From: Tyler Retzlaff <roretzla@linux.microsoft.com>
To: Bruce Richardson <bruce.richardson@intel.com>
Cc: Volodymyr Fialko <vfialko@marvell.com>,
dev@dpdk.org, Reshma Pattan <reshma.pattan@intel.com>,
jerinj@marvell.com, anoobj@marvell.com
Subject: Re: [PATCH] reorder: improve buffer structure layout
Date: Fri, 14 Apr 2023 10:07:16 -0700 [thread overview]
Message-ID: <20230414170716.GB10264@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net> (raw)
In-Reply-To: <ZDkcQvvUFEH26gpQ@bricha3-MOBL.ger.corp.intel.com>
On Fri, Apr 14, 2023 at 10:26:26AM +0100, Bruce Richardson wrote:
> On Fri, Apr 14, 2023 at 10:43:43AM +0200, Volodymyr Fialko wrote:
> > Rearrange the reorder buffer structure to prevent padding to extra one
> > cache line.
> >
> > Current layout:
> > struct rte_reorder_buffer {
> > char name[RTE_REORDER_NAMESIZE];
> > uint32_t min_seqn;
> > unsigned int memsize;
> > // -> padding to cache align (cir_buffer is also cache aligned)
> > struct cir_buffer ready_buf;
> > struct cir_buffer order_buf;
> > int is_initialized;
> > // -> padding to cache align, eat whole line
> > };
> >
> > New layout:
> > struct rte_reorder_buffer {
> > char name[RTE_REORDER_NAMESIZE];
> > uint32_t min_seqn;
> > unsigned int memsize;
> > int is_initialized;
> > // -> padding to cache align (cir_buffer is also cache aligned)
> > struct cir_buffer ready_buf;
> > struct cir_buffer order_buf;
> > // -> no padding
> > };
> >
> > Signed-off-by: Volodymyr Fialko <vfialko@marvell.com>
> > ---
>
> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
>
> > lib/reorder/rte_reorder.c | 3 ++-
> > 1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/lib/reorder/rte_reorder.c b/lib/reorder/rte_reorder.c
> > index f55f383700..7418202b04 100644
> > --- a/lib/reorder/rte_reorder.c
> > +++ b/lib/reorder/rte_reorder.c
> > @@ -46,9 +46,10 @@ struct rte_reorder_buffer {
> > char name[RTE_REORDER_NAMESIZE];
> > uint32_t min_seqn; /**< Lowest seq. number that can be in the buffer */
> > unsigned int memsize; /**< memory area size of reorder buffer */
> > + int is_initialized; /**< flag indicates that buffer was initialized */
> > +
>
> Since we are moving it, it might be an opportunity to change it from "int"
> to "bool".
+1
>
> > struct cir_buffer ready_buf; /**< temp buffer for dequeued entries */
> > struct cir_buffer order_buf; /**< buffer used to reorder entries */
> > - int is_initialized;
> > } __rte_cache_aligned;
> >
> > static void
> > --
> > 2.34.1
> >
next prev parent reply other threads:[~2023-04-14 17:07 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-14 8:43 Volodymyr Fialko
2023-04-14 9:26 ` Bruce Richardson
2023-04-14 17:07 ` Tyler Retzlaff [this message]
2023-04-14 14:52 ` Stephen Hemminger
2023-04-14 14:54 ` Bruce Richardson
2023-04-14 15:30 ` Stephen Hemminger
2023-04-17 9:12 ` [PATCH v2] " Volodymyr Fialko
2023-06-01 15:19 ` 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=20230414170716.GB10264@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net \
--to=roretzla@linux.microsoft.com \
--cc=anoobj@marvell.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=jerinj@marvell.com \
--cc=reshma.pattan@intel.com \
--cc=vfialko@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).