Olivier, thanks for the reviewing.
I'll remove the comment and send the v2.
I use 1G huge pages, will retest over 2M
and continue finding why my host fails.
With best regards, Slava
> -----Original Message-----
> From: Olivier Matz <olivier.m...@6wind.com>
> Sent: Thursday, February 6, 2020 10:17
> To: Slava Ovsiienko <viachesl...@mellanox.com>
> Cc: dev@dpdk.org; Matan Azrad <ma...@mellanox.com>; Raslan Darawsheh
> <rasl...@mellanox.com>; Ori Kam <or...@mellanox.com>; Shahaf Shuler
> <shah...@mellanox.com>; step...@networkplumber.org;
> tho...@mellanox.net
> Subject: Re: [PATCH] app/test: add test for mbuf with pinned external buffer
>
> Hi,
>
> On Fri, Jan 24, 2020 at 08:25:18PM +0000, Viacheslav Ovsiienko wrote:
> > This patch adds unit test for the mbufs allocated from the special
> > pool with pinned external data buffers.
> >
> > The pinned buffer mbufs are tested in the same way as regular ones
> > with taking into account some specifics of cloning/attaching.
> >
> > Signed-off-by: Viacheslav Ovsiienko <viachesl...@mellanox.com>
>
> Looks good to me, you can add my ack in the v2, once we understand the
> issue with verify_mbuf_check_panics().
>
> > @@ -1199,10 +1212,11 @@
> > buf = rte_pktmbuf_alloc(pktmbuf_pool);
> > if (buf == NULL)
> > return -1;
> > + /*
> > printf("Checking good mbuf initially\n");
> > if (verify_mbuf_check_panics(buf) != -1)
> > return -1;
> > -
> > + */
> > printf("Now checking for error conditions\n");
> >
> > if (verify_mbuf_check_panics(NULL)) { @@ -2411,6 +2425,120 @@
> struct
> > test_case {
>
> Note: on my platform, it still works if I remove this comment.
>
> Regards,
> Olivier
