From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: Nick Connolly <nick.connolly@mayadata.io>
Cc: dev@dpdk.org, nicolas.dichtel@6wind.com, stable@dpdk.org
Subject: Re: [dpdk-stable] [PATCH] mem: fix allocation failure on non-NUMA kernel
Date: Thu, 17 Sep 2020 12:31:57 +0100 [thread overview]
Message-ID: <be6c5f8d-aaca-5a73-3fff-03febb3533ad@intel.com> (raw)
In-Reply-To: <20200805122640.13884-1-nick.connolly@mayadata.io>
On 05-Aug-20 1:26 PM, Nick Connolly wrote:
> Running dpdk-helloworld on Linux with lib numa present,
> but no kernel support for NUMA (CONFIG_NUMA=n) causes
> ret_service_init() to fail with EAL: error allocating
> rte services array.
>
> alloc_seg() calls get_mempolicy to verify that the allocation
> has happened on the correct socket, but receives ENOSYS from
> the kernel and fails the allocation.
>
> The allocated socket should only be verified if check_numa() is true.
>
> Fixes: 2a96c88be83e ("mem: ease init in a docker container")
> Cc: nicolas.dichtel@6wind.com
> Cc: stable@dpdk.org
> Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
> ---
> lib/librte_eal/linux/eal_memalloc.c | 28 +++++++++++++++++-----------
> 1 file changed, 17 insertions(+), 11 deletions(-)
>
> diff --git a/lib/librte_eal/linux/eal_memalloc.c b/lib/librte_eal/linux/eal_memalloc.c
> index db60e7997..179757809 100644
> --- a/lib/librte_eal/linux/eal_memalloc.c
> +++ b/lib/librte_eal/linux/eal_memalloc.c
> @@ -610,17 +610,23 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
> }
>
> #ifdef RTE_EAL_NUMA_AWARE_HUGEPAGES
> - ret = get_mempolicy(&cur_socket_id, NULL, 0, addr,
> - MPOL_F_NODE | MPOL_F_ADDR);
> - if (ret < 0) {
> - RTE_LOG(DEBUG, EAL, "%s(): get_mempolicy: %s\n",
> - __func__, strerror(errno));
> - goto mapped;
> - } else if (cur_socket_id != socket_id) {
> - RTE_LOG(DEBUG, EAL,
> - "%s(): allocation happened on wrong socket (wanted %d, got %d)\n",
> - __func__, socket_id, cur_socket_id);
> - goto mapped;
> + if (check_numa()) {
> + ret = get_mempolicy(&cur_socket_id, NULL, 0, addr,
> + MPOL_F_NODE | MPOL_F_ADDR);
> + if (ret < 0) {
> + RTE_LOG(DEBUG, EAL, "%s(): get_mempolicy: %s\n",
> + __func__, strerror(errno));
> + goto mapped;
> + } else if (cur_socket_id != socket_id) {
> + RTE_LOG(DEBUG, EAL,
> + "%s(): allocation happened on wrong socket (wanted %d, got %d)\n",
> + __func__, socket_id, cur_socket_id);
> + goto mapped;
> + }
> + } else {
> + if (rte_socket_count() > 1)
> + RTE_LOG(DEBUG, EAL, "%s(): not checking socket for allocation (wanted %d)\n",
> + __func__, socket_id);
> }
If there is no kernel support for NUMA, how would we end up with >1
socket count?
> #else
> if (rte_socket_count() > 1)
>
--
Thanks,
Anatoly
next prev parent reply other threads:[~2020-09-17 11:32 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-05 12:26 Nick Connolly
2020-08-05 13:42 ` Nicolas Dichtel
2020-08-05 14:20 ` Nick Connolly
2020-08-05 14:36 ` Nicolas Dichtel
2020-08-05 14:53 ` Nick Connolly
2020-08-05 15:13 ` Nicolas Dichtel
2020-08-05 15:21 ` Nick Connolly
2020-09-17 11:28 ` Burakov, Anatoly
2020-09-17 11:31 ` Burakov, Anatoly [this message]
2020-09-17 12:29 ` Nick Connolly
2020-09-17 12:57 ` Burakov, Anatoly
2020-09-17 13:05 ` Nick Connolly
2020-09-17 14:07 ` Burakov, Anatoly
2020-09-17 14:08 ` Nick Connolly
2020-09-17 14:18 ` Burakov, Anatoly
2020-09-17 14:19 ` Nick Connolly
2020-10-12 19:28 ` [dpdk-stable] [PATCH v2] " Nick Connolly
2020-10-13 7:59 ` Nicolas Dichtel
2020-10-13 12:01 ` David Marchand
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=be6c5f8d-aaca-5a73-3fff-03febb3533ad@intel.com \
--to=anatoly.burakov@intel.com \
--cc=dev@dpdk.org \
--cc=nick.connolly@mayadata.io \
--cc=nicolas.dichtel@6wind.com \
--cc=stable@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).