>On 10/20/2014 11:01 AM, Or Gerlitz wrote:
>> On Mon, Oct 20, 2014 at 8:36 AM, Minh Duc Tran
>> <MinhDuc.Tran@xxxxxxxxxx> > ---
>> a/drivers/infiniband/ulp/iser/iser_verbs.c
>>> +++ b/drivers/infiniband/ulp/iser/iser_verbs.c
>> @@ -114,6 +114,9 @@ static int iser_create_device_ib_res(struct iser_device *device)
>>> if (IS_ERR(device->pd))
>>> goto pd_err;
>>>
>>> + max_cqe = (dev_attr->max_cqe < ISER_MAX_CQ_LEN) ?
>>> + dev_attr->max_cqe : ISER_MAX_CQ_LEN;
>>> +
>>
>> If I was the ocrdma maintainer I would say load and clear: NO, please.
>>
>> Your current offering supports 32 CQs per device, and this means that
>> on 32 core node you will be able to run only iSER, no other ULP.
>This is max CQ entries, are you referring to max_cq? or am I missing something?
>I tend to agree that if the device supports smaller CQs we should not just fail everything, but adjust accordingly.
>Sagi.
Yes, I think Or's response is a bit confusing when post under the block of patch which is relating to max CQ entries per CQ, not max CQs.
Though, we did mention supporting more CQs as part of the TODO list at some points in this discussion.
The patch we have posted will work with current IB/iser supported CQs as well as max_cq/2 in the TODO list.
-Minh
��.n��������+%������w��{.n�����{���fk��ܨ}���Ơz�j:+v�����w����ޙ��&�)ߡ�a����z�ޗ���ݢj��w�f
