[ovs-discuss] xenServer and openVswitch 1.0.99

Juan Tellez juan at embrane.com
Thu Feb 2 02:07:00 UTC 2012


Dmesg hasn't changed for a while .. and sadly it is not time-stamped.  Below is the tail:

device vif467.1 entered promiscuous mode
device tap467.0 entered promiscuous mode
device tap467.1 entered promiscuous mode
/local/domain/465/device/vif/0: Connected
/local/domain/465/device/vif/1: Connected
/local/domain/466/device/vif/0: Connected
/local/domain/466/device/vif/1: Connected
/local/domain/467/device/vif/0: Connected
/local/domain/467/device/vif/1: Connected
vif458.2: draining TX queue
vif456.2: draining TX queue
vif457.2: draining TX queue
vif459.2: draining TX queue

> What are the outputs of dmesg and ovs-dpctl show?

[root at localhost ~]# ovs-dpctl show
system at xenbr0:
	lookups: frags:0, hit:14616686, missed:3478742, lost:0
	port 0: xenbr0 (internal)
	port 1: eth0
	port 2: vif455.0
system at xenbr13:
	lookups: frags:0, hit:593802148, missed:104343731, lost:0
	port 0: xenbr13 (internal)
	port 1: eth13
	port 2: vif457.2
system at xenbr7:
	lookups: frags:0, hit:3920419, missed:925949, lost:0
	port 0: xenbr7 (internal)
	port 2: eth7
system at xenbr4:
	lookups: frags:0, hit:3915022, missed:924411, lost:562
	port 0: xenbr4 (internal)
	port 1: eth4
system at xenbr9:
	lookups: frags:0, hit:3915487, missed:923946, lost:0
	port 0: xenbr9 (internal)
	port 1: eth9
system at xenbr3:
	lookups: frags:0, hit:5683665220, missed:12414007, lost:0
	port 0: xenbr3 (internal)
	port 1: eth3
	port 2: xapi22 (internal)
	port 3: vif456.1
	port 4: vif461.1
	port 5: vif457.1
	port 6: vif462.1
	port 7: vif458.1
	port 8: vif463.1
	port 9: vif459.1
	port 10: vif464.1
	port 11: vif460.1
	port 12: vif465.1
	port 13: vif467.1
	port 15: vif466.1
system at xenbr1:
	lookups: frags:0, hit:8477, missed:1261, lost:0
	port 0: xenbr1 (internal)
	port 1: eth1
system at xenbr10:
	lookups: frags:0, hit:3914906, missed:924527, lost:0
	port 0: xenbr10 (internal)
	port 1: eth10
system at xenbr6:
	lookups: frags:0, hit:3915340, missed:924093, lost:0
	port 0: xenbr6 (internal)
	port 1: eth6
system at xenbr12:
	lookups: frags:0, hit:633864034, missed:124577500, lost:0
	port 0: xenbr12 (internal)
	port 1: eth12
	port 2: vif458.2
system at xenbr8:
	lookups: frags:0, hit:3914333, missed:925100, lost:374
	port 0: xenbr8 (internal)
	port 1: eth8
system at xenbr2:
	lookups: frags:0, hit:110495900, missed:1284600, lost:34
	port 0: xenbr2 (internal)
	port 1: eth2
	port 2: xapi21 (internal)
	port 3: vif455.1
	port 4: vif462.0
	port 5: vif456.0
	port 6: vif461.0
	port 7: vif457.0
	port 8: vif458.0
	port 9: vif465.0
	port 10: vif459.0
	port 11: vif467.0
	port 12: vif460.0
	port 13: vif463.0
	port 14: vif464.0
	port 16: vif466.0
system at xenbr11:
	lookups: frags:0, hit:813453787, missed:188880581, lost:593198
	port 0: xenbr11 (internal)
	port 1: eth11
	port 2: vif459.2
system at xenbr14:
	lookups: frags:0, hit:772844627, missed:147971589, lost:332
	port 0: xenbr14 (internal)
	port 1: eth14
	port 2: vif456.2
system at xenbr5:
	lookups: frags:0, hit:3915489, missed:923944, lost:0
	port 0: xenbr5 (internal)
	port 1: eth5



-----Original Message-----
From: Jesse Gross [mailto:jesse at nicira.com] 
Sent: Wednesday, February 01, 2012 5:54 PM
To: Juan Tellez
Cc: discuss at openvswitch.org
Subject: Re: [ovs-discuss] xenServer and openVswitch 1.0.99

On Wed, Feb 1, 2012 at 5:18 PM, Juan Tellez <juan at embrane.com> wrote:
> We also suspect vswitchd as responsible for dropping packets.
>     39:          RX packets:494125 errors:0 dropped:0 overruns:0 frame:0
>      40:          TX packets:519707 errors:0 dropped:8357 overruns:0
> carrier:0
>      46:          RX packets:455837 errors:0 dropped:0 overruns:0 frame:0
>      47:          TX packets:485736 errors:0 dropped:10118 overruns:0
> carrier:0
>      53:          RX packets:455547 errors:0 dropped:0 overruns:0 frame:0
>      54:          TX packets:484577 errors:0 dropped:5718 overruns:0
> carrier:0
>      60:          RX packets:455611 errors:0 dropped:0 overruns:0 frame:0
>      61:          TX packets:481385 errors:0 dropped:10404 overruns:0
> carrier:0
>      67:          RX packets:455162 errors:0 dropped:0 overruns:0 frame:0

These stats are coming from your NIC? Assuming yes, it's unlikely that
they are caused by OVS directly because those are hardware counters.
Since OVS runs before hardware transmit, in order for the packet to be
dropped in hardware it would have to already have passed through OVS.
What are the outputs of dmesg and ovs-dpctl show?

More information about the discuss mailing list