[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#732279: linux-image-3.2.0-4-686-pae: netback page allocation failure (Xen memory leak?)

Hi Ben,

Thank you for the quick reply. :-)

OThe only "strange" network related thing on this machine is pgld[1] which messes heavily with iptables.

> Please provide details of your networking configuration,
> including:
>
> - Are you using ebtables?

No

> - Are you using VLAN devices?

No

Here is ifconfig -a
---
eth0      Link encap:Ethernet  HWaddr 00:1c:c4:5c:28:d2 
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:17280502 errors:0 dropped:0 overruns:0 frame:0
          TX packets:14882131 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000
          RX bytes:12453053120 (11.5 GiB)  TX bytes:13160381323 (12.2 GiB)
          Interrupt:17

lo        Link encap:Local Loopback 
          inet addr:127.0.0.1  Mask:255.0.0.0
          inet6 addr: ::1/128 Scope:Host
          UP LOOPBACK RUNNING  MTU:16436  Metric:1
          RX packets:49929 errors:0 dropped:0 overruns:0 frame:0
          TX packets:49929 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:0
          RX bytes:7632840 (7.2 MiB)  TX bytes:7632840 (7.2 MiB)

vif2.0    Link encap:Ethernet  HWaddr fe:ff:ff:ff:ff:ff 
          inet6 addr: fe80::fcff:ffff:feff:ffff/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:7680792 errors:0 dropped:0 overruns:0 frame:0
          TX packets:10164315 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:32
          RX bytes:2514841954 (2.3 GiB)  TX bytes:3670559977 (3.4 GiB)

xenbr0    Link encap:Ethernet  HWaddr 00:1c:c4:5c:28:d2 
          inet addr:10.0.0.10  Bcast:10.0.0.255  Mask:255.255.255.0
          inet6 addr: fe80::21c:c4ff:fe5c:28d2/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:17967984 errors:0 dropped:0 overruns:0 frame:0
          TX packets:14972347 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:0
          RX bytes:13275577776 (12.3 GiB)  TX bytes:15076571340 (14.0 GiB)
---

iptables -L -n -v
---
Chain INPUT (policy ACCEPT 18M packets, 13G bytes)
 pkts bytes target     prot opt in     out     source               destination        
 371K   30M pgl_in     all  --  *      *       0.0.0.0/0            0.0.0.0/0            ! ctstate RELATED,ESTABLISHED mark match ! 0x14
 117K 9242K fail2ban-ssh  tcp  --  *      *       0.0.0.0/0            0.0.0.0/0            multiport dports 22

Chain FORWARD (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination        
2128K 5213M ACCEPT     all  --  *      *       0.0.0.0/0            0.0.0.0/0            PHYSDEV match --physdev-out vif2.0 --physdev-is-bridged
1982K  299M ACCEPT     all  --  *      *       0.0.0.0/0            0.0.0.0/0            PHYSDEV match --physdev-in vif2.0 --physdev-is-bridged
    0     0 pgl_fwd    all  --  *      *       0.0.0.0/0            0.0.0.0/0            ! ctstate RELATED,ESTABLISHED mark match ! 0x14

Chain OUTPUT (policy ACCEPT 15M packets, 15G bytes)
 pkts bytes target     prot opt in     out     source               destination        
 189K   12M pgl_out    all  --  *      *       0.0.0.0/0            0.0.0.0/0            ! ctstate RELATED,ESTABLISHED mark match ! 0x14

Chain fail2ban-ssh (1 references)
 pkts bytes target     prot opt in     out     source               destination        
 117K 9242K RETURN     all  --  *      *       0.0.0.0/0            0.0.0.0/0          

Chain pgl_fwd (1 references)
 pkts bytes target     prot opt in     out     source               destination        
    0     0 RETURN     all  --  *      *       10.0.0.0/24          10.0.0.0/24        
    0     0 RETURN     all  --  *      *       0.0.0.0/0            10.0.0.1           
    0     0 RETURN     all  --  *      *       0.0.0.0/0            127.0.0.1          
    0     0 DROP       all  --  *      *       0.0.0.0/0            0.0.0.0/0            mark match 0xa
    0     0 NFQUEUE    all  --  *      *       0.0.0.0/0            0.0.0.0/0            NFQUEUE num 92

Chain pgl_in (1 references)
 pkts bytes target     prot opt in     out     source               destination        
 309K   26M RETURN     all  --  *      *       10.0.0.0/24          0.0.0.0/0          
24085 1561K RETURN     all  --  lo     *       0.0.0.0/0            0.0.0.0/0          
 4274  251K DROP       all  --  *      *       0.0.0.0/0            0.0.0.0/0            mark match 0xa
    0     0 RETURN     all  --  *      *       0.0.0.0/0            0.0.0.0/0            source IP range [snip]
    0     0 RETURN     all  --  *      *       0.0.0.0/0            0.0.0.0/0            source IP range [snip]
    0     0 RETURN     all  --  *      *       0.0.0.0/0            0.0.0.0/0            source IP range [snip]
    0     0 RETURN     all  --  *      *       0.0.0.0/0            0.0.0.0/0            source IP range [snip]
    0     0 RETURN     all  --  *      *       0.0.0.0/0            0.0.0.0/0            source IP range [snip]
    0     0 RETURN     tcp  --  *      *       0.0.0.0/0            0.0.0.0/0            tcp dpt:993
    0     0 RETURN     tcp  --  *      *       0.0.0.0/0            0.0.0.0/0            tcp dpt:443
    0     0 RETURN     tcp  --  *      *       0.0.0.0/0            0.0.0.0/0            tcp dpt:80
    0     0 RETURN     tcp  --  *      *       0.0.0.0/0            0.0.0.0/0            tcp dpt:25
 4546  263K RETURN     tcp  --  *      *       0.0.0.0/0            0.0.0.0/0            tcp dpt:22
28548 1631K NFQUEUE    all  --  *      *       0.0.0.0/0            0.0.0.0/0            NFQUEUE num 92
---

Let me know if you need to see anything else.

[1] http://sourceforge.net/p/peerguardian/wiki/pgl-Main/


Best regards,

George


On 16 December 2013 17:52, Ben Hutchings <ben@decadent.org.uk> wrote:
On Mon, Dec 16, 2013 at 09:41:56AM +0000, George B. wrote:
> Package: src:linux
> Version: 3.2.51-1
> Severity: normal
>
> Hello,
>
> I am seeing the backtrace below in my kernel log after the system has been running for several weeks.
>
> Looks like it has something to do with Xen - memory leak maybe?

I'm not sure it's directly connected with Xen - I think that an
interrupt from the physical network interface interrupted a task that
is part of the netback driver.

This is not necessarily due to a memory leak; more likely this is
memory fragmentation.  Some oddity of your networking configuration
results in linearising large packets:

[...]
> [955212.368551] netback/0: page allocation failure: order:3, mode:0x20
[...]

This means: allocating something between 16 and 32K atomically
(no waiting allowed).

The call trace appears to show that a packet received by the local TCP
via a bridge resulted in an immediate transmission, again going
through the bridge, and that then required this large memory
allocation.

Please provide details of your networking configuration,
including:

- Are you using ebtables?
- Are you using VLAN devices?

Ben.

--
Ben Hutchings
Life is like a sewer:
what you get out of it depends on what you put into it.

Reply to: