OpenVZ is an Operating System-level server virtualization solution, built on Linux. OpenVZ creates isolated, secure virtual environments

Cedric Jeanneret | 1 Feb 2010 13:31

NFS stall problem

Hello,

we're currently using openvz (2.6.18-128.2.1.el5.028stab064.4) on debian lenny nodes, with debian
lenny or etch VE (kernel was alienized from latest openvz rpm).

We have an nfs server on a hardware node (so NOT in a VE) which shares some cartographic datas (means: LOT of
small files, aka tiles).

For now, we're mounting NFS shares in VE in this way :
nfs-server:/path/to/share on /path/to/mount/point type nfs (ro,nfsvers=3,rsize=32768,wsize=32768,hard,proto=tcp,timeo=600,retrans=2,sec=sys,addr=nfs-server)

Share is done as follow :
/path/to/share     IP(ro,all_squash,anongid=65534,sync,no_subtree_check)

Problem :
sometimes (well, about once a day, or each two days), nfs share seems to be stalled. That means :
- unable to access datas from VE
- unable to umount share in VE

The only thing we can do is a restart of the VE.
As far as I can see, the others VE having an nfs share on the same HN don't have any problem (well, for a while,
than it stalls too).

We don't have any logs in syslog nor kern.log, either on HN or in VEs.

NFS-SRV is in a VLAN, and distributes files accross up to 3 VLANS. firewall rules are correct...

Any idea ?

I've read on wiki that "it's better to mount nfs share on HN, then use a mount -o bind". We can't afford that, as

(Continue reading)

Rafael Ruiz | 1 Feb 2010 20:53

Picon

Re: NFS stall problem

Hello, NFSv3 is know to have stability issues on linux, so by default it 
uses NFSv2 wich is more stable but doesn't support files large than 2GB. 
As I can see you are using NFSv3. I would recommend you to Try using 
NFSv4, the link 
http://wiki.linux-nfs.org/wiki/index.php/General_troubleshooting_recommendations 
would help on setting this up.

This would help too 
http://www.citi.umich.edu/projects/nfsv4/OLS2001/tsld004.htm

I hope this help.

Best regards,

> Hello,
>
> we're currently using openvz (2.6.18-128.2.1.el5.028stab064.4) on debian lenny nodes, with debian
lenny or etch VE (kernel was alienized from latest openvz rpm).
>
> We have an nfs server on a hardware node (so NOT in a VE) which shares some cartographic datas (means: LOT of
small files, aka tiles).
>
> For now, we're mounting NFS shares in VE in this way :
> nfs-server:/path/to/share on /path/to/mount/point type nfs (ro,nfsvers=3,rsize=32768,wsize=32768,hard,proto=tcp,timeo=600,retrans=2,sec=sys,addr=nfs-server)
>
> Share is done as follow :
> /path/to/share     IP(ro,all_squash,anongid=65534,sync,no_subtree_check)
>
> Problem :
> sometimes (well, about once a day, or each two days), nfs share seems to be stalled. That means :

(Continue reading)

Gordan Bobic | 1 Feb 2010 23:35

Re: Re: NFS stall problem

NFSv2?! You are joking, right? NFSv3 has been stable for over a decade. 
Last time I saw NFSv2 in the wild was in the '90s.

If you said NFSv4 was unstable, that I might have been inclined to agree 
with.

Gordan

Rafael Ruiz wrote:
> Hello, NFSv3 is know to have stability issues on linux, so by default it 
> uses NFSv2 wich is more stable but doesn't support files large than 2GB. 
> As I can see you are using NFSv3. I would recommend you to Try using 
> NFSv4, the link 
> http://wiki.linux-nfs.org/wiki/index.php/General_troubleshooting_recommendations 
> would help on setting this up.
> 
> This would help too 
> http://www.citi.umich.edu/projects/nfsv4/OLS2001/tsld004.htm
> 
> I hope this help.
> 
> Best regards,
> 
>> Hello,
>>
>> we're currently using openvz (2.6.18-128.2.1.el5.028stab064.4) on 
>> debian lenny nodes, with debian lenny or etch VE (kernel was alienized 
>> from latest openvz rpm).
>>
>> We have an nfs server on a hardware node (so NOT in a VE) which shares

(Continue reading)

Cédric Jeanneret | 2 Feb 2010 07:35

Re: Re: NFS stall problem

Hello,

Hm, in fact lenny includes nfsv4. But we had same troubles with nfsv3
(they were even worth). I'll check the links and keep this thread
updated.

Thank you for your concern.

Best regards,

C.

On Mon, Feb 1, 2010 at 11:35 PM, Gordan Bobic <gordan@...> wrote:
> NFSv2?! You are joking, right? NFSv3 has been stable for over a decade. Last
> time I saw NFSv2 in the wild was in the '90s.
>
> If you said NFSv4 was unstable, that I might have been inclined to agree
> with.
>
> Gordan
>
> Rafael Ruiz wrote:
>>
>> Hello, NFSv3 is know to have stability issues on linux, so by default it
>> uses NFSv2 wich is more stable but doesn't support files large than 2GB. As
>> I can see you are using NFSv3. I would recommend you to Try using NFSv4, the
>> link
>> http://wiki.linux-nfs.org/wiki/index.php/General_troubleshooting_recommendations
>> would help on setting this up.
>>

(Continue reading)

Cliff Wells | 2 Feb 2010 22:28

BUG: scheduling while atomic

I'm running proxmox 1.4:

Linux proxmox1 2.6.24-9-pve #1 SMP PREEMPT Tue Nov 17 09:34:41 CET 2009 x86_64 GNU/Linux

I occasionally get these in syslog, sometimes they come in so fast the
machine becomes unresponsive and must be power cycled:

Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31143]: (root) CMD (/usr/share/vzctl/scripts/vpsreboot)
Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31146]: (root) CMD (/usr/share/vzctl/scripts/vpsnetclean)
Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: nginx/7242/0x00000003
Jan 30 13:35:03 proxmox1 kernel: Pid: 7242, comm: nginx Tainted:  G   M    2.6.24-9-pve #1
Jan 30 13:35:03 proxmox1 kernel:
Jan 30 13:35:03 proxmox1 kernel: Call Trace:
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7485>] thread_return+0x103/0x67e
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d8f4>] lock_timer_base+0x34/0x70
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024debd>] __mod_timer+0xbd/0xe0
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d38>] schedule_timeout+0x58/0xd0
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d5c0>] process_timeout+0x0/0x10
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d33>] schedule_timeout+0x53/0xd0
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8030876a>] sys_epoll_wait+0x49a/0x560
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8044c0a4>] compat_sys_getsockopt+0x74/0x1d0
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff802370f0>] default_wake_function+0x0/0x10
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8022aae2>] ia32_sysret+0x0/0xa
Jan 30 13:35:03 proxmox1 kernel:
Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: swapper/0/0x00000005
Jan 30 13:35:03 proxmox1 kernel: Pid: 0, comm: swapper Tainted:  G   M    2.6.24-9-pve #1
Jan 30 13:35:03 proxmox1 kernel:
Jan 30 13:35:03 proxmox1 kernel: Call Trace:
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7485>] thread_return+0x103/0x67e
Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8025fd44>] hrtimer_start+0xd4/0x190

(Continue reading)

John Drescher | 2 Feb 2010 22:36

Picon

Re: BUG: scheduling while atomic

On Tue, Feb 2, 2010 at 4:28 PM, Cliff Wells <cliff@...> wrote:
> I'm running proxmox 1.4:
>
> Linux proxmox1 2.6.24-9-pve #1 SMP PREEMPT Tue Nov 17 09:34:41 CET 2009 x86_64 GNU/Linux
>
>
> I occasionally get these in syslog, sometimes they come in so fast the
> machine becomes unresponsive and must be power cycled:
>
>
> Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31143]: (root) CMD (/usr/share/vzctl/scripts/vpsreboot)
> Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31146]: (root) CMD (/usr/share/vzctl/scripts/vpsnetclean)
> Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: nginx/7242/0x00000003
> Jan 30 13:35:03 proxmox1 kernel: Pid: 7242, comm: nginx Tainted:  G   M    2.6.24-9-pve #1
> Jan 30 13:35:03 proxmox1 kernel:
> Jan 30 13:35:03 proxmox1 kernel: Call Trace:
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7485>] thread_return+0x103/0x67e
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d8f4>] lock_timer_base+0x34/0x70
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024debd>] __mod_timer+0xbd/0xe0
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d38>] schedule_timeout+0x58/0xd0
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d5c0>] process_timeout+0x0/0x10
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d33>] schedule_timeout+0x53/0xd0
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8030876a>] sys_epoll_wait+0x49a/0x560
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8044c0a4>] compat_sys_getsockopt+0x74/0x1d0
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff802370f0>] default_wake_function+0x0/0x10
> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8022aae2>] ia32_sysret+0x0/0xa
> Jan 30 13:35:03 proxmox1 kernel:
> Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: swapper/0/0x00000005
> Jan 30 13:35:03 proxmox1 kernel: Pid: 0, comm: swapper Tainted:  G   M    2.6.24-9-pve #1
> Jan 30 13:35:03 proxmox1 kernel:

(Continue reading)

John Drescher | 2 Feb 2010 22:38

Picon

Re: BUG: scheduling while atomic

On Tue, Feb 2, 2010 at 4:36 PM, John Drescher <drescherjm@...> wrote:
> On Tue, Feb 2, 2010 at 4:28 PM, Cliff Wells <cliff@...> wrote:
>> I'm running proxmox 1.4:
>>
>> Linux proxmox1 2.6.24-9-pve #1 SMP PREEMPT Tue Nov 17 09:34:41 CET 2009 x86_64 GNU/Linux
>>
>>
>> I occasionally get these in syslog, sometimes they come in so fast the
>> machine becomes unresponsive and must be power cycled:
>>
>>
>> Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31143]: (root) CMD (/usr/share/vzctl/scripts/vpsreboot)
>> Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31146]: (root) CMD (/usr/share/vzctl/scripts/vpsnetclean)
>> Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: nginx/7242/0x00000003
>> Jan 30 13:35:03 proxmox1 kernel: Pid: 7242, comm: nginx Tainted:  G   M    2.6.24-9-pve #1
>> Jan 30 13:35:03 proxmox1 kernel:
>> Jan 30 13:35:03 proxmox1 kernel: Call Trace:
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7485>] thread_return+0x103/0x67e
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d8f4>] lock_timer_base+0x34/0x70
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024debd>] __mod_timer+0xbd/0xe0
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d38>] schedule_timeout+0x58/0xd0
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d5c0>] process_timeout+0x0/0x10
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d33>] schedule_timeout+0x53/0xd0
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8030876a>] sys_epoll_wait+0x49a/0x560
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8044c0a4>] compat_sys_getsockopt+0x74/0x1d0
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff802370f0>] default_wake_function+0x0/0x10
>> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8022aae2>] ia32_sysret+0x0/0xa
>> Jan 30 13:35:03 proxmox1 kernel:
>> Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: swapper/0/0x00000005
>> Jan 30 13:35:03 proxmox1 kernel: Pid: 0, comm: swapper Tainted:  G   M    2.6.24-9-pve #1

(Continue reading)

Cliff Wells | 2 Feb 2010 23:53

Re: BUG: scheduling while atomic

Thanks much.  That was my suspicion.

Cliff

On Tue, 2010-02-02 at 16:38 -0500, John Drescher wrote:
> On Tue, Feb 2, 2010 at 4:36 PM, John Drescher <drescherjm@...> wrote:
> > On Tue, Feb 2, 2010 at 4:28 PM, Cliff Wells <cliff@...> wrote:
> >> I'm running proxmox 1.4:
> >>
> >> Linux proxmox1 2.6.24-9-pve #1 SMP PREEMPT Tue Nov 17 09:34:41 CET 2009 x86_64 GNU/Linux
> >>
> >>
> >> I occasionally get these in syslog, sometimes they come in so fast the
> >> machine becomes unresponsive and must be power cycled:
> >>
> >>
> >> Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31143]: (root) CMD (/usr/share/vzctl/scripts/vpsreboot)
> >> Jan 30 13:35:01 proxmox1 /USR/SBIN/CRON[31146]: (root) CMD (/usr/share/vzctl/scripts/vpsnetclean)
> >> Jan 30 13:35:03 proxmox1 kernel: BUG: scheduling while atomic: nginx/7242/0x00000003
> >> Jan 30 13:35:03 proxmox1 kernel: Pid: 7242, comm: nginx Tainted:  G   M    2.6.24-9-pve #1
> >> Jan 30 13:35:03 proxmox1 kernel:
> >> Jan 30 13:35:03 proxmox1 kernel: Call Trace:
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7485>] thread_return+0x103/0x67e
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d8f4>] lock_timer_base+0x34/0x70
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024debd>] __mod_timer+0xbd/0xe0
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d38>] schedule_timeout+0x58/0xd0
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8024d5c0>] process_timeout+0x0/0x10
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff804c7d33>] schedule_timeout+0x53/0xd0
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8030876a>] sys_epoll_wait+0x49a/0x560
> >> Jan 30 13:35:03 proxmox1 kernel: [<ffffffff8044c0a4>] compat_sys_getsockopt+0x74/0x1d0

(Continue reading)

Dietmar Maurer | 3 Feb 2010 08:24

RE: BUG: scheduling while atomic

> -----Original Message-----
> From: users-bounces@...
[mailto:users-bounces@...] On
> Behalf Of Cliff Wells
> Sent: Dienstag, 02. Februar 2010 22:28
> To: users@...
> Subject: [Users] BUG: scheduling while atomic
> 
> I'm running proxmox 1.4:
> 
> Linux proxmox1 2.6.24-9-pve #1 SMP PREEMPT Tue Nov 17 09:34:41 CET 2009
> x86_64 GNU/Linux

I suggest to update to proxmox 1.5 and try the 2.6.18 kernel branch.

- Dietmar

Cliff Wells | 3 Feb 2010 18:47

RE: BUG: scheduling while atomic

On Wed, 2010-02-03 at 08:24 +0100, Dietmar Maurer wrote:
> > -----Original Message-----
> > From: users-bounces@...
[mailto:users-bounces@...] On
> > Behalf Of Cliff Wells
> > Sent: Dienstag, 02. Februar 2010 22:28
> > To: users@...
> > Subject: [Users] BUG: scheduling while atomic
> > 
> > I'm running proxmox 1.4:
> > 
> > Linux proxmox1 2.6.24-9-pve #1 SMP PREEMPT Tue Nov 17 09:34:41 CET 2009
> > x86_64 GNU/Linux
> 
> I suggest to update to proxmox 1.5 and try the 2.6.18 kernel branch.

I have done so, thanks.   I'd still be interested in trying a proxmox
kernel minus preemption.

Cliff

Group

gmane.linux.openvz.user.

Project Web Page

OpenVZ is an Operating System-level server virtualization solution, built on Linux. OpenVZ creates isolated, secure virtual environments

Search Archive

Page

1 | 2 | 3 | 4 | 5 | 6 | 7 | 8

Articles in period: 71

February 2010

Language

Change language

Options

Current view: Threads only / Showing only 20 lines / Not hiding cited text.
Change to All messages, whole messages, or hide cited text.

Post a message
NNTP Newsgroup
Classic Gmane web interface
XML

XML

RSS Feed
List Information

About Gmane

Recent entries

vzctl --noatime (13 May 2013)
AES-NI inside CT (11 May 2013)
OpenVZ Maintenance Partnership (8 May 2013)
add second ploop device to CT (6 May 2013)
Why does vzctl not check dirty flag of ploop device? (6 May 2013)
Openvz template for Debian Wheezy (6 May 2013)
"-R" TASK_ALIVE option (3 May 2013)
vzstats 0.2.1 debianization (1 May 2013)
syslog-ng unable to read /proc/kmsg on 2.6.32-042stab076.5 (18 Apr 2013)
Macvlan with openvz? (18 Apr 2013)
CT produces corrupt dump files (15 Apr 2013)
Error when starting ploop CT (10 Apr 2013)
OpenVZ NFS4/IdmapD (9 Apr 2013)
syslog-ng issues in container (9 Apr 2013)
Unable to bind socket: 80 : Permission denied (8 Apr 2013)
ploop and rhel5 running rhel6 kernel (2 Apr 2013)
Using a specified CPU with cpuset.cpus (31 Mar 2013)
Mounting a cgroup namesapce (special device cgroup does not exist) (31 Mar 2013)
Web server on demand with ckpnt/suspend? (24 Mar 2013)
Backing up ploop-based containers (21 Mar 2013)
eth0 works, vzbr0 does not (21 Mar 2013)

Archives

21	May 2013
23	April 2013
24	March 2013
22	February 2013
36	January 2013
23	December 2012
42	November 2012
29	October 2012
72	September 2012
29	August 2012
49	July 2012
41	June 2012
56	May 2012
64	April 2012
113	March 2012
31	February 2012
46	January 2012
39	December 2011
83	November 2011
55	October 2011
40	September 2011
66	August 2011
8	July 2011
33	June 2011
75	May 2011
30	April 2011
33	March 2011
17	February 2011
21	January 2011
37	December 2010
41	November 2010
11	October 2010
52	September 2010
46	August 2010
122	July 2010
76	June 2010
48	May 2010
88	April 2010
67	March 2010
61	February 2010
86	January 2010
53	December 2009
57	November 2009
22	October 2009
45	September 2009
47	August 2009
42	July 2009
50	June 2009
28	May 2009
25	April 2009
58	March 2009
53	February 2009
130	January 2009
92	December 2008
94	November 2008
35	October 2008
93	September 2008
95	August 2008
65	July 2008
70	June 2008
107	May 2008
41	April 2008
68	March 2008
81	February 2008
104	January 2008
208	December 2007
85	November 2007
80	October 2007
92	September 2007
62	August 2007
51	July 2007
54	June 2007
98	May 2007
95	April 2007
147	March 2007
56	February 2007
55	January 2007
77	December 2006
50	November 2006
47	October 2006
23	September 2006
43	August 2006
15	July 2006
39	June 2006
62	May 2006
19	April 2006
66	February 2006
36	January 2006
3	December 2005
8	November 2005
18	September 2005
1	January 2004

Design

Zawodny | Right Menu | Left Menu

Your Own Design

Paste the URL of your CSS below. Download CSS template