Re: don't reorder requests passed to ->queue_rqs

[Jens Axboe <axboe@kernel.dk>]

On 11/13/24 11:33 AM, Bart Van Assche wrote:
> 
> On 11/13/24 7:20 AM, Christoph Hellwig wrote:
>> currently blk-mq reorders requests when adding them to the plug because
>> the request list can't do efficient tail appends.  When the plug is
>> directly issued using ->queue_rqs that means reordered requests are
>> passed to the driver, which can lead to very bad I/O patterns when
>> not corrected, especially on rotational devices (e.g. NVMe HDD) or
>> when using zone append.
>>
>> This series first adds two easily backportable workarounds to reverse
>> the reording in the virtio_blk and nvme-pci ->queue_rq implementations
>> similar to what the non-queue_rqs path does, and then adds a rq_list
>> type that allows for efficient tail insertions and uses that to fix
>> the reordering for real and then does the same for I/O completions as
>> well.
> 
> Hi Christoph,
> 
> Could something like the patch below replace this patch series? I
> don't have a strong opinion about which approach to select.

I mean it obviously could, but it'd be a terrible way to go as we're now
iterating the full list just to reverse it...

-- 
Jens Axboe