In the event of Sept. 10, however, the hardware was not able to fit the entire forwarding table, which was 210x their normal routes into the FIB memory, and the routers fell back to "software switching mode."
Why was the entire forwarding table 210x their normal routes? Is that a normal expansion due to the exponential nature of a fully (or substantially) connected graph or did something Very Bad happen and GoDaddy effectively DOSed their forwarding tables?
If (a), then GoDaddy missed the fact that they had nearly exhausted their FIB table physical size. This is easy to do and understandable.
If (b), they the article has not come clean why they had a massive, unexpected forwarding table size increase.
2 comments
[ 3.0 ms ] story [ 19.2 ms ] threadWhy was the entire forwarding table 210x their normal routes? Is that a normal expansion due to the exponential nature of a fully (or substantially) connected graph or did something Very Bad happen and GoDaddy effectively DOSed their forwarding tables?
If (a), then GoDaddy missed the fact that they had nearly exhausted their FIB table physical size. This is easy to do and understandable.
If (b), they the article has not come clean why they had a massive, unexpected forwarding table size increase.