On Wed, May 25, 2016 at 5:21 PM, Kirill A. Shutemov [off-list ref]
wrote:

On Wed, May 25, 2016 at 05:11:03PM -0400, neha agarwal wrote:

quoted

On Wed, May 25, 2016 at 4:03 PM, Kirill A. Shutemov <

kirill@shutemov.name>

quoted

wrote:

quoted

On Wed, May 25, 2016 at 03:11:55PM -0400, neha agarwal wrote:

quoted

Hi All,

I have been testing Hugh's and Kirill's huge tmpfs patch sets with
Cassandra (NoSQL database). I am seeing significant performance gap

between

quoted

these two implementations (~30%). Hugh's implementation performs

better

quoted

quoted

quoted

than Kirill's implementation. I am surprised why I am seeing this
performance gap. Following is my test setup.

Thanks for the report. I'll look into it.

Thanks Kirill for looking into it.

quoted

quoted

Patchsets
========
- For Hugh's:
I checked out 4.6-rc3, applied Hugh's preliminary patches (01 to 10
patches) from here: https://lkml.org/lkml/2016/4/5/792 and then

applied

quoted

quoted

the

quoted

THP patches posted on April 16 (01 to 29 patches).

- For Kirill's:
I am using his branch  "git://
git.kernel.org/pub/scm/linux/kernel/git/kas/linux.git hugetmpfs/v8",

which

quoted

is based off of 4.6-rc3, posted on May 12.


Khugepaged settings
================
cd /sys/kernel/mm/transparent_hugepage
echo 10 >khugepaged/alloc_sleep_millisecs
echo 10 >khugepaged/scan_sleep_millisecs
echo 511 >khugepaged/max_ptes_none

Do you make this for both setup?

It's not really nessesary for Hugh's, but it makes sense to have this
idenatical for testing.

Yeah right, Hugh's will not be impacted by these settings but for

identical

quoted

testing I did that.

Could you try to drop this changes and leave khugepaged with defaults.

With default khugepaged options also, the performance difference between
the two implementation remains as before.

One theory is that you just create additional load on the system without
any gain. As pages wasn't swapped out we have nothing to collapse back,
but scanning takes CPU time.

Since the performance difference is still there with default khugepaged
settings, probably khugepaged is not the culprit here.

Hugh didn't change khugepaged, so it would not need to look into tmpfs
mapping to check if there's something to collapse...

--
 Kirill A. Shutemov

-- 
Thanks and Regards,
Neha