On 12/01/2017 06:02 PM, Kirill Tkhai wrote:
> When there are more than 2 users of a page, __tcache_page_tree_delete()
> fails to freeze it. We skip it and never try to freeze it again.
>
> In this case the page remains not invalidated, and tcache_node->nr_pages
> never decremented. Later, we
When there are more than 2 users of a page, __tcache_page_tree_delete()
fails to freeze it. We skip it and never try to freeze it again.
In this case the page remains not invalidated, and tcache_node->nr_pages
never decremented. Later, we catch WARN_ON() reporting about this.
From: Trond Myklebust
While COMMIT has the potential to free up a lot of memory that is being
taken by unstable writes, it isn't guaranteed to free up this particular
page. Also, calling fsync() on the server is expensive and so we want to
do it in a more
Checking for empty cgroup is not correct, because init process leaves cgroup
early in do_exit.
This leads to a situation, when container is treated as stopped but its
resources (VEIP for instance) are not yet released.
Which in turn leads to container restart failure due to non-releases VEIP