[dpdk-dev] [EXT] Re: [PATCH] app/testpmd: tx pkt clones parameter in flowgen
Igor Russkikh
irusskikh at marvell.com
Tue Jan 19 12:58:33 CET 2021
>> Doing similar measurements per core, I see one core can do
>> 6.9MPPS (without clones) vs 11MPPS (with clones)
>>
>> Verified on Marvell qede and atlantic PMDs.
>
> Ubuntu 18.04 gcc complains:
> https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_ovsrobot_dpdk_runs_1713302522-3Fcheck-5Fsuite-5Ffocus-3Dtrue-23step-3A14-3A3097&d=DwIBaQ&c=nKjWec2b6R0mOyPaz7xtfQ&r=3kUjVPjrPMvlbd3rzgP63W0eewvCq4D-kzQRqaXHOqU&m=AkyYUO7yiMI9Y3lF78e0dzcp_f95VqFm9SsKGvGvZSs&s=KbY-M7bennVuSeEXqqVUG2JFCPAikRYxT5P1kY56QTM&e=
>
> Can you have a look?
Hi David,
Thanks for the notice.
>From logic this looks like a false positive.. The only way I found to eliminate the
warning is
--- a/app/test-pmd/flowgen.c
+++ b/app/test-pmd/flowgen.c
@@ -85,7 +85,7 @@ pkt_burst_flow_gen(struct fwd_stream *fs)
unsigned pkt_size = tx_pkt_length - 4; /* Adjust FCS */
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
struct rte_mempool *mbp;
- struct rte_mbuf *pkt;
+ struct rte_mbuf *pkt = NULL;
Its abit dumb, but still.
Will resubmit.
Thanks,
Igor
More information about the dev
mailing list