From: David Ahern <dsahern@gmail.com>
To: Eric Dumazet <edumazet@google.com>,
Stephen Hemminger <stephen@networkplumber.org>
Cc: netdev <netdev@vger.kernel.org>,
Eric Dumazet <eric.dumazet@gmail.com>,
Hangbin Liu <liuhangbin@gmail.com>, Phil Sutter <phil@nwl.cc>
Subject: Re: [PATCH iproute2] lib/libnetlink: ensure a minimum of 32KB for the buffer used in rtnl_recvmsg()
Date: Tue, 12 Feb 2019 19:04:17 -0700 [thread overview]
Message-ID: <b42f0dcb-3c8c-9797-a9f1-da71642e26cc@gmail.com> (raw)
In-Reply-To: <20190213015841.140383-1-edumazet@google.com>
On 2/12/19 6:58 PM, Eric Dumazet wrote:
> In the past, we tried to increase the buffer size up to 32 KB in order
> to reduce number of syscalls per dump.
>
> Commit 2d34851cd341 ("lib/libnetlink: re malloc buff if size is not enough")
> brought the size back to 4KB because the kernel can not know the application
> is ready to receive bigger requests.
>
> See kernel commits 9063e21fb026 ("netlink: autosize skb lengthes") and
> d35c99ff77ec ("netlink: do not enter direct reclaim from netlink_dump()")
> for more details.
>
> Fixes: 2d34851cd341 ("lib/libnetlink: re malloc buff if size is not enough")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: Hangbin Liu <liuhangbin@gmail.com>
> Cc: Phil Sutter <phil@nwl.cc>
> ---
> lib/libnetlink.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/lib/libnetlink.c b/lib/libnetlink.c
> index 1892a02ab5d0d73776c9882ffc77edcd2c663d01..0d48a3d43cf03065dacbd419578ab10af56431a4 100644
> --- a/lib/libnetlink.c
> +++ b/lib/libnetlink.c
> @@ -718,6 +718,8 @@ static int rtnl_recvmsg(int fd, struct msghdr *msg, char **answer)
> if (len < 0)
> return len;
>
> + if (len < 32768)
> + len = 32768;
> buf = malloc(len);
> if (!buf) {
> fprintf(stderr, "malloc error: not enough buffer\n");
>
I believe that negates the whole point of 2d34851cd341 - which I have no
problem with. 2 recvmsg calls per message is overkill.
Do we know of any single message sizes > 32k? 2d34851cd341 cites
increasing VF's but at some point there is a limit. If not, the whole
PEEK thing should go away and we just malloc 32k (or 64k) buffers for
each recvmsg.
next prev parent reply other threads:[~2019-02-13 2:04 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-13 1:58 [PATCH iproute2] lib/libnetlink: ensure a minimum of 32KB for the buffer used in rtnl_recvmsg() Eric Dumazet
2019-02-13 2:04 ` David Ahern [this message]
2019-02-13 2:08 ` Eric Dumazet
2019-02-13 6:20 ` Hangbin Liu
2019-02-14 13:51 ` Michal Kubecek
2019-02-14 13:49 ` Michal Kubecek
2019-02-14 17:34 ` David Ahern
2019-02-14 17:47 ` Phil Sutter
2023-05-29 12:29 ` Gal Pressman
2023-05-31 21:51 ` Stephen Hemminger
2023-06-04 13:33 ` Gal Pressman
2023-06-04 16:03 ` David Ahern
2023-06-05 7:24 ` Gal Pressman
2019-02-13 17:46 ` Phil Sutter
2019-02-13 17:58 ` Eric Dumazet
2019-02-13 21:57 ` Stephen Hemminger
2019-02-13 21:59 ` Eric Dumazet
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=b42f0dcb-3c8c-9797-a9f1-da71642e26cc@gmail.com \
--to=dsahern@gmail.com \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=liuhangbin@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=phil@nwl.cc \
--cc=stephen@networkplumber.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).