DPDK patches and discussions
 help / color / mirror / Atom feed
From: Balazs Nemeth <bnemeth@redhat.com>
To: bnemeth@redhat.com, dev@dpdk.org
Subject: [dpdk-dev] [PATCH 5/8] net/qede: use rte_pktmbuf_free_bulk instead of rte_pktmbuf_free
Date: Fri,  5 Mar 2021 14:14:03 +0100	[thread overview]
Message-ID: <c8ff6417ecd36116114b3889362500b6bf231499.1614938727.git.bnemeth@redhat.com> (raw)
In-Reply-To: <cover.1614938727.git.bnemeth@redhat.com>

rte_pktmbuf_free_bulk calls rte_mempool_put_bulk with the number of
pending packets to return to the mempool. In contrast, rte_pktmbuf_free
calls rte_mempool_put that calls rte_mempool_put_bulk with one object.
An important performance related downside of adding one packet at a time
to the mempool is that on each call, the per-core cache pointer needs to
be read from tls while a single rte_mempool_put_bulk only reads from the
tls once.

Signed-off-by: Balazs Nemeth <bnemeth@redhat.com>
---
 drivers/net/qede/qede_rxtx.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/qede/qede_rxtx.c b/drivers/net/qede/qede_rxtx.c
index 7ce4c00e3..e24a937f4 100644
--- a/drivers/net/qede/qede_rxtx.c
+++ b/drivers/net/qede/qede_rxtx.c
@@ -891,6 +891,7 @@ qede_process_tx_compl(__rte_unused struct ecore_dev *edev,
 	struct rte_mbuf *mbuf;
 	uint16_t nb_segs;
 	uint16_t idx;
+	uint16_t first_idx;
 
 	rte_compiler_barrier();
 	sw_tx_cons = ecore_chain_get_cons_idx(&txq->tx_pbl);
@@ -905,6 +906,7 @@ qede_process_tx_compl(__rte_unused struct ecore_dev *edev,
 
 	remaining = hw_bd_cons - sw_tx_cons;
 	txq->nb_tx_avail += remaining;
+	first_idx = idx;
 
 	while (remaining) {
 		mbuf = txq->sw_tx_ring[idx];
@@ -919,11 +921,17 @@ qede_process_tx_compl(__rte_unused struct ecore_dev *edev,
 			nb_segs--;
 		}
 
-		rte_pktmbuf_free(mbuf);
 		idx = (idx + 1) & mask;
 		PMD_TX_LOG(DEBUG, txq, "Freed tx packet\n");
 	}
 	txq->sw_tx_cons = idx;
+
+	if (first_idx > idx) {
+		rte_pktmbuf_free_bulk(&txq->sw_tx_ring[first_idx], mask - first_idx + 1);
+		rte_pktmbuf_free_bulk(&txq->sw_tx_ring[0], idx);
+	} else {
+		rte_pktmbuf_free_bulk(&txq->sw_tx_ring[first_idx], idx - first_idx);
+	}
 }
 
 static int qede_drain_txq(struct qede_dev *qdev,
-- 
2.29.2


  parent reply	other threads:[~2021-03-05 13:14 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-05 13:13 [dpdk-dev] [PATCH 0/8] Optimize qede use of rx/tx_entries Balazs Nemeth
2021-03-05 13:13 ` [dpdk-dev] [PATCH 1/8] net/qede: remove flags from qede_tx_entry and simplify to rte_mbuf Balazs Nemeth
2021-03-05 13:14 ` [dpdk-dev] [PATCH 2/8] net/qede: avoid repeatedly calling ecore_chain_get_cons_idx Balazs Nemeth
2021-03-05 13:14 ` [dpdk-dev] [PATCH 3/8] net/qede: assume txq->sw_tx_ring[idx] is never null in qede_free_tx_pkt Balazs Nemeth
2021-03-05 13:14 ` [dpdk-dev] [PATCH 4/8] net/qede: inline qede_free_tx_pkt to prepare for rte_pktmbuf_free_bulk Balazs Nemeth
2021-03-05 13:14 ` Balazs Nemeth [this message]
2021-03-05 13:14 ` [dpdk-dev] [PATCH 6/8] net/qede: prefetch txq->hw_cons_ptr Balazs Nemeth
2021-03-05 13:14 ` [dpdk-dev] [PATCH 7/8] net/qede: prefetch next packet to free Balazs Nemeth
2021-03-05 13:14 ` [dpdk-dev] [PATCH 8/8] net/qede: remove page_offset from struct qede_rx_entry and simplify Balazs Nemeth
2021-03-08 18:13 ` [dpdk-dev] [PATCH 0/8] Optimize qede use of rx/tx_entries Jerin Jacob
2021-03-10  6:43   ` [dpdk-dev] [EXT] " Igor Russkikh
2021-03-10  7:51     ` Jerin Jacob
2021-03-10  8:17       ` Igor Russkikh
2021-03-20 13:16     ` Jerin Jacob
2021-03-22 17:08 ` [dpdk-dev] [EXT] " Igor Russkikh
2021-03-24  9:18   ` Jerin Jacob
2021-03-24  9:34     ` Balazs Nemeth

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=c8ff6417ecd36116114b3889362500b6bf231499.1614938727.git.bnemeth@redhat.com \
    --to=bnemeth@redhat.com \
    --cc=dev@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).