From mboxrd@z Thu Jan 1 00:00:00 1970 From: Li Wang Subject: [PATCH] iputils: multiply sndbuf size by sending icmp times Date: Wed, 3 Dec 2014 10:58:51 +0800 Message-ID: <1417575531-12856-1-git-send-email-li.wang@windriver.com> Mime-Version: 1.0 Content-Type: text/plain To: , Return-path: Received: from mail1.windriver.com ([147.11.146.13]:34804 "EHLO mail1.windriver.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750927AbaLCC7H (ORCPT ); Tue, 2 Dec 2014 21:59:07 -0500 Sender: netdev-owner@vger.kernel.org List-ID: $ ping -i 0.1 198.168.5.200 -W 1 PING 128.224.124.76 (128.224.124.76) 56(84) bytes of data. ping: sendmsg: No buffer space available >>From 128.224.124.205 icmp_seq=1 Destination Host Unreachable when ping a non-exist IP with same subnet, ping will send arp packet, at first. there is a limitation for arp packet of same ping. for linux-2.6, the arp packet of number is 3. so, the size of limitation is (3*sizeof(arp packet)). for linux-3.x, the arp packet of size is 64k. so, it maybe exceed the sock of sndbuf. the linux kernel impoves the limitation. when customer use "-i 0.1 -W 1" option, it will send 20 icmp packets. at the same time, it send 20 arp packets. it does not exceed the limitation of linux-3.x, but, it exceeds the sock sndbuf of ping(324): setsockopt(3, SOL_SOCKET, SO_SNDBUF, [324], 4) = 0 so, auto-resize sndbuf according to the arp packet number. Signed-off-by: Li Wang --- ping.c | 1 + ping6.c | 1 + 2 files changed, 2 insertions(+) diff --git a/ping.c b/ping.c index c0366cd..46ca6df 100644 --- a/ping.c +++ b/ping.c @@ -531,6 +531,7 @@ main(int argc, char **argv) * Actually, for small datalen's it depends on kernel side a lot. */ hold = datalen + 8; hold += ((hold+511)/512)*(optlen + 20 + 16 + 64 + 160); + hold *= lingertime/SCHINT(interval/2); sock_setbufs(icmp_sock, hold); if (broadcast_pings) { diff --git a/ping6.c b/ping6.c index 6d83462..58843a9 100644 --- a/ping6.c +++ b/ping6.c @@ -1086,6 +1086,7 @@ int main(int argc, char *argv[]) * Actually, for small datalen's it depends on kernel side a lot. */ hold = datalen+8; hold += ((hold+511)/512)*(40+16+64+160); + hold *= lingertime/SCHINT(interval/2); sock_setbufs(icmp_sock, hold); #ifdef __linux__ -- 1.7.9.5