. For example:
a small number of deadline tasks which have common rt_spinlocks
with fair tasks. Priority inheritance mechanism does this every
time it is acquiring a lock.
[This is confirmed by Juri Lelli and LKML was CC'ed, but
unfotunately I can't find direct link on lkml.org]
Signed-off-by: Kirill
can't find direct link on lkml.org]
Signed-off-by: Kirill Tkhai ktk...@parallels.com
CC: Juri Lelli juri.le...@gmail.com
CC: Peter Zijlstra pet...@infradead.org
CC: Ingo Molnar mi...@kernel.org
---
kernel/sched/deadline.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel
is permittions line
example:
0 xxx;1 balloon_ino=12,pfcache_csum,pfcache=/vz/pfcache;2 barrier=1
Here, xxx is st_rdev of device, '1' starts comma-separated list of
hidden options, and '2' is allowed ones.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/linux/ve.h | 11
kernel/ve/ve.c
').
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
fs/namespace.c | 136
fs/super.c | 17 ++-
include/linux/fs.h |2 +
3 files changed, 153 insertions(+), 2 deletions(-)
diff --git a/fs/namespace.c b/fs/namespace.c
index
, this was need for versions = PCS5.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/linux/sched.h |2 --
include/linux/ve.h |2 --
kernel/exit.c | 15 ---
kernel/pid_namespace.c |2 --
kernel/ve/ve.c | 38 --
5
Hi, Maxim,
В Ср, 06/05/2015 в 15:05 -0700, Maxim Patlasov пишет:
Kirill, see please a couple of inline comments below...
On 04/29/2015 01:29 AM, Kirill Tkhai wrote:
1)Porting patch ve: mount option list by Maxim Patlasov:
The patch adds new fields to ve_struct: devmnt_list
/PSBM-33239
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
drivers/base/core.c |6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 98e8e3b..6583bec 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1840,12 +1840,14
').
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
fs/namespace.c | 136
fs/super.c | 17 ++-
include/linux/fs.h |2 +
3 files changed, 153 insertions(+), 2 deletions(-)
diff --git a/fs/namespace.c b/fs/namespace.c
index
/show_bug.cgi?id=2940
Signed-off-by: Vasily Averin v...@openvz.org
Acked-by: Kirill Tkhai ktk...@odin.com
___
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
-32273
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/ve/ve.c | 55 +++
1 file changed, 55 insertions(+)
diff --git a/kernel/ve/ve.c b/kernel/ve/ve.c
index 6ab409f..e598d15 100644
--- a/kernel/ve/ve.c
+++ b/kernel/ve/ve.c
@@ -1032,6
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
scripts/basic/fixdep | Bin
scripts/kconfig/conf | Bin
2 files changed, 0 insertions(+), 0 deletions(-)
delete mode 100755 scripts/basic/fixdep
delete mode 100755 scripts/kconfig/conf
diff --git a/scripts/basic/fixdep b/scripts/basic/fixdep
)) {
retry = 1;
bh_unlock_sock(sk);
sock_put(sk);
goto enable_bh;
On 19.05.2015 17:43, Kirill Tkhai wrote:
Double loop is here, break works is not as expected
Double loop is here, break works is not as expected.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/ipv4/tcp_ipv4.c |3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 532edea..0e990c2 100644
--- a/net/ipv4/tcp_ipv4.c
Konstantin, this is the first part containing 2/3 of patches from the BUG:
https://jira.sw.ru/browse/PSBM-33645
---
Kirill Tkhai (14):
netpoll: don't free skb from completion_queue in interrupt context
netfilter: Add {ipt,ip6t}_osf aliases for xt_osf
net: Port diff-ve-net
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/core/netpoll.c |6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 99091a2..18eeb81 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -291,8 +291,12 @@ static void
, but the master_dev is accesses
without locks, so here is a race.
This patch allows safely assess to master_dev in rcu context.
https://jira.sw.ru/browse/PSBM-24056
Signed-off-by: Andrey Vagin ava...@openvz.org
Acked-by: Stanislav Kinsbursky skinsbur...@parallels.com
Signed-off-by: Kirill Tkhai ktk
://jira.sw.ru/browse/PSBM-23514
Signed-off-by: Andrey Vagin ava...@openvz.org
Acked-by: Cyrill Gorcunov gorcu...@openvz.org
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/netlink/af_netlink.c |4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/netlink/af_netlink.c b
@khorenko:
We never differed ipv4 and ipv6 in the iptables mask =
let's put the ipv6 bits into kernel default mask.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/uapi/linux/vziptable_defs.h |3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux
Porting mainstream commit b8ddd9eac8788b0aa9a9d4e09d76dc9e1667bb2c:
Orig author: Kirill Tkhai ktk...@parallels.com
netfilter: Add {ipt,ip6t}_osf aliases for xt_osf
There are no these aliases, so kernel can not request appropriate
match table:
$ iptables -I INPUT -p tcp -m
, but it's only suggestion. So I leave it up to Konstantin
if he knows why we did that.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/packet/af_packet.c |8 ++--
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index
...@parallels.com
CC: Andrey Vagin ava...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/netfilter/xt_mark.c | 18 --
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c
index db7fbfc..09ef00f 100644
/PSBM-31451
Signed-off-by: Cyrill Gorcunov gorcu...@parallels.com
Acked-by: Vladimir Davydov vdavy...@parallels.com
CC: Andrey Vagin ava...@parallels.com
CC: Kirill Tkhai ktk...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/linux/netfilter.h |6 +++---
include/linux/ve.h
-by: Vladimir Davydov vdavy...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
To Konstantin: we most likely need to convert old time, which is
returned to userspace, back in absolute. This is need for 2.6.32
and 3.10 both. Please, create a jira task to do not forget.
---
fs/timerfd.c
a CT while it's not done.
https://jira.sw.ru/browse/PSBM-27792
https://bugzilla.openvz.org/show_bug.cgi?id=2644
Signed-off-by: Kirill Tkhai ktk...@parallels.com
---
net/netfilter/nfnetlink.c |4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nfnetlink.c b/net
Port patch diff-ve-net-ip_gre-containerize-per-net-devices from 2.6.32:
This patch adds IP GRE devices support in a container.
Done in the scope of
https://jira.sw.ru/browse/PSBM-24331
Signed-off-by: Stanislav Kinsbursky skinsbur...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
is changed from
NF_CONNTRACK_IPV4 to NF_DEFRAG_IPV4
Signed-off-by: Vasily Averin v...@openvz.org
Signed-off-by: Pablo Neira Ayuso pa...@netfilter.org
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/bridge/br_netfilter.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net
-by: Andrey Vagin ava...@openvz.org
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
drivers/net/venetdev.c |1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/venetdev.c b/drivers/net/venetdev.c
index 6b7d8fc7..faeed33 100644
--- a/drivers/net/venetdev.c
+++ b/drivers/net/venetdev.c
,
if VE_IP_IPTABLES is not allowed.
https://jira.sw.ru/browse/PSBM-27181
Signed-off-by: Kirill Tkhai ktk...@parallels.com
---
net/ipv4/netfilter/iptable_raw.c | 11 +++
1 file changed, 11 insertions(+)
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 44b8fc1
В Пн, 08/06/2015 в 19:07 +0300, Andrew Vagin пишет:
On Mon, Jun 08, 2015 at 05:22:25PM +0300, Kirill Tkhai wrote:
Port diff-ve-netfilter-ipset-prohibit-ipset-from-the-inside-CT from 2.6.32:
Currently a CT owner can configure ipset rules which are not virtualized =
affect the whole
Porting mainstream commit b8ddd9eac8788b0aa9a9d4e09d76dc9e1667bb2c:
Orig author: Kirill Tkhai ktk...@parallels.com
netfilter: Add {ipt,ip6t}_osf aliases for xt_osf
There are no these aliases, so kernel can not request appropriate
match table:
$ iptables -I INPUT -p tcp -m
В Вт, 09/06/2015 в 14:57 +0300, Andrew Vagin пишет:
On Mon, Jun 08, 2015 at 05:20:39PM +0300, Kirill Tkhai wrote:
Porting patches diff-ve-net-bridge-dont-set-NULL-in-skb-dev
and diff-ve-net-bridge-dont-forget-to-init-master_dev from 2.6.32:
skb-dev can't be NULL, because it is accessed
-- the @tb array allocated
on the stack and (!) nlmsg_parse is not tested for error code thus
it might leave unitialized if nlmsg_parse exit early (I already
hit #GP once). So fix this problem at once.
Signed-off-by: Cyrill Gorcunov gorcu...@openvz.org
Acked-by: Kirill Tkhai ktk
Khorenko,
Virtuozzo Linux Kernel Team
On 06/08/2015 05:20 PM, Kirill Tkhai wrote:
Porting patch
diff-netpoll-dont-free-skb-from-completion_queue-in-interrupt-context
from 2.6.32:
skb is queued to completion_queue from dev_kfree_skb_irq,
because skb can't be freed in irq context
Khorenko,
Virtuozzo Linux Kernel Team
On 06/08/2015 05:20 PM, Kirill Tkhai wrote:
Porting patches diff-ve-net-bridge-dont-set-NULL-in-skb-dev
and diff-ve-net-bridge-dont-forget-to-init-master_dev from 2.6.32:
skb-dev can't be NULL, because it is accessed from netfilters
without testing
В Чт, 04/06/2015 в 16:44 +0300, Andrew Vagin пишет:
On Thu, Jun 04, 2015 at 02:29:50PM +0300, Kirill Tkhai wrote:
Hi, Andrew,
please, see the comment below
В Чт, 28/05/2015 в 15:06 +0400, Andrew Vagin пишет:
Only if the NETIF_F_VENET flag is set.
A containers doesn't get
in pernet init]
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/ve/veowner.c | 23 ---
net/ipv4/route.c|9 +
2 files changed, 9 insertions(+), 23 deletions(-)
diff --git a/kernel/ve/veowner.c b/kernel/ve/veowner.c
index ada4df3..316e4d0 100644
These are unused (even in 2.6.32) leftovers from
earlier versions.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/net/netns/ipv6.h |2 --
1 file changed, 2 deletions(-)
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 9defaf6..005e2c2 100644
--- a/include/net
/browse/PSBM-34437
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
lib/kmapset.c|5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/lib/kmapset.c b/lib/kmapset.c
index b809e69..a8b79ae 100644
--- a/lib/kmapset.c
+++ b/lib/kmapset.c
@@ -245,7 +245,7 @@ int
[8160edec] ret_from_fork+0x7c/0xb0
[8108a2a0] ? create_kthread+0x60/0x60
In fact, it's my fault: I didn't notice all of these at a quick glance
at this patch and let it trickle through.
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Reviewed-by: Kirill Tkhai ktk...@odin.com
-by: Kirill Tkhai ktk...@odin.com
---
fs/block_dev.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 15bd3ae..34949b0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1075,8 +1075,16 @@ static int __blkdev_get(struct
Please, drop this, I'll write another commentary.
В Чт, 25/06/2015 в 17:52 +0300, Kirill Tkhai пишет:
We doesn't want to allow a CT full write access over a bdev,
so that vzctl usually prohibits it.
But we want to permit a mounting in RW mode inside container.
https://jira.sw.ru/browse
Port commit 31ff6aa5c86f7564f0dd97c5b3e1404cad238d00 from mainstream.
Using whole of allocated pages reduces requested skb-data size.
This is just a little more thriftily allocation.
netperf does not show difference with the current performance.
Signed-off-by: Kirill Tkhai ktk...@parallels.com
-off-by: David S. Miller da...@davemloft.net
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/net/af_unix.h |1 +
net/unix/af_unix.c| 65 +++--
2 files changed, 31 insertions(+), 35 deletions(-)
diff --git a/include/net/af_unix.h b/include
-by: Kirill Tkhai ktk...@odin.com
---
include/net/sock.h |3 +
net/core/sock.c| 99
net/packet/af_packet.c |2 -
net/unix/af_unix.c |6 ++-
4 files changed, 57 insertions(+), 53 deletions(-)
diff --git a/include/net
New vzctl works with UUID, not ID. We should show it.
Alignment 36 is default UUID lenght.
https://jira.sw.ru/browse/PSBM-34317
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/ve/vecalls.c |4 ++--
security/device_cgroup.c |4 ++--
2 files changed, 4 insertions(+), 4
В Пт, 19/06/2015 в 14:39 +0300, Kirill Tkhai пишет:
В Пт, 19/06/2015 в 14:26 +0300, Vladimir Davydov пишет:
On Fri, Jun 19, 2015 at 02:19:38PM +0300, Kirill Tkhai wrote:
В Пт, 19/06/2015 в 14:15 +0300, Vladimir Davydov пишет:
On Fri, Jun 19, 2015 at 02:07:32PM +0300, Kirill Tkhai wrote
, CRIU should set appropriate jiffies_fixup
on restore.
Also, we may think about submitting this patch to
mainstream.
From patch diff-ve-network-combined-10-rh494-2 of
https://jira.sw.ru/browse/PSBM-33645
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include/linux/ve.h
В Чт, 18/06/2015 в 21:26 +0300, Cyrill Gorcunov пишет:
On Tue, Jun 16, 2015 at 07:51:52PM +0300, Cyrill Gorcunov wrote:
If we have any problems because of this, the solution is good.
OK. Gimme sometime (util tomorrow probably) to think of. This issue
not critical at the moment
https://jira.sw.ru/browse/PSBM-34497
В Пт, 26/06/2015 в 20:02 +0300, Kirill Tkhai пишет:
In PCS7 we use UUID instead of ctid for cgroup directories names,
so we should open it.
Below is small test program to check the patch works:
#include linux/vzcalluser.h
#include stdio.h
#include
limit-vs-RESOURCE_MAX comparisons use
greater-or-equal sign.
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Reviewed-by: Kirill Tkhai ktk...@odin.com
---
mm/memcontrol.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
;
}
if (ioctl(fd, VZCTL_SETDEVPERMS, s))
printf(ioctl\n);
}
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/ve/vecalls.c |9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/kernel/ve/vecalls.c b/kernel/ve/vecalls.c
index e262c5e..be4fb1e
It's better to avoid get_exec_env() in a place, where we easily can
do that.
get_exec_env() used to be used in the places, where caller did
set_exec_env() before the call. Delete it to make it do not confuse
us like it would be an unported place from 2.6.32.
Signed-off-by: Kirill Tkhai ktk
with its cgroup on cgroup_post_fork.
This patch does the trick. It is safe to change exec_ub there, because
the task is not allowed to run yet and therefore cannot get/set its
exec_ub.
Reported-by: Kirill Tkhai ktk...@odin.com
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Reviewed
В Вт, 16/06/2015 в 19:07 +0300, Cyrill Gorcunov пишет:
On Tue, Jun 16, 2015 at 06:19:44PM +0300, Kirill Tkhai wrote:
This patch brings a couple of problems. The first one is if we're setting
a ve cgroup for a forking task, it's possible the parent and the child
fall into different
В Чт, 14/05/2015 в 19:52 +0300, Cyrill Gorcunov пишет:
In vzctl/libvzctl bundle we restore container like
- create ve/$ctid cgroup
- move self into this cgroup
- run criu from inside
So that kernel code passes ve_can_attach test. In turn for
our P.Haul project (which is managing live
В Вт, 16/06/2015 в 19:36 +0300, Cyrill Gorcunov пишет:
On Tue, Jun 16, 2015 at 07:25:48PM +0300, Kirill Tkhai wrote:
May not we simply add into ve cgroup?
.can_attach
...
spin_lock(task-sighand-siglock);
.cance_attach
...
spin_unlock(task-sighand-siglock
, SIOCSHWTSTAMP inside a CT.
https://jira.sw.ru/browse/PSBM-29808
Signed-off-by: Pavel Tikhomirov ptikhomi...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/bridge/br_ioctl.c | 33 ++---
net/core/dev_ioctl.c |8
2 files changed, 26 insertions
://jira.sw.ru/browse/PSBM-31819
https://jira.sw.ru/browse/PSBM-29808
Signed-off-by: Pavel Tikhomirov ptikhomi...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/core/dev_ioctl.c |5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/core/dev_ioctl.c b/net/core
We can't use the same bit in _iptables_modules for different
modules. This leads to a memory leak, because it's cleared
after pernet exit method, so only one pernet exit is executed.
Found in the process of fixing: https://jira.sw.ru/browse/PSBM-34192.
Signed-off-by: Kirill Tkhai ktk...@odin.com
-by: Kirill Tkhai ktk...@odin.com
---
drivers/net/tun.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9c57c11..614dabb 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1437,7 +1437,6 @@ static void tun_setup
В Ср, 10/06/2015 в 17:37 +0300, Konstantin Khorenko пишет:
On 06/10/2015 11:42 AM, Kirill Tkhai wrote:
В Ср, 10/06/2015 в 11:35 +0300, Konstantin Khorenko пишет:
JFYI: this patch is related to via_phys_dev feature,
we've dropped it = no need for this patch.
When you did that? My git
) in tcp_v4_kill_ve_sockets(), i.e.
#define bh_lock_sock(__sk) spin_lock(((__sk)-sk_lock.slock))
we are trying to manipulate with tw_timeout, which is not zero, and can't
acquire the spinlock.
On Fri, May 29, 2015 at 04:53:39PM +0300, Kirill Tkhai wrote:
This is a leftover from earlier versions
В Пн, 01/06/2015 в 15:16 +0300, Vasily Averin пишет:
On 01.06.2015 14:31, Kirill Tkhai wrote:
В Пт, 29/05/2015 в 17:20 +0300, Andrew Vagin пишет:
Acked-by: Andrew Vagin ava...@odin.com
I'm agree that we need to remove this function, but I don't know how it
fixes the bug
В Пн, 01/06/2015 в 17:25 +0300, Vasily Averin пишет:
On 01.06.2015 15:46, Kirill Tkhai wrote:
В Пн, 01/06/2015 в 15:16 +0300, Vasily Averin пишет:
On 01.06.2015 14:31, Kirill Tkhai wrote:
В Пт, 29/05/2015 в 17:20 +0300, Andrew Vagin пишет:
Acked-by: Andrew Vagin ava...@odin.com
I'm
have the same issues with struct net, because nobody
waits for it.
PCS6 also needs the same patch.
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/ipv4/inet_timewait_sock.c |4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4
that is allow the userspace assign a memory cgroup to a ve or
beancounter cgroup and get the memory cgroup of a container from
get_exec_env() or get_exec_ub().
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Reviewed-by: Kirill Tkhai ktk...@odin.com
---
include/linux/memcontrol.h |6
the running container or they
were modified after and don't really apply to the running
instance.
Thus when user space tools modify these members make sure
the container is offline.
Reported-by: Kirill Tkhai ktk...@odin.com
Signed-off-by: Cyrill Gorcunov gorcu...@odin.com
CC: Vladimir Davydov
-by: Kirill Tkhai ktk...@odin.com
---
include/bc/beancounter.h |3 +--
kernel/bc/beancounter.c | 20 +++-
kernel/bc/sys.c |2 +-
3 files changed, 9 insertions(+), 16 deletions(-)
diff --git a/include/bc/beancounter.h b/include/bc/beancounter.h
index
В Ср, 20/05/2015 в 15:09 +0300, Vladimir Davydov пишет:
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Reviewed-by: Kirill Tkhai ktk...@odin.com
---
kernel/bc/beancounter.c | 52
+++
1 file changed, 12 insertions(+), 40 deletions
В Чт, 21/05/2015 в 12:50 +0300, Vladimir Davydov пишет:
OOM guarantee works exactly like low limit, but for OOM, i.e. tasks
inside cgroups above the limit are killed first.
Read/write via memory.oom_guarantee.
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Reviewed-by: Kirill
.
https://jira.sw.ru/browse/PSBM-31246
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Acked-by: Andrew Vagin ava...@parallels.com
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/core/net_namespace.c |6 ++
1 file changed, 6 insertions(+)
diff --git a/net/core/net_namespace.c
-by: Kirill Tkhai ktk...@odin.com
kernel/bc/beancounter.c |4 +--
mm/memcontrol.c | 77
---
2 files changed, 61 insertions(+), 20 deletions(-)
___
Devel mailing list
Devel@openvz.org
https
В Пн, 25/05/2015 в 17:05 +0300, Vladimir Davydov пишет:
This is neater than checking if the root is passed to the write method
and this is how it works upstream (for memory.low).
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
---
mm/memcontrol.c | 8 ++--
1 file changed, 2
В Вт, 26/05/2015 в 13:47 +0300, Vladimir Davydov пишет:
On Tue, May 26, 2015 at 01:36:35PM +0300, Kirill Tkhai wrote:
В Пн, 25/05/2015 в 17:05 +0300, Vladimir Davydov пишет:
@@ -5222,9 +5219,6 @@ static int mem_cgroup_oom_guarantee_write(struct
cgroup *cont,
I can't find
nf_tables is a new netfilter table. Add autoload permittions
like we have for {ip,ip6,x}tables.
https://jira.sw.ru/browse/PSBM-33631
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/kmod.c | 47 +++
1 file changed, 47 insertions(+)
diff --git
Cyrill, please, review the series.
В Вт, 26/05/2015 в 14:09 +0300, Kirill Tkhai пишет:
Here are the modules, which need extended permittions
(see module_payload_allowed() for details).
https://jira.sw.ru/browse/PSBM-33631
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/kmod.c
Here are the modules, which need extended permittions
(see module_payload_allowed() for details).
https://jira.sw.ru/browse/PSBM-33631
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/kmod.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/kernel/kmod.c b/kernel/kmod.c
On 20.08.2015 19:45, Vladimir Davydov wrote:
On Thu, Aug 20, 2015 at 07:10:07PM +0300, Kirill Tkhai wrote:
The scheduller code is written with the assumption, that rq-curr task can't
be already put. For example, in sched_move_task() we check for
running = task_current(rq, tsk
. And this simply looks wrong in any case.
Signed-off-by: Oleg Nesterov o...@redhat.com
Signed-off-by: Peter Zijlstra (Intel) pet...@infradead.org
Cc: Steven Rostedt rost...@goodmis.org
Cc: Kirill Tkhai tk...@yandex.ru
Cc: Linus Torvalds torva...@linux-foundation.org
Link: http://lkml.kernel.org/r
has
already been put, so concurrent cpu_cgroup_attach_task()-sched_move_task()
puts it one more time.
https://jira.sw.ru/browse/PSBM-35082
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/sched/core.c |8
kernel/sched/fair.c | 34 +++---
kernel
On 20.08.2015 15:59, Vladimir Davydov wrote:
On Thu, Aug 20, 2015 at 02:27:05PM +0300, Kirill Tkhai wrote:
...
+static void pre_schedule_fair(struct rq *rq, struct task_struct *prev)
+{
+trigger_cpulimit_balance(prev);
+}
+
You don't remove trigger_cpulimit_balance call from
-0 for ipv6 (AF_INET6)
https://jira.sw.ru/browse/PSBM-38573
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
Acked-by: Kirill Tkhai ktk...@odin.com
---
kernel/kmod.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/kmod.c b/kernel/kmod.c
index e0554f819b2d
. And this simply looks wrong in any case.
Signed-off-by: Oleg Nesterov o...@redhat.com
Signed-off-by: Peter Zijlstra (Intel) pet...@infradead.org
Cc: Steven Rostedt rost...@goodmis.org
Cc: Kirill Tkhai tk...@yandex.ru
Cc: Linus Torvalds torva...@linux-foundation.org
Link: http://lkml.kernel.org/r
has
already been put, so concurrent cpu_cgroup_attach_task()-sched_move_task()
puts it one more time.
https://jira.sw.ru/browse/PSBM-35082
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
kernel/sched/fair.c | 36 ++--
scripts/kconfig/conf | Bin
2 files changed
/1.925 ms
# tc class change dev eth0 classid 1:2 parent 1: htb rate 1mbit mpu 1000
# ping -f -c 1000 10.30.22.52
rtt min/avg/max/mdev = 15.352/22.229/38.646/2.212 ms, pipe 3, ipg/ewma
15.999/22.609 ms
https://jira.sw.ru/browse/PSBM-34874
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
include
)
Signed-off-by: Andrey Ryabinin aryabi...@odin.com
Acked-by: Kirill Tkhai ktk...@odin.com
Cc: Konstantin Khorenko khore...@virtuozzo.com
Cc: Kirill Tkhai ktk...@odin.com
---
kernel/kmod.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/kmod.c b/kernel/kmod.c
index
/browse/PSBM-35266
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/8021q/vlan_dev.c |3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 80fa918..09205c3 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -794,6
This is a missed hunk from diff-ve-net-netfilter-combined.
https://jira.sw.ru/browse/PSBM-35154
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/netfilter/nf_conntrack_core.c |3 +++
1 file changed, 3 insertions(+)
diff --git a/net/netfilter/nf_conntrack_core.c
b/net/netfilter
Register pernet table only if it's allowed.
https://jira.sw.ru/browse/PSBM-34748
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/ipv6/netfilter/ip6table_nat.c |8
1 file changed, 8 insertions(+)
diff --git a/net/ipv6/netfilter/ip6table_nat.c
b/net/ipv6/netfilter
В Пн, 13/07/2015 в 12:38 -0700, Maxim Patlasov пишет:
On 07/08/2015 04:50 AM, Kirill Tkhai wrote:
...
Why do we need to show hidden options to CT' user? He/she doesn't
see
.balloon file, so it doesn't seem consistent to show
balloon_ino=N.
But this way read won't show all
,
this
patch also makes tswap_frontswap_store use GFP_NOIO instead of
GFP_NOWAIT and issue radix tree preallocation before inserting a page
to
tswap_page_tree.
https://jira.sw.ru/browse/PSBM-34876
Signed-off-by: Vladimir Davydov vdavy...@parallels.com
For the whole series:
Reviewed-by: Kirill
https://jira.sw.ru/browse/PSBM-34875
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
net/ipv4/tcp_ipv4.c |6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4125556..aa64e15 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4
blkid needs /proc/partitions to populate /etc/blkid/blkid.tab.
If it's not populated, mount by UUID does not work.
https://jira.sw.ru/browse/PSBM-34805
Signed-off-by: Kirill Tkhai ktk...@odin.com
---
block/genhd.c | 13 +++--
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git
I reviewed it long ago. Forgot to CC mailing list:
Forwarded Message
Subject: Re: [Devel] [PATCH vz7 0/5] nf_conntrack: expose sysctls according to
rhel6
Date: Mon, 12 Oct 2015 12:31:59 +0300
From: Kirill Tkhai <ktk...@odin.com>
To: Stanislav Kinsburskiy <skinsbur...
On 28.10.2015 15:58, Vladimir Davydov wrote:
> On Wed, Oct 28, 2015 at 12:54:31PM +0300, Kirill Tkhai wrote:
>> On 27.10.2015 19:22, Vladimir Davydov wrote:
>>> On Fri, Oct 16, 2015 at 07:25:15PM +0300, Kirill Tkhai wrote:
>>>> wait_on_bit() prevents excess schedu
On 28.10.2015 17:37, Kirill Tkhai wrote:
> On 28.10.2015 15:58, Vladimir Davydov wrote:
>> On Wed, Oct 28, 2015 at 12:54:31PM +0300, Kirill Tkhai wrote:
>>> On 27.10.2015 19:22, Vladimir Davydov wrote:
>>>> On Fri, Oct 16, 2015 at 07:25:15PM +0300, Kirill
On 28.10.2015 15:40, Vladimir Davydov wrote:
> On Wed, Oct 28, 2015 at 12:53:44PM +0300, Kirill Tkhai wrote:
>> On 27.10.2015 19:13, Vladimir Davydov wrote:
>>> On Fri, Oct 16, 2015 at 07:24:49PM +0300, Kirill Tkhai wrote:
>>> ...
>>>> @@ -733,6 +742,13 @@
On 28.10.2015 15:51, Vladimir Davydov wrote:
> On Wed, Oct 28, 2015 at 12:54:10PM +0300, Kirill Tkhai wrote:
> ...
>>>> +static void ve_wait_work(struct callback_head *head)
>>>> +{
>>>> + atomic_t *nr = >task_ve_nr_works;
>>>> +
>>&
On 27.10.2015 19:20, Vladimir Davydov wrote:
> On Fri, Oct 16, 2015 at 07:25:00PM +0300, Kirill Tkhai wrote:
> ...
>> @@ -1565,6 +1565,10 @@ struct task_struct {
>> #ifdef CONFIG_VE
>> struct ve_struct *task_ve;
>> struct callback_he
On 27.10.2015 19:22, Vladimir Davydov wrote:
> On Fri, Oct 16, 2015 at 07:25:15PM +0300, Kirill Tkhai wrote:
>> wait_on_bit() prevents excess schedule_timeout() looping
>> (i.e. cpu time waisting and possible livelocks)
>
> I think a completion would suit th
1 - 100 of 1519 matches
Mail list logo