quoted

quoted

quoted

Yeah, I'm more interested in some reasonable value, now the default is
2048 but probably it should be sectorsize/2 in general.

Half of sectorsize is pretty solid to me.

But I'm afraid this is a little too late, especially considering we're
moving to 4K sectorsize as default for all page sizes.

I am writing a patch to autotune it to sectorsize/2 by default.

That would be pretty good.

quoted

To test this, we need to have a filesystem with file sizes of various
sizes (so that we have both inline and regular extents) and run rw. It
looks like no regular workload (fio/sysbench) can do that and, I am
stuck on that. Any inputs?

Is that a performance benchmark or just function tests?

For the former one, I guess you can specific the file sizes for
fio/sysbench.

  Right. Performance benchmark.
  I just found, in fio, you can specify a range for the filesize, which I
  am planning to specify 1K to 10K as it is the most common file size in
  a Linux root fs.

  sysbench does not allow to specify a range of file sizes.

For the latter part, it's pretty simple, just write a bunch of files
with different sizes, and use fiemap to check their block range.

Inline extents should report block range the same as their file offset.

  I didn't have a plan of writing a functional test case for this,
  but now I am reconsidering.

Thanks, Anand

Thanks,
Qu

quoted

quoted

quoted

quoted

quoted

Please fix/reformat/improve any comments that are in moved code.

   I think you are pointing to s/f/F and 80 chars long? Will fix.

Yes, already fixed in the committed version in misc-next, thanks.

  Thanks.

- Anand