (see MESOS-9502). We do a
+ // SIGKILL here as a safeguard so that switchboard server forcefully
+ // exits and causes this cleanup feature to be completed, thus
+ // unblocking the container's cleanup.
+ LOG(ERROR) << "Sending SIGKILL to I/O switchboard server (pid: "
+ << pid.get() << ") for container " << containerId
+ << " since the I/O switchboard server did not terminate "
+ << "60 seconds after SIGTERM was sent to it";
+
+ os::kill(pid.get(), SIGKILL);
+ }
+ });
}
});
}