On 1/17/2020 4:10 PM, Ilya Maximets wrote:
On 17.01.2020 15:23, Stokes, Ian wrote:
On 1/16/2020 5:00 PM, Flavio Leitner wrote:
Abbreviated as TSO, TCP Segmentation Offload is a feature which enables
the network stack to delegate the TCP segmentation to the NIC reducing
the per packet CPU overhead.
A guest using vhostuser interface with TSO enabled can send TCP packets
much bigger than the MTU, which saves CPU cycles normally used to break
the packets down to MTU size and to calculate checksums.
It also saves CPU cycles used to parse multiple packets/headers during
the packet processing inside virtual switch.
If the destination of the packet is another guest in the same host, then
the same big packet can be sent through a vhostuser interface skipping
the segmentation completely. However, if the destination is not local,
the NIC hardware is instructed to do the TCP segmentation and checksum
calculation.
It is recommended to check if NIC hardware supports TSO before enabling
the feature, which is off by default. For additional information please
check the tso.rst document.
Thanks for the patch Flavio,
Ciara has vaidated the series and no issues found on our side.
@Ilya, any concerns on your side? Any reason to blocking this to merge?
I'm looking at patches now. Will reply soon with results.
One thing is that I'm asking to rename patches before pushing them
to master due to incorrect 'area':
vhost: Disable multi-segmented buffers
--> netdev-dpdk: Disable multi-segmented buffers for vhost.
netdev-dpdk: Add TCP Segmentation Offload support
--> userspace: Add TCP Segmentation Offload support.
Thanks Ilya, your feedback is much appreciated.
Regards
Ian
Best regards, Ilya Maximets.
_______________________________________________
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
