We might have been able to get away with raw SQL, but because of some of the complexities and dependencies on this same code, I felt like it wasn't the prudent choice during a fire. I wouldn't have had time to properly test it.
As for moving the inserts to an async job, that was one of our thoughts, too. Really it's what we did, but we just have the intermediary step of MongoDB. We wanted that step (rather than just immediately returning to the user and having the client not know when the inserts actually occur) because we wanted to keep the user experience great. Our app immediately sends you to personalized recs. We didn't want the initial experience to be: open the app => sent to a blank page of "recommendations."
An async job that didn't wait for any sort of confirmation would have left us in this position (or we would have had to implement a poller to check if the inserts were complete, which seemed wasteful and would need a push to Android Market which seemed less feasible.)
As for moving the inserts to an async job, that was one of our thoughts, too. Really it's what we did, but we just have the intermediary step of MongoDB. We wanted that step (rather than just immediately returning to the user and having the client not know when the inserts actually occur) because we wanted to keep the user experience great. Our app immediately sends you to personalized recs. We didn't want the initial experience to be: open the app => sent to a blank page of "recommendations."
An async job that didn't wait for any sort of confirmation would have left us in this position (or we would have had to implement a poller to check if the inserts were complete, which seemed wasteful and would need a push to Android Market which seemed less feasible.)