Re: Direct I/O performance problems with 1GB pages

[David Hildenbrand <david@redhat.com>]

On 27.01.25 19:54, Jens Axboe wrote:
> On 1/27/25 11:21 AM, Andres Freund wrote:
>>> That's precisely what io-uring fixed buffers do :)
>>
>> I looked at using them at some point - unfortunately it seems that there is
>> just {READ,WRITE}_FIXED not {READV,WRITEV}_FIXED. It's *exceedingly* common
>> for us to do reads/writes where source/target buffers aren't wholly
>> contiguous. Thus - unless I am misunderstanding something, entirely plausible
>> - using fixed buffers would unfortunately increase the number of IOs
>> noticeably.
>>
>> Should have sent an email about that...
>>
>> I guess we could add some heuristic to use _FIXED if it doesn't require
>> splitting an IO into too many sub-ios. But that seems pretty gnarly.
> 
> Adding Pavel, he's been working on support registered buffers with
> readv/writev.
> 
>> I dimly recall that I also ran into some around using fixed buffers as a
>> non-root user. It might just be the accounting of registered buffers as
>> mlocked memory and the difficulty of configuring that across
>> distributions. But I unfortunately don't remember any details anymore.
> 
> Should just be accounting.

For hugetlb we might be able to relax the accounting restriction. It's 
effectively mlocked already, and setting up hugetlb requires privileges.

-- 
Cheers,

David / dhildenb