From: Thomas Monjalon <thomas@monjalon.net>
To: Ori Kam <orika@nvidia.com>, Guy Kaneti <guyk@marvell.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, Smadar Fuks <smadarf@marvell.com>,
Dovrat Zifroni <dovrat@marvell.com>,
Jerin Jacob Kollanukkaran <jerinj@marvell.com>
Subject: Re: [dpdk-dev] [EXT] Re: [PATCH v1] regexdev: add OOS capability definition
Date: Wed, 21 Oct 2020 09:53:48 +0200 [thread overview]
Message-ID: <1814836.qjuG4n952W@thomas> (raw)
In-Reply-To: <DM6PR18MB24108309B404573D722C6666D81C0@DM6PR18MB2410.namprd18.prod.outlook.com>
21/10/2020 09:39, Guy Kaneti:
> From: Ori Kam <orika@nvidia.com>
> > From: Guy Kaneti <guyk@marvell.com>
> > > From: Thomas Monjalon <thomas@monjalon.net>
> > > > 20/10/2020 10:16, guyk@marvell.com:
> > > > > From: Guy Kaneti <guyk@marvell.com>
> > > > >
> > > > > Add out of order scan capability to check PMD support for OOS.
> > > > >
> > > > > Signed-off-by: Guy Kaneti <guyk@marvell.com>
> > > > > ---
> > > > > --- a/lib/librte_regexdev/rte_regexdev.h
> > > > > +++ b/lib/librte_regexdev/rte_regexdev.h
> > > > > +#define RTE_REGEXDEV_CAPA_QUEUE_PAIR_OOS_F (1ULL << 22)
> > /**<
> > > > RegEx
> > > > > +device support out of order scan, this means the scan can be
> > > > > +retired
> > > >
> > > > s/support/supports/
> > >
> > > I followed the other RTE_REGEXDEV_CAPA_ definitions I can fix it here
> > >
> > > >
> > > > What means "retired"?
> > >
> > > This was the original description in the rte_regexdev.h:
> > >
> > > #define RTE_REGEX_QUEUE_PAIR_CFG_OOS_F (1ULL << 0) /**< Out of
> > order
> > > scan, If not set, a scan must retire after previously issued
> > > * in-order scans to this queue pair. If set, this scan can be retired
> > > as soon
> > > * as device returns completion. Application should not set out of
> > > order scan
> > > * flag if it needs to maintain the ingress order of scan request.
> > >
> > I agree with Thomas, it is not very clear, The idea was to show that a scan can
> > return a result From newer job/search on a specific queue before a previous
> > job on the same queue is completed.
>
> How about this description:
>
> /**< RegEx device supports out of order scan.
> * Out of order scan means the response of a specific job can be returned as
> * soon as it is ready even if previous jobs on the same queue didn't complete.
A lot better :)
Thanks
next prev parent reply other threads:[~2020-10-21 7:54 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-20 8:16 [dpdk-dev] " guyk
2020-10-20 9:11 ` Ori Kam
2020-10-20 12:37 ` Thomas Monjalon
2020-10-20 14:24 ` [dpdk-dev] [EXT] " Guy Kaneti
2020-10-21 7:15 ` Ori Kam
2020-10-21 7:39 ` Guy Kaneti
2020-10-21 7:53 ` Thomas Monjalon [this message]
2020-10-21 8:03 ` [dpdk-dev] [PATCH v2] " guyk
2020-10-21 9:17 ` Ori Kam
2020-10-27 9:19 ` Guy Kaneti
2020-11-03 0:35 ` 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=1814836.qjuG4n952W@thomas \
--to=thomas@monjalon.net \
--cc=dev@dpdk.org \
--cc=dovrat@marvell.com \
--cc=guyk@marvell.com \
--cc=jerinj@marvell.com \
--cc=orika@nvidia.com \
--cc=smadarf@marvell.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).