MIME-Version: 1.0
References: <20230131130412.432549-1-andrei.gherzan@canonical.com> <20230131130412.432549-4-andrei.gherzan@canonical.com>
In-Reply-To: <20230131130412.432549-4-andrei.gherzan@canonical.com>
From:   Willem de Bruijn <willemb@google.com>
Date:   Tue, 31 Jan 2023 08:39:40 -0500
Message-ID: <CA+FuTSe-C+rOx+zUYzhGCm24hnBXUNpAM5iUqf4shVNEL6niSQ@mail.gmail.com>
Subject: Re: [PATCH v2 4/4] selftests: net: udpgso_bench_tx: Cater for pending
 datagrams zerocopy benchmarking
To:     Andrei Gherzan <andrei.gherzan@canonical.com>
Cc:     "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>, Shuah Khan <shuah@kernel.org>,
        netdev@vger.kernel.org, linux-kselftest@vger.kernel.org,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Tue, Jan 31, 2023 at 8:06 AM Andrei Gherzan
<andrei.gherzan@canonical.com> wrote:
>
> The test tool can check that the zerocopy number of completions value is
> valid taking into consideration the number of datagram send calls. This can
> catch the system into a state where the datagrams are still in the system
> (for example in a qdisk, waiting for the network interface to return a
> completion notification, etc).
>
> This change adds a retry logic of computing the number of completions up to
> a configurable (via CLI) timeout (default: 2 seconds).
>
> Signed-off-by: Andrei Gherzan <andrei.gherzan@canonical.com>
> ---
>  tools/testing/selftests/net/udpgso_bench_tx.c | 38 +++++++++++++++----
>  1 file changed, 30 insertions(+), 8 deletions(-)
>
> diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
> index b47b5c32039f..5a29b5f24023 100644
> --- a/tools/testing/selftests/net/udpgso_bench_tx.c
> +++ b/tools/testing/selftests/net/udpgso_bench_tx.c
> @@ -62,6 +62,7 @@ static int    cfg_payload_len = (1472 * 42);
>  static int     cfg_port        = 8000;
>  static int     cfg_runtime_ms  = -1;
>  static bool    cfg_poll;
> +static int     cfg_poll_loop_timeout_ms = 2000;
>  static bool    cfg_segment;
>  static bool    cfg_sendmmsg;
>  static bool    cfg_tcp;
> @@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd)
>         }
>  }
>
> -static void flush_errqueue(int fd, const bool do_poll)
> +static void flush_errqueue(int fd, const bool do_poll,
> +               unsigned long poll_timeout, const bool poll_err)
>  {
>         if (do_poll) {
>                 struct pollfd fds = {0};
>                 int ret;
>
>                 fds.fd = fd;
> -               ret = poll(&fds, 1, 500);
> +               ret = poll(&fds, 1, poll_timeout);
>                 if (ret == 0) {
> -                       if (cfg_verbose)
> +                       if ((cfg_verbose) && (poll_err))
>                                 fprintf(stderr, "poll timeout\n");
>                 } else if (ret < 0) {
>                         error(1, errno, "poll");
> @@ -254,6 +256,22 @@ static void flush_errqueue(int fd, const bool do_poll)
>         flush_errqueue_recv(fd);
>  }
>
> +static void flush_errqueue_retry(int fd, const bool do_poll, unsigned long num_sends)
> +{
> +       unsigned long tnow, tstop;
> +       bool first_try = true;
> +
> +       tnow = gettimeofday_ms();
> +       tstop = tnow + cfg_poll_loop_timeout_ms;
> +       do {
> +               flush_errqueue(fd, do_poll, tstop - tnow, first_try);
> +               first_try = false;
> +               if (!do_poll)
> +                       usleep(1000);  // a throttling delay if polling is enabled

never reached