Re: tmpfs loses (sub-page chunks of) data?

On 17/11/2024 04:10, Konstantin Belousov wrote:
> On Sat, Nov 16, 2024 at 02:31:25PM +0200, Andriy Gapon wrote:
>> I think  that mmap is not involved at all.
>> Files are written from kernel using kern_writev().
> Why?

Why from kernel or why kern_writev?
That's how our appliance works.

>> After they are complete, they are read from userland using whatever libssl
>> uses to read input files (when encrypting).  Looks like that's fread(3) /
>> read(2).
> 
> Try to reproduce it on the HEAD kernel.
> Then, turn off swap and see if it is still there.
> On HEAD, if reproducable without swap, try to add 'pgread' option to the
> tmpfs moount.
> 
> I am interested if the issue persists after all the measures listed above.

Switching the systems where the problem happens to HEAD would be very 
nontrivial, unfortunately.
I can experiment with swap and pgread much more easily.

Thank you for suggestions.

-- 
Andriy Gapon