Hi Kireeti. Kireeti Kompella <[email protected]> writes:
> So, here's my attempt to quantify the cost of push by normalizing > the cost per VM. This is all very naive and preliminary (for now), > but the numbers, such as they are, may speak for themselves. > Let's go back to the case of a VN with 10,000 VMs (each with 4GB > RAM); as the worst case, assume each VM is on a different > hypervisor. > 1) assuming 100 bytes per route, the memory cost per VM (as above) > is 1MB for FIB space. For a 4GB VM, that's a "tax" of 0.025% > 2) For VM motion, each VM moves needs an update to 10,000 NVEs. > Assume each update is ~1000 bytes; that's a total of 10MB sent. > Moving the VM is 4GB (or more) sent. The "tax" is 0.25%. 10MB worth of updates for a single VM move doesn't seem insignificant to me. A few MB here, a few MB there, pretty soon we're talking about real bandwith. :) The .25% tax figures is apples to oranges. The VM that is moving pays the cost of doing the 4MB move. But that tax you are talking about is paid by the NVEs, not the VM doing the move. If we assume 10 VMs per NV, thats 1000 NVEs paying that tax. > 3) Processing an update message is a very small number of cycles. I > don't know enough to compute the "tax" for this, but I'd guess very > small. A small tax here, a small tax there, ... > Clearly, there are other dimensions to this problem; folks might > have better numbers or estimates. But so far, push is looking > pretty good. > So, is there a metric whereby push really hurts, and considering > pull becomes a necessity? Or is the suggestion to explore pull > models as due diligence, irrespective of the need? Or ? I doubt that it's worthwile trying to come up with a metric in advance. Most likely, we'll just start arguing about the assumptions being fed into the mode. I don't see the point in restricting the architecture to a "push" model at this early juncture. I also don't think its necessary. Thomas
_______________________________________________ nvo3 mailing list [email protected] https://www.ietf.org/mailman/listinfo/nvo3
