After updating the patch, it seems that the `lcores_autotest` unit test now
times out on Windows Server 2019. I looked at the test logs, but they were
identical as far as I could tell, with the timed out test even printing "Test
OK" to stdout. Is this a flake? Or is there any other way to get extra
information about why the test timed out or run the test with extra
debugging information?

Thanks,
Josh

On Fri, Apr 21, 2023 at 4:20 PM Joshua Washington <joshwash@google.com>
wrote:

> Google cloud routes traffic using IP addresses without the support of MAC
> addresses, so changing source IP address for txonly-multi-flow can have
> negative performance implications for net/gve when using testpmd. This
> patch updates txonly multiflow mode to modify source ports instead of
> source IP addresses.
>
> The change can be tested with the following command:
> dpdk-testpmd -- --forward-mode=txonly --txonly-multi-flow \
>     --tx-ip=<SRC>,<DST>
>
> Signed-off-by: Joshua Washington <joshwash@google.com>
> Reviewed-by: Rushil Gupta <rushilg@google.com>
> ---
>  app/test-pmd/txonly.c | 39 +++++++++++++++++++++++----------------
>  1 file changed, 23 insertions(+), 16 deletions(-)
>
> diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
> index b3d6873104..f79e0e5d0b 100644
> --- a/app/test-pmd/txonly.c
> +++ b/app/test-pmd/txonly.c
> @@ -56,7 +56,7 @@ uint32_t tx_ip_dst_addr = (198U << 24) | (18 << 16) | (0
> << 8) | 2;
>  #define IP_DEFTTL  64   /* from RFC 1340. */
>
>  static struct rte_ipv4_hdr pkt_ip_hdr; /**< IP header of transmitted
> packets. */
> -RTE_DEFINE_PER_LCORE(uint8_t, _ip_var); /**< IP address variation */
> +RTE_DEFINE_PER_LCORE(uint8_t, _src_var); /**< Source port variation */
>  static struct rte_udp_hdr pkt_udp_hdr; /**< UDP header of tx packets. */
>
>  static uint64_t timestamp_mask; /**< Timestamp dynamic flag mask */
> @@ -230,28 +230,35 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct
> rte_mempool *mbp,
>         copy_buf_to_pkt(eth_hdr, sizeof(*eth_hdr), pkt, 0);
>         copy_buf_to_pkt(&pkt_ip_hdr, sizeof(pkt_ip_hdr), pkt,
>                         sizeof(struct rte_ether_hdr));
> +       copy_buf_to_pkt(&pkt_udp_hdr, sizeof(pkt_udp_hdr), pkt,
> +                       sizeof(struct rte_ether_hdr) +
> +                       sizeof(struct rte_ipv4_hdr));
>         if (txonly_multi_flow) {
> -               uint8_t  ip_var = RTE_PER_LCORE(_ip_var);
> -               struct rte_ipv4_hdr *ip_hdr;
> -               uint32_t addr;
> +               uint16_t src_var = RTE_PER_LCORE(_src_var);
> +               struct rte_udp_hdr *udp_hdr;
> +               uint16_t port;
>
> -               ip_hdr = rte_pktmbuf_mtod_offset(pkt,
> -                               struct rte_ipv4_hdr *,
> -                               sizeof(struct rte_ether_hdr));
> +               udp_hdr = rte_pktmbuf_mtod_offset(pkt,
> +                               struct rte_udp_hdr *,
> +                               sizeof(struct rte_ether_hdr) +
> +                               sizeof(struct rte_ipv4_hdr));
>                 /*
> -                * Generate multiple flows by varying IP src addr. This
> -                * enables packets are well distributed by RSS in
> +                * Generate multiple flows by varying UDP source port.
> +                * This enables packets are well distributed by RSS in
>                  * receiver side if any and txonly mode can be a decent
>                  * packet generator for developer's quick performance
>                  * regression test.
> +                *
> +                * Only ports in the range 49152 (0xC000) and 65535
> (0xFFFF)
> +                * will be used, with the least significant byte
> representing
> +                * the lcore ID. As such, the most significant byte will
> cycle
> +                * through 0xC0 and 0xFF.
>                  */
> -               addr = (tx_ip_dst_addr | (ip_var++ << 8)) + rte_lcore_id();
> -               ip_hdr->src_addr = rte_cpu_to_be_32(addr);
> -               RTE_PER_LCORE(_ip_var) = ip_var;
> +               port = ((((src_var++) % (0xFF - 0xC0) + 0xC0) & 0xFF) << 8)
> +                               + rte_lcore_id();
> +               udp_hdr->src_port = rte_cpu_to_be_16(port);
> +               RTE_PER_LCORE(_src_var) = src_var;
>         }
> -       copy_buf_to_pkt(&pkt_udp_hdr, sizeof(pkt_udp_hdr), pkt,
> -                       sizeof(struct rte_ether_hdr) +
> -                       sizeof(struct rte_ipv4_hdr));
>
>         if (unlikely(tx_pkt_split == TX_PKT_SPLIT_RND) ||
> txonly_multi_flow)
>                 update_pkt_header(pkt, pkt_len);
> @@ -393,7 +400,7 @@ pkt_burst_transmit(struct fwd_stream *fs)
>         nb_tx = common_fwd_stream_transmit(fs, pkts_burst, nb_pkt);
>
>         if (txonly_multi_flow)
> -               RTE_PER_LCORE(_ip_var) -= nb_pkt - nb_tx;
> +               RTE_PER_LCORE(_src_var) -= nb_pkt - nb_tx;
>
>         if (unlikely(nb_tx < nb_pkt)) {
>                 if (verbose_level > 0 && fs->fwd_dropped == 0)
> --
> 2.40.0.634.g4ca3ef3211-goog
>
>

-- 

Joshua Washington | Software Engineer | joshwash@google.com | (414) 366-4423