Re: [PATCH 1/9] move blk_iopoll to limit and make it generally available

[Christoph Hellwig <hch@lst.de>]

On Sun, Nov 15, 2015 at 10:48:41AM +0200, Sagi Grimberg wrote:
> I have attempted to convert iser to use blk_iopoll in the past, however
> I've seen inconsistent performance and latency skews (comparing to
> tasklets iser is using today). This was manifested in IOPs test cases
> where I ran multiple threads with higher queue-depth and not in
> sanitized pure latency (QD=1) test cases. Unfortunately I didn't have
> the time to pick it up since.
>
> I do have every intention of testing it again with this. If it still
> exist we will need to find the root-cause of it before converting
> drivers to use it.

Thanks.  If you see issue like that with high iops and high loads
the next thing to check are:

 a) increasing the budget (both in the main poll loop and the IB
    code)
 b) try without the single jiffie time limit in the main softirq handler