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 00:16:42 UTC
[mesos] branch master 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 master
in repository https://gitbox.apache.org/repos/asf/mesos.git
The following commit(s) were added to refs/heads/master by this push:
new 3478e34 Sent SIGKILL to I/O switchboard server as a safeguard.
3478e34 is described below
commit 3478e344fb77d931f6122980c6e94cd3913c441d
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/
---
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 c445a8f..8e02e51 100644
--- a/src/slave/containerizer/mesos/io/switchboard.cpp
+++ b/src/slave/containerizer/mesos/io/switchboard.cpp
@@ -814,6 +814,23 @@ 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);
+ }
+ });
}
});
}