1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
|
<think>
Okay, so I'm trying to figure out why the VM isn't pinging the remote bridged network system properly. Let's see what information is provided.
First, looking at the ping results from the VM (10.153.107.92) to 10.153.107.80: it works with 0% packet loss, so maybe that's not an issue. But I notice that in the arp -an outputs, on the KVMhost, only 10.153.107.80 is listed with a MAC address on br0. On the VM itself, when it tries to ping, one of the entries shows (10.153.107.61) at incomplete on eth0. That might be a problem because if the ARP entry is incomplete, the VM doesn't know how to reach that IP address.
Wait, but in Test #3, when pinging from VM to 10.153.107.80, it worked. So maybe the issue isn't with the bridged network itself, but perhaps something else. The user mentioned a workaround using active-backup mode on the bonded device. Maybe the current setup is in another mode that's causing issues.
Looking at the packages and kernel version: Ubuntu 10.04.02 with qemu-kvm-0.12.3. That's an older version, so perhaps there are known bugs or compatibility issues. The bonding driver might not be handling the modes correctly on this setup.
Another thought: Maybe the bridge configuration is causing problems. If br0 is set up incorrectly, it could prevent proper communication between VMs and external networks. I should check if the bridge interface is properly configured to allow traffic through.
Also, looking at the ARP tables, on KVMhost only 10.153.107.80 is listed with a MAC, but from the remote system, it also shows 10.153.107.92 correctly. On the VM, when pinging 10.153.107.80, it sees that address and its MAC on eth0, which seems correct.
Wait, in Test #3's VM arp -an, there's an entry for 10.153.107.61 with incomplete. Maybe the VM is trying to reach another IP (maybe its own?) but can't resolve it. That could be a separate issue or maybe related to the network setup.
The user suggested switching to active-backup mode as a workaround, so perhaps the current mode isn't handling failover correctly. If using active-backup, only one link is used at a time, which might resolve issues with how traffic is routed through the bond.
I should also consider if there are any firewall rules or network policies blocking certain traffic. But since pings are working, maybe it's not a firewall issue.
To sum up, possible causes could be:
1. Incorrect bonding mode configuration.
2. Bridge setup problems on KVMhost.
3. ARP resolution issues within the VM or host.
The suggested workaround is to switch to active-backup mode, which might fix the problem if it's related to how traffic is being handled across multiple links in the bond.
</think>
To resolve the issue with network communication between the virtual machine and the bridged network system, we can try switching the bonding mode to "active-backup." This mode ensures that only one link is used at a time, which might fix any issues related to how traffic is routed through the bond.
**Step-by-Step Solution:**
1. **Identify Bonding Configuration File:**
- Locate the bonding configuration file, typically found in `/etc/modprobe.d/bonding.conf` or by checking your distribution's specific location.
2. **Modify Bonding Mode to Active-Backup:**
- Edit the bonding configuration file to set the default mode to active-backup.
```bash
alias bond-type bond0=active-backup
```
3. **Reconfigure Network Interfaces:**
- Update your network interface configuration (e.g., `/etc/network/interfaces`) to use the new bonding settings, ensuring that only one link is active at a time.
4. **Restart Networking Services:**
- After updating configurations, restart the networking services to apply the changes.
```bash
sudo /etc/init.d/networking restart
```
5. **Test Network Communication:**
- From the VM, attempt to ping the remote bridged network system again to check if communication has been established.
6. **Verify ARP Tables and Traffic:**
- Check the ARP tables on both the KVM host and the VM to ensure that all necessary IP-MAC mappings are correctly resolved.
```bash
arp -an
```
7. **Monitor Network Performance:**
- If issues persist, monitor network traffic and bonding status to ensure that the active-backup mode is functioning as expected.
By switching to the active-backup mode, we can test if this resolves the communication issue, allowing proper network traffic flow between the VM and the external network.
|