[Devel] [Q] migrating inotify assigned on ploop device

Hi guys, today I've been investigating a problem of container's migration with inotify assigned on /dev/ploop10308p1 device. The main problem is that the mark is set to devtmpfs where device ID and inode number is not persistent by default so to workaraound such problem we keep a real "path" to

Re: [Devel] ploop vs. BTRFS conflict resolved

On 01/10/2016 12:28 AM, Dmitry Monakhov wrote: Konstantin Khorenko writes: Maxim, Dima, are you ok with this rename? Ok. that's reasonable. +1 Alexey, thank you for the patch! i'll fix format issues like absence of Signed-off-by line, subject without $subsystem,

[Devel] [PATCH libvzctl] lib/env.c: setup_devtmpfs -- Don't miss tty12 device

Seems it has been lost while we were reworking tty layer code. https://jira.sw.ru/browse/PSBM-41628 Signed-off-by: Cyrill Gorcunov --- lib/env.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/env.c b/lib/env.c index 2bb8df8..aa60a10 100644 --- a/lib/env.c +++

[Devel] [PATCH RHEL7 COMMIT] ploop: rename extent maps management funtions

The commit is pushed to "branch-rh7-3.10.0-229.7.2.vz7.9.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git after rh7-3.10.0-229.7.2.vz7.9.20 --> commit e874b67c2d89b333633fb143cf92b35493623421 Author: Alexey V. Vissarionov Date: Mon Jan 11 18:13:03

[Devel] [PATCH RHEL7 COMMIT] ve/userns: allow unprivileged creation of the mount namespace.

The commit is pushed to "branch-rh7-3.10.0-327.3.1-vz7.10.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git after rh7-3.10.0-327.3.1.el7 --> commit 2bf35f0914403ef0666c4a40540ab4f58bb02adf Author: Andrey Ryabinin Date: Mon Jan 11 17:46:44 2016

[Devel] [PATCH 1/2] sched: introduce cond_resched_may_throttle

From: Kirill Tkhai Port diff-sched-introduce-cond_resched_may_throttle by Vladimir Davydov: Since cond_resched() is sometimes called under a semaphore, it was forbidden to throttle tasks there in order to eliminate the possibility of the priority inversion problem. However, it

[Devel] [PATCH 2/2] kvm: Allow scheduler throttling in __vcpu_run()

Since __vcpu_run() does not hold any mutexes, it's save to throttle there. Otherwise, the character of this place makes it behave as in-kernel busy loop: while () { cond_resched(); } and sys cpu usage takes up to 100% cpu. https://jira.sw.ru/browse/PSBM-42358 Signed-off-by: Kirill Tkhai

Re: [Devel] [PATCH 1/2] sched: introduce cond_resched_may_throttle

On Mon, Jan 11, 2016 at 08:15:35PM +0300, Kirill Tkhai wrote: > @@ -1246,6 +1246,7 @@ struct task_struct { > unsigned sched_interruptible_sleep:1; > > unsigned woken_while_running:1; > + unsigned may_throttle:1; [off-topic] There's a potential problem with these bitfields AFAIU