From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: Asaf Sinai <AsafSi@Radware.com>, "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES: no difference in memory pool allocations, when enabling/disabling this configuration
Date: Mon, 26 Nov 2018 11:09:58 +0000 [thread overview]
Message-ID: <2b09cec8-0883-2ed2-0264-aeef871ea6a9@intel.com> (raw)
In-Reply-To: <DB7PR01MB4635B4B0B14F9CD1C135F3C1CCD70@DB7PR01MB4635.eurprd01.prod.exchangelabs.com>
On 26-Nov-18 9:15 AM, Asaf Sinai wrote:
> Hi,
>
> We have 2 NUMAs in our system, and we try to allocate a single DPDK memory pool on each NUMA.
> However, we see no difference when enabling/disabling "CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES" configuration.
> We expected that disabling it will allocate pools only on one NUMA (probably NUMA0), but it actually allocates pools on both NUMAs, according to "socket_id" parameter passed to "rte_mempool_create" API.
> We have 192GB memory, so NUMA1 memory starts from address: 0x1800000000.
> As you can see below, "undDpdkPoolNameSocket_1" was indeed allocated on NUMA1, as we wanted, although "CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES" is disabled:
>
> CONFIG_RTE_LIBRTE_VHOST_NUMA=n
> CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=n
>
> created poolName=undDpdkPoolNameSocket_0, nbufs=887808, bufferSize=2432, total=2059MB
> (memZone: name=MP_undDpdkPoolNameSocket_0, socket_id=0, vaddr=0x1f2c0427d00-0x1f2c05abe00, paddr=0x178e627d00-0x178e7abe00, len=1589504, hugepage_sz=2MB)
> created poolName=undDpdkPoolNameSocket_1, nbufs=887808, bufferSize=2432, total=2059MB
> (memZone: name=MP_undDpdkPoolNameSocket_1, socket_id=1, vaddr=0x1f57fa7be40-0x1f57fbfff40, paddr=0x2f8247be40-0x2f825fff40, len=1589504, hugepage_sz=2MB)
>
> Does anyone know what is "CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES" configuration used for?
>
> Thanks,
> Asaf
>
Hi Asaf,
I cannot reproduce this behavior. Just tried running testpmd with DPDK
18.08 as well as latest master [1], and DPDK could not successfully
allocate a mempool on socket 1.
Did you reconfigure and recompile DPDK after this config change?
[1] Latest master will crash on init in this configuration, fix:
http://patches.dpdk.org/patch/48338/
--
Thanks,
Anatoly
next prev parent reply other threads:[~2018-11-26 11:10 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-26 9:15 Asaf Sinai
2018-11-26 11:09 ` Burakov, Anatoly [this message]
2018-11-26 11:33 ` Asaf Sinai
2018-11-26 11:43 ` Burakov, Anatoly
2018-11-26 12:50 ` Burakov, Anatoly
2018-11-26 13:16 ` Ilya Maximets
2018-11-26 13:20 ` Ilya Maximets
2018-11-26 13:42 ` Burakov, Anatoly
2018-11-26 14:10 ` Ilya Maximets
2018-11-26 14:21 ` Burakov, Anatoly
2018-11-26 14:32 ` Ilya Maximets
2018-11-26 14:57 ` Burakov, Anatoly
2018-11-26 15:25 ` Asaf Sinai
2018-11-27 10:26 ` Hemant Agrawal
2018-11-27 10:33 ` Burakov, Anatoly
2018-11-27 16:49 ` Ilya Maximets
2018-12-09 8:14 ` Asaf Sinai
2018-12-10 10:09 ` Burakov, Anatoly
2018-12-16 9:44 ` Asaf Sinai
[not found] ` <CGME20181126122321eucas1p1c8bfe7e1b74fc5cd71eec3a3c8929f5d@eucas1p1.samsung.com>
2018-11-26 12:23 ` [dpdk-dev] CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES: no difference in memory pool allocations Ilya Maximets
2018-11-26 12:46 ` Ilya Maximets
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=2b09cec8-0883-2ed2-0264-aeef871ea6a9@intel.com \
--to=anatoly.burakov@intel.com \
--cc=AsafSi@Radware.com \
--cc=dev@dpdk.org \
/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).