From: Adrien Mazarguil <adrien.mazarguil@6wind.com>
To: Keith Wiles <keith.wiles@intel.com>
Cc: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 1/2] net/tap: remove redundant syscall on Tx
Date: Tue, 14 Mar 2017 13:51:57 +0100 [thread overview]
Message-ID: <f8b03c0556b9d7adad14058b5f8c4af26be6d504.1489495663.git.adrien.mazarguil@6wind.com> (raw)
Polling the Tx queue file descriptor before writing to it is not mandatory
since it is configured as non-blocking.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Pascal Mazon <pascal.mazon@6wind.com>
---
drivers/net/tap/rte_eth_tap.c | 26 ++++++++------------------
1 file changed, 8 insertions(+), 18 deletions(-)
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index efc4426..c757a7c 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -43,7 +43,6 @@
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <unistd.h>
-#include <poll.h>
#include <arpa/inet.h>
#include <linux/if.h>
#include <linux/if_tun.h>
@@ -242,7 +241,6 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
struct rte_mbuf *mbuf;
struct tx_queue *txq = queue;
- struct pollfd pfd;
uint16_t num_tx = 0;
unsigned long num_tx_bytes = 0;
int i, n;
@@ -250,26 +248,18 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
if (unlikely(nb_pkts == 0))
return 0;
- pfd.events = POLLOUT;
- pfd.fd = txq->fd;
for (i = 0; i < nb_pkts; i++) {
- n = poll(&pfd, 1, 0);
-
+ /* copy the tx frame data */
+ mbuf = bufs[num_tx];
+ n = write(txq->fd,
+ rte_pktmbuf_mtod(mbuf, void *),
+ rte_pktmbuf_pkt_len(mbuf));
if (n <= 0)
break;
- if (pfd.revents & POLLOUT) {
- /* copy the tx frame data */
- mbuf = bufs[num_tx];
- n = write(pfd.fd, rte_pktmbuf_mtod(mbuf, void*),
- rte_pktmbuf_pkt_len(mbuf));
- if (n <= 0)
- break;
-
- num_tx++;
- num_tx_bytes += mbuf->pkt_len;
- rte_pktmbuf_free(mbuf);
- }
+ num_tx++;
+ num_tx_bytes += mbuf->pkt_len;
+ rte_pktmbuf_free(mbuf);
}
txq->stats.opackets += num_tx;
--
2.1.4
next reply other threads:[~2017-03-14 12:52 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-14 12:51 Adrien Mazarguil [this message]
2017-03-14 12:51 ` [dpdk-dev] [PATCH 2/2] net/tap: add Rx trigger Adrien Mazarguil
2017-03-14 13:57 ` Wiles, Keith
2017-03-14 13:52 ` [dpdk-dev] [PATCH 1/2] net/tap: remove redundant syscall on Tx Wiles, Keith
2017-03-14 17:04 ` Ferruh Yigit
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=f8b03c0556b9d7adad14058b5f8c4af26be6d504.1489495663.git.adrien.mazarguil@6wind.com \
--to=adrien.mazarguil@6wind.com \
--cc=dev@dpdk.org \
--cc=keith.wiles@intel.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).