Re: [PATCH] block: Export REQ_FLUSH status via sysfs

[Andy Grover <agrover@redhat.com>]

On 05/14/2014 05:11 PM, Nicholas A. Bellinger wrote:
> On Wed, 2014-05-14 at 15:51 -0700, Andy Grover wrote:
>> Whether this is set or not is important for whether good performance is
>> possible, when using the block device as a backstore for the kernel
>> target. Exposing this will let kernel target configuration tools provide
>> this information to the user when configuring LIO targets.
>>
>
> The whole point is that IBLOCK detects if WCE is enabled on the
> underlying block_device at creation time using these same flags, and
> sets its own WCE bit automatically without any user interaction.
>
> The user should not be allowed to change the WCE bit to something
> different from what the underlying block_device is reporting.
>
> That said, I don't see the point of this patch for target related logic.

My understanding is that a LIO target backed by a block device that 
doesn't support REQ_FLUSH will have subpar performance.

Userspace configuration tools could potentially warn the user if this is 
the case.

This information doesn't appear to be currently available to userspace.

Regards -- Andy