[ryao]

Your information is out of date. Losing s SLOG device while the system is running is fine. As far as I know, it has always been fine (unless someone goofed on the initial implementation long before I became involved). All data in ZIL is kept in memory, regardless of whether it is written to the main pool or to a SLOG device. The data is written to the main pool in a permanent fashion with the transaction group commit. If a SLOG device dies, that write out still happens and the pool harmlessly stops using it. If the SLOG device dies on an exported pool, you need to set the zil_replay_disable kernel module parameter to allow the pool to be imported. The same might be true if you reboot (although I doubt it, but need to check).

You can test these things for yourself.