On Tue, Apr 29, 2014 at 8:35 AM, Jarno Rajahalme wrote:
>
> On Apr 28, 2014, at 3:58 PM, Andy Zhou wrote:
>
>> Currently physical ports stats are collected from kernel datapath.
>> However, those counter do not reflect actual wire packet counters
>> when LSO or TSO are enabled by the NIC. In the
On Tue, Apr 29, 2014 at 7:33 AM, Ben Pfaff wrote:
> On Mon, Apr 28, 2014 at 03:58:51PM -0700, Andy Zhou wrote:
>> Currently physical ports stats are collected from kernel datapath.
>> However, those counter do not reflect actual wire packet counters
>> when LSO or TSO are enabled by the NIC. In th
On Tue, Apr 29, 2014 at 7:33 AM, Ben Pfaff wrote:
> On Mon, Apr 28, 2014 at 03:58:51PM -0700, Andy Zhou wrote:
>> Currently physical ports stats are collected from kernel datapath.
>> However, those counter do not reflect actual wire packet counters
>> when LSO or TSO are enabled by the NIC. In th
On Apr 28, 2014, at 3:58 PM, Andy Zhou wrote:
> Currently physical ports stats are collected from kernel datapath.
> However, those counter do not reflect actual wire packet counters
> when LSO or TSO are enabled by the NIC. In the meantime, the stats
> collected form routing stack does. While b
On Mon, Apr 28, 2014 at 03:58:51PM -0700, Andy Zhou wrote:
> Currently physical ports stats are collected from kernel datapath.
> However, those counter do not reflect actual wire packet counters
> when LSO or TSO are enabled by the NIC. In the meantime, the stats
> collected form routing stack doe
Currently physical ports stats are collected from kernel datapath.
However, those counter do not reflect actual wire packet counters
when LSO or TSO are enabled by the NIC. In the meantime, the stats
collected form routing stack does. While both stats are valid, Reporting
netlink stats for packet c
