Re: [PATCH RFC V2 33/46] mmc: mmc_test: Disable Command Queue while mmc_test is used

[Adrian Hunter <adrian.hunter@intel.com>]

On 10/06/16 13:59, Venu Byravarasu wrote:
>> -----Original Message-----
>> From: linux-mmc-owner@vger.kernel.org [mailto:linux-mmc-
>> owner@vger.kernel.org] On Behalf Of Adrian Hunter
>> Sent: Friday, June 10, 2016 4:15 PM
>> To: Ulf Hansson
>> Cc: linux-mmc; Alex Lemberg; Mateusz Nowak; Yuliy Izrailov; Jaehoon Chung;
>> Dong Aisheng; Das Asutosh; Zhangfei Gao; Sujit Reddy Thumma; Dorfman
>> Konstantin; David Griego; Sahitya Tummala; Harjani Ritesh
>> Subject: [PATCH RFC V2 33/46] mmc: mmc_test: Disable Command Queue
>> while mmc_test is used
>>
>> Normal read and write commands may not be used while the command
>> queue is enabled.
> 
> CQ may not be efficient when single rd/wr commands get issued with variable delays in between.
> In such situations, CQ preparation for individual rd/wr cmds would be an unnecessary overhead. 
> Hence even when CQ is supported, prefer CQ only when more than 1 data cmds are to be issued to device.

So you are suggesting toggling CQ on/off depending on whether there is more
than 1 data request?

Does that apply also to using hardware CQ i.e. a v5.1 host controller?