DPDK patches and discussions
 help / color / mirror / Atom feed
From: Li Feng <fengli@smartx.com>
To: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: lifeng1519@gmail.com, Kyle Zhang <kyle@smartx.com>, dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] eal: add madvise to avoid dump memory
Date: Mon, 20 Apr 2020 15:07:47 +0800	[thread overview]
Message-ID: <CAHckoCy_MwGRUGT7F2v3GbF3qv8+_-5XWp6G0+8QbkNwKKjZpg@mail.gmail.com> (raw)
In-Reply-To: <20200420070508.645533-1-fengli@smartx.com>

Add cc dev@dpdk.org

Thanks,

Feng Li

Li Feng <fengli@smartx.com> 于2020年4月20日周一 下午3:04写道:
>
> Avoid dump all mmapped memory to coredump file when crash.
> Otherwise it will very large and it's hard to analyze with gdb.
>
> In my test, it will dump 128GiB memory to coredump file when integrated
> to spdk with default configuration.
>
> Signed-off-by: Li Feng <fengli@smartx.com>
> ---
>  lib/librte_eal/common/eal_common_memory.c | 7 +++++++
>  1 file changed, 7 insertions(+)
>
> diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
> index cc7d54e0c..cc6743d56 100644
> --- a/lib/librte_eal/common/eal_common_memory.c
> +++ b/lib/librte_eal/common/eal_common_memory.c
> @@ -102,6 +102,13 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
>                 if (mapped_addr == MAP_FAILED && allow_shrink)
>                         *size -= page_sz;
>
> +               if (mapped_addr != MAP_FAILED) {
> +                       if (madvise(mapped_addr, map_sz, MADV_DONTDUMP) != 0)
> +                               RTE_LOG(INFO, EAL, "MADV_DONTDUMP advice setting failed.\n");
> +                       RTE_LOG(DEBUG, EAL, "madvise with MADV_DONTDUMP, addr: %p size: %ld\n",
> +                               mapped_addr, (size_t)map_sz);
> +               }
> +
>                 if (mapped_addr != MAP_FAILED && addr_is_hint &&
>                     mapped_addr != requested_addr) {
>                         try++;
> --
> 2.11.0
>

-- 
The SmartX email address is only for business purpose. Any sent message 
that is not related to the business is not authorized or permitted by 
SmartX.
本邮箱为北京志凌海纳科技有限公司(SmartX)工作邮箱. 如本邮箱发出的邮件与工作无关,该邮件未得到本公司任何的明示或默示的授权.



       reply	other threads:[~2020-04-20  7:08 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20200420070508.645533-1-fengli@smartx.com>
2020-04-20  7:07 ` Li Feng [this message]
2020-04-20  7:13   ` David Marchand
2020-04-20  9:40     ` Feng Li
2020-04-21  7:41       ` David Marchand
2020-04-21 11:06         ` Feng Li
2020-04-21 12:19           ` Burakov, Anatoly
2020-04-21 16:38             ` Feng Li
2020-04-21 17:02               ` Burakov, Anatoly
2020-04-22  3:13                 ` Li Feng
2020-04-22  9:53                   ` Burakov, Anatoly
     [not found]                     ` <CAEK8JBCdfZJiKNjDNgC9nDGLni9Dvw+U1doRFnh+zkAs5TXEsg@mail.gmail.com>
2020-04-23 12:22                       ` Burakov, Anatoly
2020-04-23 15:43 ` [dpdk-dev] [PATCH v2] " Li Feng
2020-04-23 16:33   ` Burakov, Anatoly
2020-04-23 20:04     ` David Marchand
2020-04-24  9:12       ` Burakov, Anatoly
2020-04-24  9:14         ` Bruce Richardson
2020-04-24  9:33           ` Feng Li
2020-04-24 11:00             ` Burakov, Anatoly
2020-04-24 12:03               ` Li Feng

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=CAHckoCy_MwGRUGT7F2v3GbF3qv8+_-5XWp6G0+8QbkNwKKjZpg@mail.gmail.com \
    --to=fengli@smartx.com \
    --cc=anatoly.burakov@intel.com \
    --cc=dev@dpdk.org \
    --cc=kyle@smartx.com \
    --cc=lifeng1519@gmail.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).