Tuesday's Gmail Fail

Google has posted their official explanation of Tuesday's nearly two-hour Gmail collapse:

Here's what happened: This morning (Pacific Time) we took a small fraction of Gmail's servers offline to perform routine upgrades. This isn't in itself a problem — we do this all the time, and Gmail's web interface runs in many locations and just sends traffic to other locations when one is offline.

However, as we now know, we had slightly underestimated the load which some recent changes (ironically, some designed to improve service availability) placed on the request routers — servers which direct web queries to the appropriate Gmail server for response. At about 12:30 pm Pacific a few of the request routers became overloaded and in effect told the rest of the system "stop sending us traffic, we're too slow!". This transferred the load onto the remaining request routers, causing a few more of them to also become overloaded, and within minutes nearly all of the request routers were overloaded. As a result, people couldn't access Gmail via the web interface because their requests couldn't be routed to a Gmail server. IMAP/POP access and mail processing continued to work normally because these requests don't use the same routers.

This is stunning incompetence from an organization that I've come to expect excellence from. First, not having good data on traffic load before undertaking an upgrade of this sort is indicative of incredible sloppiness. Second, having a router overload algorithm that defaults to shutting down routers rather than simply routing traffic more slowly is idiotic (up to a point--at some point traffic becomes so slow as to render it useless).

Google says that they've addressed these issues, but, I have to say this shakes my faith in a company that I've come to regard as a paragon of excellent quality and service.