[Drbd-dev] 答复： Re: Querying the devel plan of speed up initial sync of new and empty devices

[Nick Wang]

Hello Philipp,

Thanks for your information.
i was wrong.mkfs don't zero out the device, otherwise it won't 
perform that fast.

It is no harm for inconsistent date if don't touch it,  i still need to 
evaluate the benefit of implement the option to customer. It should 
faster than full sync (without checksum-based), but still need quite 
a long time for the large disk. 

Thanks & Best regards,
Nick

>>> 在 23:11 的 2015-3-9 上，在讯息 <2835660.5HzbWRi9pB at fat-tyre> 中，Philipp
Reisner <philipp.reisner at linbit.com> 写入：
> Hi Nick,
> 
> FYI: I do not know a mkfs that zeros out the block device.
> All mkfs.XXX I know only write a few blocks of a block device.
> The super block, block group descriptors, a journal...
> 
> ..onyl if the device supports discard (SSDs, thinly provisioned
> storage) e.g. mkfs.ext4 uses that to discard the block device.
> 
> The remaining question is if it is worth the trouble to do it
> in DRBD as well? -- BTW, you will not need to implement a
> flag in the meta-data, but you need to ship such a flag
> in the protocol...
> 
> best regards,
>  Phil