Vincent

@imzhenyu, the code piece here is fine to fix the "strerror" bug, but I can't find it in our project. So is it OK if I add this to our...

In addition, fsync is a block io operation, which is unfriendly to rDSN, so should we consider "aio_fsync" and wrap it as a api of disk_aio?

@imzhenyu, in `aio_provider` of linux, the `flush` method calls `fsync`, but we don't see anywhere that calls aio_provider's `flush` during the prepare of a mutation log.

@imzhenyu did you refer to the O_DIRECT? Behavior of O_DIRECT in Linux is not hardware/filesystem-independent, O_SYNC/O_DSYNC should be the proper choice for us. See [this](http://man7.org/linux/man-pages/man2/open.2.html) Three issues: (1) is there...

O_SYNC is enough for hard sync, but as far as I can see, O_DIRECT is not necessary. And if we write file with a buffer of page size, the write...

3q. I will try to work on this, too :)

I'd prefer closing the socket, because I think it is closer to the real world's tcp failure model. Besides, closing the tcp socket helps to test some corner case of...

OK, let me try to locate the root cause later.

placing replicas on ssd is more or less balanced with a greedy algorithm currently.

把rserver和mserver改名成replica_server和meta_server就好，别的没问题。