From: "Richardson, Bruce" <bruce.richardson@intel.com>
To: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>,
"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads to lcore 0
Date: Fri, 12 Sep 2014 08:07:12 +0000 [thread overview]
Message-ID: <59AF69C657FD0841A61C55336867B5B0343F0F16@IRSMSX103.ger.corp.intel.com> (raw)
In-Reply-To: <7F861DC0615E0C47A872E6F3C5FCDDBD011AC7A6@BPXM14GP.gisp.nec.co.jp>
> -----Original Message-----
> From: Hiroshi Shimamoto [mailto:h-shimamoto@ct.jp.nec.com]
> Sent: Friday, September 12, 2014 12:48 AM
> To: Richardson, Bruce; dev@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads to lcore 0
>
> Hi Bruce,
>
> > Subject: [dpdk-dev] [PATCH 0/3] eal affinitize low priority threads to lcore 0
> >
> > This patchset sets things up so that we can affinitize the interrupt,
> > vfio management, and hpet timer management threads to lcore 0, so that
> > they never interfere with data plane threads.
>
> I don't think it works well always.
> The management threads can be floating all cpus on demand, because those
> threads are created before the master thread affinity is set. The kernel
> scheduler will take care of it. And we should isolate cpus which data plane
> threads are pinned to, so the management threads cannot run on those isolated
> cpus data plane thread run.
Yes, this was my understanding as well of how things would work - we just had a report back of where the management threads were using the same core as the data-plane despite the core being isolated. I'll double-check to see if this really is happening and resubmit a new patch with a configurable core assignment if it is definitely needed.
/Bruce
> In some cases, the user may run data plane thread on lcore 0, but with
> this patchset the data plane pinned to lcore 0 always run with the
> management threads. That doesn't seem good.
>
> I think this functionality should be conditional.
> How about to add a parameter to specify the mask for the management threads
> instead of statically assignment to lcore 0?
>
> thanks,
> Hiroshi
>
> >
> > Bruce Richardson (3):
> > eal: add core id param to eal_thread_set_affinity
> > eal: increase scope of eal_thread_set_affinity
> > eal: affinitize low-priority threads to lcore 0
> >
> > lib/librte_eal/bsdapp/eal/eal_thread.c | 12 ++++++------
> > lib/librte_eal/common/include/eal_private.h | 10 ++++++++++
> > lib/librte_eal/linuxapp/eal/eal_interrupts.c | 5 +++++
> > lib/librte_eal/linuxapp/eal/eal_pci_vfio_mp_sync.c | 6 ++++++
> > lib/librte_eal/linuxapp/eal/eal_thread.c | 12 ++++++------
> > lib/librte_eal/linuxapp/eal/eal_timer.c | 5 +++++
> > 6 files changed, 38 insertions(+), 12 deletions(-)
> >
> > --
> > 1.9.3
prev parent reply other threads:[~2014-09-12 8:02 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1410445387-4849-1-git-send-email-bruce.richardson@intel.com>
2014-09-11 14:23 ` [dpdk-dev] [PATCH 1/3] eal: add core id param to eal_thread_set_affinity Bruce Richardson
2014-09-11 14:23 ` [dpdk-dev] [PATCH 2/3] eal: increase scope of eal_thread_set_affinity Bruce Richardson
2014-09-11 14:23 ` [dpdk-dev] [PATCH 3/3] eal: affinitize low-priority threads to lcore 0 Bruce Richardson
2014-09-11 23:47 ` [dpdk-dev] [PATCH 0/3] eal affinitize low priority " Hiroshi Shimamoto
2014-09-12 1:24 ` Stephen Hemminger
2014-09-12 8:07 ` Richardson, Bruce [this message]
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=59AF69C657FD0841A61C55336867B5B0343F0F16@IRSMSX103.ger.corp.intel.com \
--to=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=h-shimamoto@ct.jp.nec.com \
/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).