From: Hemant Agrawal <hemant.agrawal@nxp.com>
To: "santosh.shukla@caviumnetworks.com"
<santosh.shukla@caviumnetworks.com>,
"dev@dpdk.org" <dev@dpdk.org>
Cc: "jerin.jacob@caviumnetworks.com" <jerin.jacob@caviumnetworks.com>,
"olivier.matz@6wind.com" <olivier.matz@6wind.com>,
Nipun Gupta <nipun.gupta@nxp.com>
Subject: Re: [dpdk-dev] [PATCH FIX-OPTION-1] mbuf: fix the logic of user mempool ops API
Date: Sun, 4 Feb 2018 10:27:22 +0000 [thread overview]
Message-ID: <AM2PR04MB0753EC30A74FD7A1D533D74889FF0@AM2PR04MB0753.eurprd04.prod.outlook.com> (raw)
In-Reply-To: <0e0099bc-99f5-bd41-cc53-b0ea9ded2f53@caviumnetworks.com>
Thanks we also identified it. The fix is on the way.
Sent from my Android phone using TouchDown (www.symantec.com)
-----Original Message-----
From: santosh [santosh.shukla@caviumnetworks.com]
Received: Sunday, 04 Feb 2018, 12:05PM
To: Hemant Agrawal [hemant.agrawal@nxp.com]; dev [dev@dpdk.org]
CC: Olivier MATZ [olivier.matz@6wind.com]; Jerin Jacob [jerin.jacob@caviumnetworks.com]; Nipun Gupta [nipun.gupta@nxp.com]
Subject: Re: Fw: [PATCH FIX-OPTION-1] mbuf: fix the logic of user mempool ops API
Hi Hemant,
On Sunday 04 February 2018 11:52 AM, Shukla, Santosh wrote:
> The existing rte_eal_mbuf_default mempool ops can return the compile time
> default ops name if the user has not provided command line inputs for
> mempool ops name. It will break the logic of best mempool ops as it will
> never return platform hw mempool ops.
>
> This patch introduces a new API to just return the user mempool ops only.
>
> Fixes: 8b0f7f434132 ("mbuf: maintain user and compile time mempool ops name")
>
> Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
> ---
This patch introduces regression for octeontx platform.
Fails with:
---------
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=163456, size=2176, socket=0
testpmd: preferred mempool ops selected: dpaa
dpaa_mbuf_create_pool(): bman_new_pool() failed
EAL: Error - exiting with code: 1
----------
Command:
./testpmd -c 0xe00000 -n 4 -- --portmask 0x1 --nb-cores=2 --port-topology=loop --rxq=2 --txq=2 --rss-ip --no-flush-rx
-------------
It's because rte_dpaa_bus_probe() sets platform mempool ops
i.e. rte_mbuf_set_platform_mempool_ops(DPAA_MEMPOOL_OPS_NAME);
therefore `rte_mbuf_best_mempool_ops` returns with `dpaa` ops which
is incorrect mempool_ops choice for octeontx platform.
We can fix such regression with following ways:
# option 1) unset LIBRTE_DPAA_MEMPOOL=y from common_armv8a_linuxapp config and
set at dpaa/dpaa2 specific configs
commit: 1ee9569576f6 ("config: enable dpaaX drivers for generic ARMv8")
# option 2) Don;t set platform mempool ops in dpaa bus layer instead defer it
to driver layer.
Thanks.
next prev parent reply other threads:[~2018-02-04 10:27 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-01 19:47 [dpdk-dev] [PATCH 1/2] Revert "eal: fix default mempool ops" Hemant Agrawal
2018-02-01 19:47 ` [dpdk-dev] [PATCH 2/2] test: use the best mempool ops API to get mbuf pool Hemant Agrawal
2018-02-01 19:56 ` [dpdk-dev] [PATCH 1/2] Revert "eal: fix default mempool ops" Hemant Agrawal
2018-02-01 20:40 ` Pavan Nikhilesh
2018-02-02 5:43 ` Hemant Agrawal
2018-02-02 8:03 ` [dpdk-dev] [PATCH FIX-OPTION-2 1/2] eal: use named memzone to store user mempool ops name Hemant Agrawal
2018-02-02 8:03 ` [dpdk-dev] [PATCH FIX-OPTION-1] mbuf: fix the logic of user mempool ops API Hemant Agrawal
2018-02-02 13:40 ` Olivier Matz
2018-02-02 13:47 ` Hemant Agrawal
2018-02-06 0:05 ` Thomas Monjalon
[not found] ` <BY1PR0701MB1895B37B913A223180EED6D3EAFF0@BY1PR0701MB1895.namprd07.prod.outlook.com>
2018-02-04 6:34 ` [dpdk-dev] Fw: " santosh
2018-02-04 10:27 ` Hemant Agrawal [this message]
2018-02-02 8:03 ` [dpdk-dev] [PATCH FIX-OPTION-2 2/2] mbuf: fix user mempool ops get to use only named memzone Hemant Agrawal
2018-02-02 8:03 ` [dpdk-dev] [PATCH] doc: remove eal API for default mempool ops name Hemant Agrawal
2018-02-02 8:31 ` [dpdk-dev] [PATCH v2] " Hemant Agrawal
2018-02-02 14:01 ` Olivier Matz
2018-02-13 11:28 ` Ferruh Yigit
2018-02-14 14:58 ` Thomas Monjalon
2018-02-03 13:28 ` Jerin Jacob
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=AM2PR04MB0753EC30A74FD7A1D533D74889FF0@AM2PR04MB0753.eurprd04.prod.outlook.com \
--to=hemant.agrawal@nxp.com \
--cc=dev@dpdk.org \
--cc=jerin.jacob@caviumnetworks.com \
--cc=nipun.gupta@nxp.com \
--cc=olivier.matz@6wind.com \
--cc=santosh.shukla@caviumnetworks.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).