From: Dengdui Huang <huangdengdui@huawei.com>
To: <dev@dpdk.org>
Cc: <ferruh.yigit@amd.com>, <aman.deep.singh@intel.com>,
<yuying.zhang@intel.com>, <liuyonglong@huawei.com>
Subject: [PATCH] app/testpmd: fix crash in multi-process packet forwarding
Date: Fri, 26 Jan 2024 10:41:10 +0800 [thread overview]
Message-ID: <20240126024110.2671570-1-huangdengdui@huawei.com> (raw)
On multi-process scenario, each process creates flows based on the
number of queues. When nbcore is greater than 1, multiple cores may
use the same queue to forward packet, like:
dpdk-testpmd -a BDF --proc-type=auto -- -i --rxq=4 --txq=4
--nb-cores=2 --num-procs=2 --proc-id=0
testpmd> start
mac packet forwarding - ports=1 - cores=2 - streams=4 - NUMA support
enabled, MP allocation mode: native
Logical Core 2 (socket 0) forwards packets on 2 streams:
RX P=0/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
RX P=0/Q=1 (socket 0) -> TX P=0/Q=1 (socket 0) peer=02:00:00:00:00:00
Logical Core 3 (socket 0) forwards packets on 2 streams:
RX P=0/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
RX P=0/Q=1 (socket 0) -> TX P=0/Q=1 (socket 0) peer=02:00:00:00:00:00
After this commit, the result will be:
dpdk-testpmd -a BDF --proc-type=auto -- -i --rxq=4 --txq=4
--nb-cores=2 --num-procs=2 --proc-id=0
testpmd> start
io packet forwarding - ports=1 - cores=2 - streams=2 - NUMA support
enabled, MP allocation mode: native
Logical Core 2 (socket 0) forwards packets on 1 streams:
RX P=0/Q=0 (socket 2) -> TX P=0/Q=0 (socket 2) peer=02:00:00:00:00:00
Logical Core 3 (socket 0) forwards packets on 1 streams:
RX P=0/Q=1 (socket 2) -> TX P=0/Q=1 (socket 2) peer=02:00:00:00:00:00
Fixes: a550baf24af9 ("app/testpmd: support multi-process")
Cc: stable@dpdk.org
Signed-off-by: Dengdui Huang <huangdengdui@huawei.com>
---
app/test-pmd/config.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index cad7537bc6..2c4dedd603 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -4794,7 +4794,6 @@ rss_fwd_config_setup(void)
queueid_t nb_q;
streamid_t sm_id;
int start;
- int end;
nb_q = nb_rxq;
if (nb_q > nb_txq)
@@ -4802,7 +4801,7 @@ rss_fwd_config_setup(void)
cur_fwd_config.nb_fwd_lcores = (lcoreid_t) nb_fwd_lcores;
cur_fwd_config.nb_fwd_ports = nb_fwd_ports;
cur_fwd_config.nb_fwd_streams =
- (streamid_t) (nb_q * cur_fwd_config.nb_fwd_ports);
+ (streamid_t) (nb_q / num_procs * cur_fwd_config.nb_fwd_ports);
if (cur_fwd_config.nb_fwd_streams < cur_fwd_config.nb_fwd_lcores)
cur_fwd_config.nb_fwd_lcores =
@@ -4824,7 +4823,6 @@ rss_fwd_config_setup(void)
* the 2~3 queue for secondary process.
*/
start = proc_id * nb_q / num_procs;
- end = start + nb_q / num_procs;
rxp = 0;
rxq = start;
for (sm_id = 0; sm_id < cur_fwd_config.nb_fwd_streams; sm_id++) {
@@ -4843,8 +4841,6 @@ rss_fwd_config_setup(void)
continue;
rxp = 0;
rxq++;
- if (rxq >= end)
- rxq = start;
}
}
--
2.33.0
next reply other threads:[~2024-01-26 2:41 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-26 2:41 Dengdui Huang [this message]
2024-01-26 6:23 ` fengchengwen
2024-01-30 1:32 ` huangdengdui
2024-01-30 1:32 ` [PATCH v2] " Dengdui Huang
2024-02-08 1:12 ` 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=20240126024110.2671570-1-huangdengdui@huawei.com \
--to=huangdengdui@huawei.com \
--cc=aman.deep.singh@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@amd.com \
--cc=liuyonglong@huawei.com \
--cc=yuying.zhang@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).