Has anybody ever had any luck with TCP offload on onboard NICs of consumer motherboards?
Were you able to get it to work?
Did it really reduce CPU load?
Did it improve or hinder actual network performance (either ping times or RX/TX speeds)?
Has anybody ever had any luck with TCP offload on onboard NICs of consumer motherboards?
Were you able to get it to work?
Did it really reduce CPU load?
Did it improve or hinder actual network performance (either ping times or RX/TX speeds)?
flow man:
du/dt + u dot del u = - del P / rho + v vector_Laplacian u
{\partial\mathbf{u}\over\partial t}+\mathbf{u}\cdot\nabla\mathbf{u} = -{\nabla P\over\rho} + \nu\nabla^2\mathbf{u}
Sometimes it can help, Sometimes it can do damage
I have turned it on in Vmware and passed to through to the VM - and its not helped at all
Sometimes simple LSO or LRO is enough but its it better for iscsi where you want to do something and not have the x86 cpu be bothered by storage workloads.
It's not (only) for iSCSI. I'm talking just generically.
flow man:
du/dt + u dot del u = - del P / rho + v vector_Laplacian u
{\partial\mathbf{u}\over\partial t}+\mathbf{u}\cdot\nabla\mathbf{u} = -{\nabla P\over\rho} + \nu\nabla^2\mathbf{u}
Posting Permissions
Reply With Quote
Bookmarks