search for: fill_zero

...t after the first regular write, the boolean is set to false, and all further write zero requests fail as being potentially slow; and such an implementation is still useful for the qemu-img convert case. > > There is not such problem if we have only one iteration, so may be new command > FILL_ZERO, filling the whole device by zeros? Or better yet, implement support for 64-bit commands. Yes, my cover letter called out further orthogonal extensions, and implementing 64-bit zeroing (so that you can issue a write zero request over the entire image in one command), as well as a way for a server...

This is a cover letter to a series of patches being proposed in tandem to four different projects: - nbd: Document a new NBD_CMD_FLAG_FAST_ZERO command flag - qemu: Implement the flag for both clients and server - libnbd: Implement the flag for clients - nbdkit: Implement the flag for servers, including the nbd passthrough client If you want to test the patches together, I've pushed a