From: Jerin Jacob Kollanukkaran <jerinj@marvell.com>
To: "thomas@monjalon.net" <thomas@monjalon.net>,
"bruce.richardson@intel.com" <bruce.richardson@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>,
"anatoly.burakov@intel.com" <anatoly.burakov@intel.com>
Subject: Re: [dpdk-dev] [EXT] Re: [PATCH v2] eal: make max interrupt vectors configurable
Date: Tue, 26 Mar 2019 15:57:48 +0000 [thread overview]
Message-ID: <5b16f07563e223d8cce5da68398f132c761d1f19.camel@marvell.com> (raw)
Message-ID: <20190326155748.XNW2r-3T2rwlrUifUBZ4QBycCQo52Ltmr2Bt-JWJ_Z4@z> (raw)
In-Reply-To: <20190326144317.GC472084@bricha3-MOBL.ger.corp.intel.com>
On Tue, 2019-03-26 at 14:43 +0000, Bruce Richardson wrote:
+ Anatoly
>
> -------------------------------------------------------------------
> ---
> On Tue, Mar 26, 2019 at 03:04:58PM +0100, Thomas Monjalon wrote:
> > 26/03/2019 14:21, Pavan Nikhilesh Bhagavatula:
> > > From: Pavan Nikhilesh <pbhagavatula@marvell.com>
> > >
> > > Make max interrupt vectors configurable so that platforms can
> > > choose interrupt vector limit.
> >
> > What is the impact of setting a big value?
> > Can we agree on a big enough value without introducing any config?
> >
> Is it a value that needs to be set differently per-platform, perhaps?
MSI supports 32 interrupts, MSI-X can allocate up to 2048 interrupt as
per the PCIe Spec.
In terms of cost, a few KB of memory in rte_intr_handle in structure
and more file handlers for vfio.
I think, We can move to reasonable numbers as 256 or 512 considering
the latest PCIe multi function devices will have enough interrupts.
And I don't think, it is a platform value as common config needs to
work for distro build which is using the base config. Marvell has PCIe
device which has 256 MSIX vectors, Not sure about other PCIe card.
next prev parent reply other threads:[~2019-03-26 15:57 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-26 12:54 [dpdk-dev] [PATCH] " Pavan Nikhilesh Bhagavatula
2019-03-26 12:54 ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:08 ` Jerin Jacob Kollanukkaran
2019-03-26 13:08 ` Jerin Jacob Kollanukkaran
2019-03-26 13:11 ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:11 ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:21 ` [dpdk-dev] [PATCH v2] " Pavan Nikhilesh Bhagavatula
2019-03-26 13:21 ` Pavan Nikhilesh Bhagavatula
2019-03-26 14:04 ` Thomas Monjalon
2019-03-26 14:04 ` Thomas Monjalon
2019-03-26 14:43 ` Bruce Richardson
2019-03-26 14:43 ` Bruce Richardson
2019-03-26 15:57 ` Jerin Jacob Kollanukkaran [this message]
2019-03-26 15:57 ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-03-31 14:55 ` [dpdk-dev] [PATCH v3] eal: increase max number of interrupt vectors Pavan Nikhilesh Bhagavatula
2019-03-31 14:55 ` Pavan Nikhilesh Bhagavatula
2019-04-02 12:32 ` Thomas Monjalon
2019-04-02 12:32 ` Thomas Monjalon
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=5b16f07563e223d8cce5da68398f132c761d1f19.camel@marvell.com \
--to=jerinj@marvell.com \
--cc=anatoly.burakov@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=pbhagavatula@marvell.com \
--cc=thomas@monjalon.net \
/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).