This is an automated email from the ASF dual-hosted git repository. gilbert pushed a commit to branch 1.5.x in repository https://gitbox.apache.org/repos/asf/mesos.git
commit 65a2059eb5c713d5b57e7b703418568e30dacc9b Author: Jie Yu <[email protected]> AuthorDate: Fri Aug 31 22:29:36 2018 -0700 Made overlay backend destroy more robust. Use MNT_DETACH for `unmount` so that if there are still processes holding files or directories in the rootfs (e.g., regular filesystem indexing), the unmount will still be successful. The kernel will cleanup the mount when the number of references reach zero. Also, do not return hard failure if `rmdir` failed. It's also possible that `rmdir` returns EBUSY. See more details in MESOS-9196. Review: https://reviews.apache.org/r/68594/ --- .../mesos/provisioner/backends/overlay.cpp | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/src/slave/containerizer/mesos/provisioner/backends/overlay.cpp b/src/slave/containerizer/mesos/provisioner/backends/overlay.cpp index 54d3e43..ba3de03 100644 --- a/src/slave/containerizer/mesos/provisioner/backends/overlay.cpp +++ b/src/slave/containerizer/mesos/provisioner/backends/overlay.cpp @@ -252,8 +252,11 @@ Future<bool> OverlayBackendProcess::destroy( foreach (const fs::MountInfoTable::Entry& entry, mountTable->entries) { if (entry.target == rootfs) { - // NOTE: This would fail if the rootfs is still in use. - Try<Nothing> unmount = fs::unmount(entry.target); + // NOTE: Use MNT_DETACH here so that if there are still + // processes holding files or directories in the rootfs, the + // unmount will still be successful. The kernel will cleanup the + // mount when the number of references reach zero. + Try<Nothing> unmount = fs::unmount(entry.target, MNT_DETACH); if (unmount.isError()) { return Failure( "Failed to destroy overlay-mounted rootfs '" + rootfs + "': " + @@ -262,9 +265,16 @@ Future<bool> OverlayBackendProcess::destroy( Try<Nothing> rmdir = os::rmdir(rootfs); if (rmdir.isError()) { - return Failure( - "Failed to remove rootfs mount point '" + rootfs + "': " + - rmdir.error()); + // NOTE: Due to the use of MNT_DETACH above, it's possible + // that `rmdir` will fail with EBUSY if some other mounts in + // other mount namespaces are still on this mount point on + // some old kernel (https://lwn.net/Articles/570338/). No need + // to return a hard failure here because the directory will be + // removed later and re-attempted on agent recovery. + // + // TODO(jieyu): Consider only ignore EBUSY error. + LOG(ERROR) << "Failed to remove rootfs mount point " + << "'" << rootfs << "': " << rmdir.error(); } // Clean up tempDir used for image layer links.
