All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jan Stancek <jstancek@redhat.com>
To: ltp@lists.linux.it
Subject: [LTP] [PATCH] kernel/numa01.sh: Remove file based tests
Date: Thu, 14 Mar 2019 04:54:48 -0400 (EDT)	[thread overview]
Message-ID: <1574820135.8166436.1552553688274.JavaMail.zimbra@redhat.com> (raw)
In-Reply-To: <20190313121242.5257-1-chrubis@suse.cz>



----- Original Message -----
> This is follow up on:
> 
> commit 55ee8a5adcf32d46372b32c0e470e42a82165c67
> Author: Cyril Hrubis <chrubis@suse.cz>
> Date:   Wed Mar 6 17:16:33 2019 +0100
> 
>     syscalls: Add set_mempolicy numa tests.
> 
> Tests 3 and 5 were using a single file mmaped into test memory to check
> NUMA allocation policy. Using a single small file for this kind of tests
> is wrong for several reasons, among other things filesystems tends to
> allocate pages in batches (to have better performance), which means that
> interleave policy has to sample several slightly larger files to check
> for fairness of the memory placements.
> 
> The testcase 5 was failing often on Btrfs and testcase 3 was failing
> rarely so this commit removes these two.
> 
> The test 3 is now reimplemented as subset of set_mempolicy03 the only
> difference is that test 3 tries to fiddle with cpu affinity to keep the
> test running on different node than is the one we requested allocation
> on but given that we try to allocate memory on all memory nodes it's
> unlikely that we will actually always run on the same node we want to
> allocate the memory on and if we ever wanted we can add another variant
> for the set_mempolicy03 test easily as well.
> 
> The test 5 is reimplemented as set_mempolicy04 with the difference that
> set_mempolicy04 runs on all supported filesystems and samples several
> files as well.
> 
> Signed-off-by: Cyril Hrubis <chrubis@suse.cz>

ack

  reply	other threads:[~2019-03-14  8:54 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-13 12:12 [LTP] [PATCH] kernel/numa01.sh: Remove file based tests Cyril Hrubis
2019-03-14  8:54 ` Jan Stancek [this message]
2019-03-14  9:18   ` Cyril Hrubis

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1574820135.8166436.1552553688274.JavaMail.zimbra@redhat.com \
    --to=jstancek@redhat.com \
    --cc=ltp@lists.linux.it \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.