From: Barret Rhoden <brho@google.com>
To: Christopher Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>,
Eial Czerwacki <eial@scalemp.com>,
tj@kernel.org, linux-kernel@vger.kernel.org,
Shai Fultheim <shai@scalemp.com>, Oren Twaig <oren@scalemp.com>,
"Paul E. McKenney" <paulmck@linux.ibm.com>
Subject: Re: [PATCH] percpu/module resevation: change resevation size iff X86_VSMP is set
Date: Wed, 13 Mar 2019 15:40:04 -0400 [thread overview]
Message-ID: <85726648-82f3-6b6b-a749-03c4159e78f3@google.com> (raw)
In-Reply-To: <010001693b404440-248fa987-624c-4587-940b-56e2ed4226d9-000000@email.amazonses.com>
Hi -
On 03/01/2019 04:54 PM, Christopher Lameter wrote:
> On Fri, 1 Mar 2019, Barret Rhoden wrote:
>
>> I'm not familiar with VSMP - how bad is it to use L1 cache alignment instead
>> of 4K page alignment? Maybe some structures can use the smaller alignment?
>> Or maybe have VSMP require SRCU-using modules to be built-in?
>
> It is very expensive. VMSP exchanges 4K segments via RDMA between servers
> to build a large address space and run a kernel in the large address
> space. Using smaller segments can cause a lot of
> "cacheline" bouncing (meaning transfers of 4K segments back and forth
> between servers).
>
Given that these are large machines, would it be OK to statically
reserve 64K on them for modules' percpu data?
The bug that led me to here was from someone running on a non-VSMP
machine but had that config set. Perhaps we make it more clear in the
Kconfig option to not set it on other machines. That might make it less
likely anyone on a non-VSMP machine pays the 64K overhead.
Are there any other alternatives? Not using static SRCU in any code
that could be built as a module seems a little harsh.
Thanks,
Barret
next prev parent reply other threads:[~2019-03-13 19:40 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-21 11:47 [PATCH] percpu/module resevation: change resevation size iff X86_VSMP is set Eial Czerwacki
2019-01-30 10:33 ` Eial Czerwacki
2019-03-01 18:30 ` Barret Rhoden
2019-03-01 20:34 ` Dennis Zhou
2019-03-01 21:27 ` Barret Rhoden
2019-03-01 21:54 ` Christopher Lameter
2019-03-13 19:40 ` Barret Rhoden [this message]
2019-03-13 20:26 ` Tejun Heo
2019-03-13 21:22 ` Paul E. McKenney
2019-03-13 21:29 ` Tejun Heo
2019-03-13 23:11 ` Paul E. McKenney
2019-03-14 17:36 ` Tejun Heo
2019-03-14 22:19 ` Paul E. McKenney
2019-03-18 8:18 ` Eial Czerwacki
2019-03-18 14:27 ` Paul E. McKenney
2019-04-04 20:53 ` Christopher Lameter
2019-03-04 7:42 ` Eial Czerwacki
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=85726648-82f3-6b6b-a749-03c4159e78f3@google.com \
--to=brho@google.com \
--cc=cl@linux.com \
--cc=dennis@kernel.org \
--cc=eial@scalemp.com \
--cc=linux-kernel@vger.kernel.org \
--cc=oren@scalemp.com \
--cc=paulmck@linux.ibm.com \
--cc=shai@scalemp.com \
--cc=tj@kernel.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).