Re: [PATCH] io_uring/rsrc: send exact nr_segs for fixed buffer

[Jens Axboe <axboe@kernel.dk>]

On 4/16/25 9:03 AM, Pavel Begunkov wrote:
> On 4/16/25 06:44, Nitesh Shetty wrote:
>> Sending exact nr_segs, avoids bio split check and processing in
>> block layer, which takes around 5%[1] of overall CPU utilization.
>>
>> In our setup, we see overall improvement of IOPS from 7.15M to 7.65M [2]
>> and 5% less CPU utilization.
>>
>> [1]
>>       3.52%  io_uring         [kernel.kallsyms]     [k] bio_split_rw_at
>>       1.42%  io_uring         [kernel.kallsyms]     [k] bio_split_rw
>>       0.62%  io_uring         [kernel.kallsyms]     [k] bio_submit_split
>>
>> [2]
>> sudo taskset -c 0,1 ./t/io_uring -b512 -d128 -c32 -s32 -p1 -F1 -B1 -n2
>> -r4 /dev/nvme0n1 /dev/nvme1n1
>>
>> Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
>> ---
>>   io_uring/rsrc.c | 3 +++
>>   1 file changed, 3 insertions(+)
>>
>> diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
>> index b36c8825550e..6fd3a4a85a9c 100644
>> --- a/io_uring/rsrc.c
>> +++ b/io_uring/rsrc.c
>> @@ -1096,6 +1096,9 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
>>               iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
>>           }
>>       }
>> +    iter->nr_segs = (iter->bvec->bv_offset + iter->iov_offset +
>> +        iter->count + ((1UL << imu->folio_shift) - 1)) /
>> +        (1UL << imu->folio_shift);
> 
> That's not going to work with ->is_kbuf as the segments are not uniform in
> size.

Oops yes good point.

> And can we make it saner? Split it into several statements, add variables
> for folio size and so, or maybe just use ALIGN. If moved above, you
> probably don't even need to recalc
> 
> iter->bvec->bv_offset + iter->iov_offset

Agree, was trying to do that with the shift at least, but seems like
there is indeed room for further improvements here in terms of
readability.

-- 
Jens Axboe