-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
vf offload dump draft #371
Conversation
797dd98
to
2e4c4b1
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The async hw tracing start event looks even simpler that I thought it would be, nice.
e42e8bf
to
bdab795
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe we could use the same approach as before, where the main work is done, and I can take care of the tedious nitpicking in my separate commit?
31f6601
to
3d9a1db
Compare
c54a957
to
26213bb
Compare
26213bb
to
06db6b1
Compare
06db6b1
to
de1e7aa
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I tried running this and (apart from small warnings), it actually segfaults for --hw
option, software works fine. Happens for both --no-offload
and with offlosing on dp-service
4e47bb1
to
6690e5a
Compare
ba7fad7
to
020d159
Compare
61f4f9d
to
28f785f
Compare
6b32ae3
to
8758ab4
Compare
ded9024
to
738eeee
Compare
29542d1
to
97da7f0
Compare
… directly jump to vnet group
97da7f0
to
66c24ce
Compare
This draft PR proposed changes to perform pkt dumping on VF when offloading is enabled. It is going to replicate the pkts coming from VMs and send them to the (local) graphtrace tool. Due to the hw limitation, it is not yet possible to mark replicated pkts so as to immediately identify the incoming pkts on the SW path. This decision is done in cntrack, and until that time it is possible to identify those replicated pkts. Extra information in the graphtrace is used to help users to identify replicated pkts' trace.
starting dp_graphtrace with option
--hw-packet
dumps packets from VF, in case VM is not accessible