Re: [PATCHSET v3 0/5] Support for RWF_UNCACHED

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 12/11/19 6:08 PM, Linus Torvalds wrote:
> On Wed, Dec 11, 2019 at 3:41 PM Jens Axboe <axboe@xxxxxxxxx> wrote:
>>
>> Here's what I did to reproduce:
> 
> Gaah. I have a fairly fast ssd (but it's "consumer fast" - Samsung 970
> Pro - I'm assuming yours is a different class), but I encrypt my disk,
> so I only get about 15k iops and I see kcyrptd in my profiles, not
> kswapd.
> 
> I didn't even try to worry about RWF_UNCACHED or RWF_NOACCESS, since I
> wanted to see the problem. But I think that with my setup, I can't
> really see it just due to my IO being slow ;(
> 
> I do see xas_create and kswapd0, but it's 0.42%. I'm assuming it's the
> very first signs of this problem, but it's certainly not all that
> noticeable.

15K is likely too slow to really show an issue, I'm afraid. The 970
is no slouch, but your crypt setup will likely hamper it a lot. You
don't have a non-encrypted partition on it? I always set aside a
decently sized empty partition on my laptop to be able to run these
kinds of things without having to resort to a test box.

Latency is where it's down the most, you'll likely do better with
more threads to get the IOPS up.

-- 
Jens Axboe





[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux