Re: [PATCH net-next] RDS: fix rds-ping deadlock over TCP transport

[santosh shilimkar <santosh.shilimkar@oracle.com>]

On 10/16/2015 6:45 PM, Sowmini Varadhan wrote:
> On (10/16/15 20:26), Santosh Shilimkar wrote:
>>
>> diff --git a/net/rds/send.c b/net/rds/send.c
>> +	if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
>> +		queue_delayed_work(rds_wq, &conn->c_send_w, 0);
>
> A minor note- it would help to add some comments here explaining
> that the pong has already been added to the sendq earlier..
> in the case of IB, if RDS_LL_SEND_FULL has been set, it takes some
> head-scratching to figure out how the pong gets sent, and a  few
> comments could help clarify that.
>
Right. The check confused you. I will update the patch and drop
the check all together and add a jiffies for the queuing which
should take care of it. Will post v2 with that update.

> but other than that, the contents look good to me, thus
>
> Acked-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
>
Thanks !!

regards,
Santosh