On Tue, June 12, 2012 8:07 pm, Jaehoon Chung wrote:
> On 06/12/2012 07:58 PM, merez@xxxxxxxxxxxxxx wrote:
>
>>> @@ -359,12 +443,15 @@ struct mmc_async_req *mmc_start_req(struct
>> mmc_host
>>> *host,
>>> if (!err && areq)
>>> start_err = __mmc_start_req(host, areq->mrq);
>>>
>>> - if (host->areq)
>>> + if (host->areq) {
>>> + if (!areq && host->areq && mmc_card_mmc(host->card))
>>> + mmc_start_bkops(host->card);
>> I think it would be better to start tey BKOPs in the queue thread when
>> it
>> becomes idle.
>> We have seen cases where there are several requests fetched and then
>> NULL
>> but by the time the previous request ends there are more requests to be
>> fetched. Starting the BKOPs here instead of in the queue thread
>> increases
>> the probability of using HPI to stop the BKOPs due to incoming request,
>> which is not a desirable action.
>
> I will change this point.
>
>>
>>> mmc_post_req(host, host->areq->mrq, 0);
>>> + }
>>>
>>> /* Cancel a prepared request if it was not started. */
>>> if ((err || start_err) && areq)
>>> - mmc_post_req(host, areq->mrq, -EINVAL);
>>> + mmc_post_req(host, areq->mrq, -EINVAL);
>> Remove this change, it is not related to this patch.
>
> Ok.
> Anything else?
>
> Best Regards,
> Jaehoon Chung
We have no further comments.
Thanks,
Maya Erez
--
Sent by consultant of Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
