On 01/14/2014 03:05 AM, Andrew Morton wrote:
> On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov
> wrote:
>
>> When reclaiming kmem, we currently don't scan slabs that have less than
>> batch_size objects (see shrink_slab_node()):
>>
>> while (total_scan >= batch_size) {
>>
On 01/14/2014 03:11 AM, Andrew Morton wrote:
> On Sat, 11 Jan 2014 16:36:33 +0400 Vladimir Davydov
> wrote:
>
>> When direct reclaim is executed by a process bound to a set of NUMA
>> nodes, we should scan only those nodes when possible, but currently we
>> will scan kmem from all online nodes ev
On 01/14/2014 03:13 AM, Andrew Morton wrote:
> On Sat, 11 Jan 2014 16:36:34 +0400 Vladimir Davydov
> wrote:
>
>> This reduces the indentation level of do_try_to_free_pages() and removes
>> extra loop over all eligible zones counting the number of on-LRU pages.
> So this should cause no functional
On Sat, 11 Jan 2014 16:36:34 +0400 Vladimir Davydov
wrote:
> This reduces the indentation level of do_try_to_free_pages() and removes
> extra loop over all eligible zones counting the number of on-LRU pages.
So this should cause no functional change, yes?
___
On Sat, 11 Jan 2014 16:36:33 +0400 Vladimir Davydov
wrote:
> When direct reclaim is executed by a process bound to a set of NUMA
> nodes, we should scan only those nodes when possible, but currently we
> will scan kmem from all online nodes even if the kmem shrinker is NUMA
> aware. That said, b
On Sat, 11 Jan 2014 16:36:31 +0400 Vladimir Davydov
wrote:
> When reclaiming kmem, we currently don't scan slabs that have less than
> batch_size objects (see shrink_slab_node()):
>
> while (total_scan >= batch_size) {
> shrinkctl->nr_to_scan = batch_size;
>
User namespaces was restricted in the mainstream kernel and
vzctl must follow to the current rules.
ps: I didn't test these patches on OpenVZ kernels.
Andrey Vagin (2):
vzctl: bind-mount the root in itself after entering in a user
namespace
hooks_ct: mount /proc and /sys before umounting
Here is workaround for the kernel commit:
commit e51db73532955dc5eaba4235e62b74b460709d5b
Author: Eric W. Biederman
Date: Sat Mar 30 19:57:41 2013 -0700
userns: Better restrictions on when proc and sysfs can be mounted
Rely on the fact that another flavor of the filesystem is already
Here is workaround for the kernel commit:
commit 5ff9d8a65ce80efb509ce4e8051394e9ed2cd942
Author: Eric W. Biederman
Date: Fri Mar 29 21:04:39 2013 -0700
vfs: Lock in place mounts from more privileged users
When creating a less privileged mount namespace or propogating mounts
from a