| Message ID | 1432815522-2925-1-git-send-email-zoltan.kiss@linaro.org |
|---|---|
| State | New |
| Headers | show |
This needs to be API-NEXT as it is a change to an API file. On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - FI/Espoo) < petri.savolainen@nokia.com> wrote: > Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com> > > > > -----Original Message----- > > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org] On Behalf Of ext > > Zoltan Kiss > > Sent: Thursday, May 28, 2015 3:19 PM > > To: lng-odp@lists.linaro.org > > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what happens when > > not all packets are sent > > > > Currently our examples are not handling this situation as well. > > > > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org> > > --- > > include/odp/api/packet_io.h | 4 +++- > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > diff --git a/include/odp/api/packet_io.h b/include/odp/api/packet_io.h > > index 89356a6..b97b2b8 100644 > > --- a/include/odp/api/packet_io.h > > +++ b/include/odp/api/packet_io.h > > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, odp_packet_t > > pkt_table[], int len); > > * @param pkt_table[] Array of packets to send > > * @param len length of pkt_table[] > > * > > - * @return Number of packets sent > > + * @return Number of packets sent. If it is less than 'len', the > > remaining > > + * packets at the end of pkt_table[] are left intact, and caller has to > > take > > + * care of them. > > * @retval <0 on failure > > */ > > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], int > len); > > -- > > 1.9.1 > > > > _______________________________________________ > > lng-odp mailing list > > lng-odp@lists.linaro.org > > https://lists.linaro.org/mailman/listinfo/lng-odp > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org > https://lists.linaro.org/mailman/listinfo/lng-odp >
On 28 May 2015 at 15:56, Bill Fischofer <bill.fischofer@linaro.org> wrote: > This needs to be API-NEXT as it is a change to an API file. > I don't see this as an API change, just as a clarification of what is defined/expected behavior. I was expecting this behavior already with the current API but I agree that it should be spelled out clearly. > > On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - FI/Espoo) < > petri.savolainen@nokia.com> wrote: > >> Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com> >> >> >> > -----Original Message----- >> > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org] On Behalf Of >> ext >> > Zoltan Kiss >> > Sent: Thursday, May 28, 2015 3:19 PM >> > To: lng-odp@lists.linaro.org >> > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what happens >> when >> > not all packets are sent >> > >> > Currently our examples are not handling this situation as well. >> > >> > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org> >> > --- >> > include/odp/api/packet_io.h | 4 +++- >> > 1 file changed, 3 insertions(+), 1 deletion(-) >> > >> > diff --git a/include/odp/api/packet_io.h b/include/odp/api/packet_io.h >> > index 89356a6..b97b2b8 100644 >> > --- a/include/odp/api/packet_io.h >> > +++ b/include/odp/api/packet_io.h >> > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, odp_packet_t >> > pkt_table[], int len); >> > * @param pkt_table[] Array of packets to send >> > * @param len length of pkt_table[] >> > * >> > - * @return Number of packets sent >> > + * @return Number of packets sent. If it is less than 'len', the >> > remaining >> > + * packets at the end of pkt_table[] are left intact, and caller has to >> > take >> > + * care of them. >> > * @retval <0 on failure >> > */ >> > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], int >> len); >> > -- >> > 1.9.1 >> > >> > _______________________________________________ >> > lng-odp mailing list >> > lng-odp@lists.linaro.org >> > https://lists.linaro.org/mailman/listinfo/lng-odp >> _______________________________________________ >> lng-odp mailing list >> lng-odp@lists.linaro.org >> https://lists.linaro.org/mailman/listinfo/lng-odp >> > > > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org > https://lists.linaro.org/mailman/listinfo/lng-odp > >
Yes, I missed that prefix. Do you want me to resend the patch? I'll send an another patch to implement this behaviour in the repo wherever odp_pktio_send is called. But I think we can't create a unit test for it, can we? On 28/05/15 14:56, Bill Fischofer wrote: > This needs to be API-NEXT as it is a change to an API file. > > On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - FI/Espoo) > <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com>> wrote: > > Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>> > > > > -----Original Message----- > > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org>] On Behalf Of ext > > Zoltan Kiss > > Sent: Thursday, May 28, 2015 3:19 PM > > To: lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what > happens when > > not all packets are sent > > > > Currently our examples are not handling this situation as well. > > > > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>> > > --- > > include/odp/api/packet_io.h | 4 +++- > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > diff --git a/include/odp/api/packet_io.h > b/include/odp/api/packet_io.h > > index 89356a6..b97b2b8 100644 > > --- a/include/odp/api/packet_io.h > > +++ b/include/odp/api/packet_io.h > > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, > odp_packet_t > > pkt_table[], int len); > > * @param pkt_table[] Array of packets to send > > * @param len length of pkt_table[] > > * > > - * @return Number of packets sent > > + * @return Number of packets sent. If it is less than 'len', the > > remaining > > + * packets at the end of pkt_table[] are left intact, and caller > has to > > take > > + * care of them. > > * @retval <0 on failure > > */ > > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], > int len); > > -- > > 1.9.1 > > > > _______________________________________________ > > lng-odp mailing list > > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > > https://lists.linaro.org/mailman/listinfo/lng-odp > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > https://lists.linaro.org/mailman/listinfo/lng-odp > >
We agreed that *any* change to the include/odp directory would be flagged API-NEXT (avoids having to make decisions). We can then decide which to cherry-pick into the mainline on an expedited basis for simple things like documentation only changes, but these would be reviewed on a case-by-case basis. On Thu, May 28, 2015 at 9:25 AM, Zoltan Kiss <zoltan.kiss@linaro.org> wrote: > Yes, I missed that prefix. Do you want me to resend the patch? > I'll send an another patch to implement this behaviour in the repo > wherever odp_pktio_send is called. But I think we can't create a unit test > for it, can we? > > On 28/05/15 14:56, Bill Fischofer wrote: > >> This needs to be API-NEXT as it is a change to an API file. >> >> On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - FI/Espoo) >> <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com>> wrote: >> >> Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com >> <mailto:petri.savolainen@nokia.com>> >> >> >> > -----Original Message----- >> > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org >> <mailto:lng-odp-bounces@lists.linaro.org>] On Behalf Of ext >> > Zoltan Kiss >> > Sent: Thursday, May 28, 2015 3:19 PM >> > To: lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what >> happens when >> > not all packets are sent >> > >> > Currently our examples are not handling this situation as well. >> > >> > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org >> <mailto:zoltan.kiss@linaro.org>> >> >> > --- >> > include/odp/api/packet_io.h | 4 +++- >> > 1 file changed, 3 insertions(+), 1 deletion(-) >> > >> > diff --git a/include/odp/api/packet_io.h >> b/include/odp/api/packet_io.h >> > index 89356a6..b97b2b8 100644 >> > --- a/include/odp/api/packet_io.h >> > +++ b/include/odp/api/packet_io.h >> > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, >> odp_packet_t >> > pkt_table[], int len); >> > * @param pkt_table[] Array of packets to send >> > * @param len length of pkt_table[] >> > * >> > - * @return Number of packets sent >> > + * @return Number of packets sent. If it is less than 'len', the >> > remaining >> > + * packets at the end of pkt_table[] are left intact, and caller >> has to >> > take >> > + * care of them. >> > * @retval <0 on failure >> > */ >> > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], >> int len); >> > -- >> > 1.9.1 >> > >> > _______________________________________________ >> > lng-odp mailing list >> > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> > https://lists.linaro.org/mailman/listinfo/lng-odp >> _______________________________________________ >> lng-odp mailing list >> lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> https://lists.linaro.org/mailman/listinfo/lng-odp >> >> >>
On 28 May 2015 at 10:16, Ola Liljedahl <ola.liljedahl@linaro.org> wrote: > On 28 May 2015 at 15:56, Bill Fischofer <bill.fischofer@linaro.org> wrote: > >> This needs to be API-NEXT as it is a change to an API file. >> > I don't see this as an API change, just as a clarification of what is > defined/expected behavior. > I was expecting this behavior already with the current API but I agree > that it should be spelled out clearly. > The rule is that anything that touches "include/odp/api" needs to go via api-next, it can then be cherry picked into master very quickly. The other mechanisms we tried left ambiguity in how to handle the patch becasue api-next and master are currently maintained by Maxim but api-next has extra rules with Petris signoff. I think it would be clearer, faster, simpler if we do split api-next to its own repo and Petri sends pull requests to Maxim every time he is happy for an odp/api change to go in. > > > >> >> On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - FI/Espoo) < >> petri.savolainen@nokia.com> wrote: >> >>> Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com> >>> >>> >>> > -----Original Message----- >>> > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org] On Behalf Of >>> ext >>> > Zoltan Kiss >>> > Sent: Thursday, May 28, 2015 3:19 PM >>> > To: lng-odp@lists.linaro.org >>> > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what happens >>> when >>> > not all packets are sent >>> > >>> > Currently our examples are not handling this situation as well. >>> > >>> > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org> >>> > --- >>> > include/odp/api/packet_io.h | 4 +++- >>> > 1 file changed, 3 insertions(+), 1 deletion(-) >>> > >>> > diff --git a/include/odp/api/packet_io.h b/include/odp/api/packet_io.h >>> > index 89356a6..b97b2b8 100644 >>> > --- a/include/odp/api/packet_io.h >>> > +++ b/include/odp/api/packet_io.h >>> > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, odp_packet_t >>> > pkt_table[], int len); >>> > * @param pkt_table[] Array of packets to send >>> > * @param len length of pkt_table[] >>> > * >>> > - * @return Number of packets sent >>> > + * @return Number of packets sent. If it is less than 'len', the >>> > remaining >>> > + * packets at the end of pkt_table[] are left intact, and caller has >>> to >>> > take >>> > + * care of them. >>> > * @retval <0 on failure >>> > */ >>> > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], int >>> len); >>> > -- >>> > 1.9.1 >>> > >>> > _______________________________________________ >>> > lng-odp mailing list >>> > lng-odp@lists.linaro.org >>> > https://lists.linaro.org/mailman/listinfo/lng-odp >>> _______________________________________________ >>> lng-odp mailing list >>> lng-odp@lists.linaro.org >>> https://lists.linaro.org/mailman/listinfo/lng-odp >>> >> >> >> _______________________________________________ >> lng-odp mailing list >> lng-odp@lists.linaro.org >> https://lists.linaro.org/mailman/listinfo/lng-odp >> >> > > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org > https://lists.linaro.org/mailman/listinfo/lng-odp > >
On 28 May 2015 at 16:25, Zoltan Kiss <zoltan.kiss@linaro.org> wrote: > Yes, I missed that prefix. Do you want me to resend the patch? > I'll send an another patch to implement this behaviour in the repo > wherever odp_pktio_send is called. But I think we can't create a unit test > for it, can we? > We can sort-of test that any packets not being consumed by odp_pktio_send() still are ours and valid (although I think it is implementation specific whether ODP will detect any violations, e.g. whether it detects that an application uses a packet handle it does not "own"). But can we force odp_pktio_send() not to consume all packets passed to it? This seems less likely. > On 28/05/15 14:56, Bill Fischofer wrote: > >> This needs to be API-NEXT as it is a change to an API file. >> >> On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - FI/Espoo) >> <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com>> wrote: >> >> Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com >> <mailto:petri.savolainen@nokia.com>> >> >> >> > -----Original Message----- >> > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org >> <mailto:lng-odp-bounces@lists.linaro.org>] On Behalf Of ext >> > Zoltan Kiss >> > Sent: Thursday, May 28, 2015 3:19 PM >> > To: lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what >> happens when >> > not all packets are sent >> > >> > Currently our examples are not handling this situation as well. >> > >> > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org >> <mailto:zoltan.kiss@linaro.org>> >> > --- >> > include/odp/api/packet_io.h | 4 +++- >> > 1 file changed, 3 insertions(+), 1 deletion(-) >> > >> > diff --git a/include/odp/api/packet_io.h >> b/include/odp/api/packet_io.h >> > index 89356a6..b97b2b8 100644 >> > --- a/include/odp/api/packet_io.h >> > +++ b/include/odp/api/packet_io.h >> > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, >> odp_packet_t >> > pkt_table[], int len); >> > * @param pkt_table[] Array of packets to send >> > * @param len length of pkt_table[] >> > * >> > - * @return Number of packets sent >> > + * @return Number of packets sent. If it is less than 'len', the >> > remaining >> > + * packets at the end of pkt_table[] are left intact, and caller >> has to >> > take >> > + * care of them. >> > * @retval <0 on failure >> > */ >> > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], >> int len); >> > -- >> > 1.9.1 >> > >> > _______________________________________________ >> > lng-odp mailing list >> > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> > https://lists.linaro.org/mailman/listinfo/lng-odp >> _______________________________________________ >> lng-odp mailing list >> lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> https://lists.linaro.org/mailman/listinfo/lng-odp >> >> >> _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org > https://lists.linaro.org/mailman/listinfo/lng-odp >
On 28/05/15 15:32, Ola Liljedahl wrote: > On 28 May 2015 at 16:25, Zoltan Kiss <zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>> wrote: > > Yes, I missed that prefix. Do you want me to resend the patch? > I'll send an another patch to implement this behaviour in the repo > wherever odp_pktio_send is called. But I think we can't create a > unit test for it, can we? > > We can sort-of test that any packets not being consumed by > odp_pktio_send() still are ours and valid (although I think it is > implementation specific whether ODP will detect any violations, e.g. > whether it detects that an application uses a packet handle it does not > "own"). > > But can we force odp_pktio_send() not to consume all packets passed to > it? This seems less likely. Yes, that's why I'm concerned if we can test that out somehow. Zoli > > > > On 28/05/15 14:56, Bill Fischofer wrote: > > This needs to be API-NEXT as it is a change to an API file. > > On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - > FI/Espoo) > <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>>> wrote: > > Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>>> > > > > -----Original Message----- > > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org> > <mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org>>] On Behalf Of ext > > Zoltan Kiss > > Sent: Thursday, May 28, 2015 3:19 PM > > To: lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what > happens when > > not all packets are sent > > > > Currently our examples are not handling this situation > as well. > > > > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org> > <mailto:zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>>> > > --- > > include/odp/api/packet_io.h | 4 +++- > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > diff --git a/include/odp/api/packet_io.h > b/include/odp/api/packet_io.h > > index 89356a6..b97b2b8 100644 > > --- a/include/odp/api/packet_io.h > > +++ b/include/odp/api/packet_io.h > > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, > odp_packet_t > > pkt_table[], int len); > > * @param pkt_table[] Array of packets to send > > * @param len length of pkt_table[] > > * > > - * @return Number of packets sent > > + * @return Number of packets sent. If it is less than > 'len', the > > remaining > > + * packets at the end of pkt_table[] are left intact, > and caller > has to > > take > > + * care of them. > > * @retval <0 on failure > > */ > > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t > pkt_table[], > int len); > > -- > > 1.9.1 > > > > _______________________________________________ > > lng-odp mailing list > > lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > > https://lists.linaro.org/mailman/listinfo/lng-odp > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > https://lists.linaro.org/mailman/listinfo/lng-odp > > > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > https://lists.linaro.org/mailman/listinfo/lng-odp > >
Hi, I think there might be some ambiguity here: I understand that the correct format of subject line is [PATCH API-NEXT], rather than lower case, I'll do my best not to forget that next time. But do you expect me to resend the patch with a different subject line? I assume however picks this up (Maxim?) is already aware of this minor mistake and picks it up anyway, but I might be wrong. Or, do you wait for me to send it again with an another patch implementing this behaviour across our codebase? I thought I should send it once it gets commited to api-next. And finally, should the subject line of this next patch start with [PATCH API-NEXT] as well? Regards, Zoli On 28/05/15 15:28, Bill Fischofer wrote: > We agreed that *any* change to the include/odp directory would be > flagged API-NEXT (avoids having to make decisions). We can then decide > which to cherry-pick into the mainline on an expedited basis for simple > things like documentation only changes, but these would be reviewed on a > case-by-case basis. > > On Thu, May 28, 2015 at 9:25 AM, Zoltan Kiss <zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>> wrote: > > Yes, I missed that prefix. Do you want me to resend the patch? > I'll send an another patch to implement this behaviour in the repo > wherever odp_pktio_send is called. But I think we can't create a > unit test for it, can we? > > On 28/05/15 14:56, Bill Fischofer wrote: > > This needs to be API-NEXT as it is a change to an API file. > > On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - > FI/Espoo) > <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>>> wrote: > > Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>>> > > > > -----Original Message----- > > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org> > <mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org>>] On Behalf Of ext > > Zoltan Kiss > > Sent: Thursday, May 28, 2015 3:19 PM > > To: lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify what > happens when > > not all packets are sent > > > > Currently our examples are not handling this situation > as well. > > > > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org> > <mailto:zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>>> > > > --- > > include/odp/api/packet_io.h | 4 +++- > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > diff --git a/include/odp/api/packet_io.h > b/include/odp/api/packet_io.h > > index 89356a6..b97b2b8 100644 > > --- a/include/odp/api/packet_io.h > > +++ b/include/odp/api/packet_io.h > > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, > odp_packet_t > > pkt_table[], int len); > > * @param pkt_table[] Array of packets to send > > * @param len length of pkt_table[] > > * > > - * @return Number of packets sent > > + * @return Number of packets sent. If it is less than > 'len', the > > remaining > > + * packets at the end of pkt_table[] are left intact, > and caller > has to > > take > > + * care of them. > > * @retval <0 on failure > > */ > > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t > pkt_table[], > int len); > > -- > > 1.9.1 > > > > _______________________________________________ > > lng-odp mailing list > > lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > > https://lists.linaro.org/mailman/listinfo/lng-odp > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > https://lists.linaro.org/mailman/listinfo/lng-odp > > >
The agreed to format for git send-email is --subject-prefix="API-NEXT PATCH" (or PATCHv2, etc.) On Wed, Jun 3, 2015 at 10:00 AM, Zoltan Kiss <zoltan.kiss@linaro.org> wrote: > Hi, > > I think there might be some ambiguity here: I understand that the correct > format of subject line is [PATCH API-NEXT], rather than lower case, I'll do > my best not to forget that next time. But do you expect me to resend the > patch with a different subject line? I assume however picks this up > (Maxim?) is already aware of this minor mistake and picks it up anyway, but > I might be wrong. > Or, do you wait for me to send it again with an another patch implementing > this behaviour across our codebase? I thought I should send it once it gets > commited to api-next. > And finally, should the subject line of this next patch start with [PATCH > API-NEXT] as well? > > Regards, > > Zoli > > On 28/05/15 15:28, Bill Fischofer wrote: > >> We agreed that *any* change to the include/odp directory would be >> flagged API-NEXT (avoids having to make decisions). We can then decide >> which to cherry-pick into the mainline on an expedited basis for simple >> things like documentation only changes, but these would be reviewed on a >> case-by-case basis. >> >> On Thu, May 28, 2015 at 9:25 AM, Zoltan Kiss <zoltan.kiss@linaro.org >> <mailto:zoltan.kiss@linaro.org>> wrote: >> >> Yes, I missed that prefix. Do you want me to resend the patch? >> I'll send an another patch to implement this behaviour in the repo >> wherever odp_pktio_send is called. But I think we can't create a >> unit test for it, can we? >> >> On 28/05/15 14:56, Bill Fischofer wrote: >> >> This needs to be API-NEXT as it is a change to an API file. >> >> On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - >> FI/Espoo) >> <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com> >> <mailto:petri.savolainen@nokia.com >> <mailto:petri.savolainen@nokia.com>>> wrote: >> >> Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com >> <mailto:petri.savolainen@nokia.com> >> <mailto:petri.savolainen@nokia.com >> <mailto:petri.savolainen@nokia.com>>> >> >> >> > -----Original Message----- >> > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org >> <mailto:lng-odp-bounces@lists.linaro.org> >> <mailto:lng-odp-bounces@lists.linaro.org >> <mailto:lng-odp-bounces@lists.linaro.org>>] On Behalf Of ext >> > Zoltan Kiss >> > Sent: Thursday, May 28, 2015 3:19 PM >> > To: lng-odp@lists.linaro.org >> <mailto:lng-odp@lists.linaro.org> >> <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org >> >> >> > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify >> what >> happens when >> > not all packets are sent >> > >> > Currently our examples are not handling this situation >> as well. >> > >> > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org >> <mailto:zoltan.kiss@linaro.org> >> <mailto:zoltan.kiss@linaro.org >> >> <mailto:zoltan.kiss@linaro.org>>> >> >> > --- >> > include/odp/api/packet_io.h | 4 +++- >> > 1 file changed, 3 insertions(+), 1 deletion(-) >> > >> > diff --git a/include/odp/api/packet_io.h >> b/include/odp/api/packet_io.h >> > index 89356a6..b97b2b8 100644 >> > --- a/include/odp/api/packet_io.h >> > +++ b/include/odp/api/packet_io.h >> > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, >> odp_packet_t >> > pkt_table[], int len); >> > * @param pkt_table[] Array of packets to send >> > * @param len length of pkt_table[] >> > * >> > - * @return Number of packets sent >> > + * @return Number of packets sent. If it is less than >> 'len', the >> > remaining >> > + * packets at the end of pkt_table[] are left intact, >> and caller >> has to >> > take >> > + * care of them. >> > * @retval <0 on failure >> > */ >> > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t >> pkt_table[], >> int len); >> > -- >> > 1.9.1 >> > >> > _______________________________________________ >> > lng-odp mailing list >> > lng-odp@lists.linaro.org >> <mailto:lng-odp@lists.linaro.org> >> <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org >> >> >> > https://lists.linaro.org/mailman/listinfo/lng-odp >> _______________________________________________ >> lng-odp mailing list >> lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >> <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org >> >> >> https://lists.linaro.org/mailman/listinfo/lng-odp >> >> >> >>
Yes, but it still doesn't answer my question: do you expect me to resend the patch with a different subject line? On 03/06/15 16:22, Bill Fischofer wrote: > The agreed to format for git send-email is --subject-prefix="API-NEXT > PATCH" (or PATCHv2, etc.) > > On Wed, Jun 3, 2015 at 10:00 AM, Zoltan Kiss <zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>> wrote: > > Hi, > > I think there might be some ambiguity here: I understand that the > correct format of subject line is [PATCH API-NEXT], rather than > lower case, I'll do my best not to forget that next time. But do you > expect me to resend the patch with a different subject line? I > assume however picks this up (Maxim?) is already aware of this minor > mistake and picks it up anyway, but I might be wrong. > Or, do you wait for me to send it again with an another patch > implementing this behaviour across our codebase? I thought I should > send it once it gets commited to api-next. > And finally, should the subject line of this next patch start with > [PATCH API-NEXT] as well? > > Regards, > > Zoli > > On 28/05/15 15:28, Bill Fischofer wrote: > > We agreed that *any* change to the include/odp directory would be > flagged API-NEXT (avoids having to make decisions). We can then > decide > which to cherry-pick into the mainline on an expedited basis for > simple > things like documentation only changes, but these would be > reviewed on a > case-by-case basis. > > On Thu, May 28, 2015 at 9:25 AM, Zoltan Kiss > <zoltan.kiss@linaro.org <mailto:zoltan.kiss@linaro.org> > <mailto:zoltan.kiss@linaro.org <mailto:zoltan.kiss@linaro.org>>> > wrote: > > Yes, I missed that prefix. Do you want me to resend the patch? > I'll send an another patch to implement this behaviour in > the repo > wherever odp_pktio_send is called. But I think we can't > create a > unit test for it, can we? > > On 28/05/15 14:56, Bill Fischofer wrote: > > This needs to be API-NEXT as it is a change to an API file. > > On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - > FI/Espoo) > <petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>>>> wrote: > > Reviewed-by: Petri Savolainen > <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com> > <mailto:petri.savolainen@nokia.com > <mailto:petri.savolainen@nokia.com>>>> > > > > -----Original Message----- > > From: lng-odp > [mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org> > <mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org>> > <mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org> > <mailto:lng-odp-bounces@lists.linaro.org > <mailto:lng-odp-bounces@lists.linaro.org>>>] On Behalf Of ext > > Zoltan Kiss > > Sent: Thursday, May 28, 2015 3:19 PM > > To: lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org>> > <mailto:lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>>> > > Subject: [lng-odp] [PATCH] api-next: packet_io: > clarify what > happens when > > not all packets are sent > > > > Currently our examples are not handling this > situation > as well. > > > > Signed-off-by: Zoltan Kiss > <zoltan.kiss@linaro.org <mailto:zoltan.kiss@linaro.org> > <mailto:zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>> > <mailto:zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org> > > <mailto:zoltan.kiss@linaro.org > <mailto:zoltan.kiss@linaro.org>>>> > > > --- > > include/odp/api/packet_io.h | 4 +++- > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > diff --git a/include/odp/api/packet_io.h > b/include/odp/api/packet_io.h > > index 89356a6..b97b2b8 100644 > > --- a/include/odp/api/packet_io.h > > +++ b/include/odp/api/packet_io.h > > @@ -111,7 +111,9 @@ int > odp_pktio_recv(odp_pktio_t pktio, > odp_packet_t > > pkt_table[], int len); > > * @param pkt_table[] Array of packets to send > > * @param len length of pkt_table[] > > * > > - * @return Number of packets sent > > + * @return Number of packets sent. If it is > less than > 'len', the > > remaining > > + * packets at the end of pkt_table[] are left > intact, > and caller > has to > > take > > + * care of them. > > * @retval <0 on failure > > */ > > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t > pkt_table[], > int len); > > -- > > 1.9.1 > > > > _______________________________________________ > > lng-odp mailing list > > lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org>> > <mailto:lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>>> > > https://lists.linaro.org/mailman/listinfo/lng-odp > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>> > <mailto:lng-odp@lists.linaro.org > <mailto:lng-odp@lists.linaro.org> > <mailto:lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org>>> > https://lists.linaro.org/mailman/listinfo/lng-odp > > > >
On 3 June 2015 at 11:22, Bill Fischofer <bill.fischofer@linaro.org> wrote: > The agreed to format for git send-email is --subject-prefix="API-NEXT > PATCH" (or PATCHv2, etc.) > Or, do you wait for me to send it again with an another patch implementing this behaviour across our codebase? I thought I should send it once it gets commited to api-next. Answers to questions like these should now be here (near bottom of page) [1] in the Bylaws and Release & Branch Plan, if we are missing something lets add it. [1] http://www.opendataplane.org/downloads/ To enter API-NEXT as a new API all that is needed is a header file. To enter API-NEXT as a change to an API the test need to be modified to work with the change. In both cases the patch must be on the list 24 hours, get a review and by acked by Petri. Before anything can migrate to Master it must have a linux-generic implementation and tests and be scheduled to be in an API release that are nominally quarterly. > On Wed, Jun 3, 2015 at 10:00 AM, Zoltan Kiss <zoltan.kiss@linaro.org> > wrote: > >> Hi, >> >> I think there might be some ambiguity here: I understand that the correct >> format of subject line is [PATCH API-NEXT], rather than lower case, I'll do >> my best not to forget that next time. But do you expect me to resend the >> patch with a different subject line? I assume however picks this up >> (Maxim?) is already aware of this minor mistake and picks it up anyway, but >> I might be wrong. >> Or, do you wait for me to send it again with an another patch >> implementing this behaviour across our codebase? I thought I should send it >> once it gets commited to api-next. >> And finally, should the subject line of this next patch start with [PATCH >> API-NEXT] as well? >> >> Regards, >> >> Zoli >> >> On 28/05/15 15:28, Bill Fischofer wrote: >> >>> We agreed that *any* change to the include/odp directory would be >>> flagged API-NEXT (avoids having to make decisions). We can then decide >>> which to cherry-pick into the mainline on an expedited basis for simple >>> things like documentation only changes, but these would be reviewed on a >>> case-by-case basis. >>> >>> On Thu, May 28, 2015 at 9:25 AM, Zoltan Kiss <zoltan.kiss@linaro.org >>> <mailto:zoltan.kiss@linaro.org>> wrote: >>> >>> Yes, I missed that prefix. Do you want me to resend the patch? >>> I'll send an another patch to implement this behaviour in the repo >>> wherever odp_pktio_send is called. But I think we can't create a >>> unit test for it, can we? >>> >>> On 28/05/15 14:56, Bill Fischofer wrote: >>> >>> This needs to be API-NEXT as it is a change to an API file. >>> >>> On Thu, May 28, 2015 at 7:53 AM, Savolainen, Petri (Nokia - >>> FI/Espoo) >>> <petri.savolainen@nokia.com <mailto:petri.savolainen@nokia.com> >>> <mailto:petri.savolainen@nokia.com >>> <mailto:petri.savolainen@nokia.com>>> wrote: >>> >>> Reviewed-by: Petri Savolainen <petri.savolainen@nokia.com >>> <mailto:petri.savolainen@nokia.com> >>> <mailto:petri.savolainen@nokia.com >>> <mailto:petri.savolainen@nokia.com>>> >>> >>> >>> > -----Original Message----- >>> > From: lng-odp [mailto:lng-odp-bounces@lists.linaro.org >>> <mailto:lng-odp-bounces@lists.linaro.org> >>> <mailto:lng-odp-bounces@lists.linaro.org >>> <mailto:lng-odp-bounces@lists.linaro.org>>] On Behalf Of ext >>> > Zoltan Kiss >>> > Sent: Thursday, May 28, 2015 3:19 PM >>> > To: lng-odp@lists.linaro.org >>> <mailto:lng-odp@lists.linaro.org> >>> <mailto:lng-odp@lists.linaro.org <mailto: >>> lng-odp@lists.linaro.org>> >>> > Subject: [lng-odp] [PATCH] api-next: packet_io: clarify >>> what >>> happens when >>> > not all packets are sent >>> > >>> > Currently our examples are not handling this situation >>> as well. >>> > >>> > Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org >>> <mailto:zoltan.kiss@linaro.org> >>> <mailto:zoltan.kiss@linaro.org >>> >>> <mailto:zoltan.kiss@linaro.org>>> >>> >>> > --- >>> > include/odp/api/packet_io.h | 4 +++- >>> > 1 file changed, 3 insertions(+), 1 deletion(-) >>> > >>> > diff --git a/include/odp/api/packet_io.h >>> b/include/odp/api/packet_io.h >>> > index 89356a6..b97b2b8 100644 >>> > --- a/include/odp/api/packet_io.h >>> > +++ b/include/odp/api/packet_io.h >>> > @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, >>> odp_packet_t >>> > pkt_table[], int len); >>> > * @param pkt_table[] Array of packets to send >>> > * @param len length of pkt_table[] >>> > * >>> > - * @return Number of packets sent >>> > + * @return Number of packets sent. If it is less than >>> 'len', the >>> > remaining >>> > + * packets at the end of pkt_table[] are left intact, >>> and caller >>> has to >>> > take >>> > + * care of them. >>> > * @retval <0 on failure >>> > */ >>> > int odp_pktio_send(odp_pktio_t pktio, odp_packet_t >>> pkt_table[], >>> int len); >>> > -- >>> > 1.9.1 >>> > >>> > _______________________________________________ >>> > lng-odp mailing list >>> > lng-odp@lists.linaro.org >>> <mailto:lng-odp@lists.linaro.org> >>> <mailto:lng-odp@lists.linaro.org <mailto: >>> lng-odp@lists.linaro.org>> >>> > https://lists.linaro.org/mailman/listinfo/lng-odp >>> _______________________________________________ >>> lng-odp mailing list >>> lng-odp@lists.linaro.org <mailto:lng-odp@lists.linaro.org> >>> <mailto:lng-odp@lists.linaro.org <mailto: >>> lng-odp@lists.linaro.org>> >>> https://lists.linaro.org/mailman/listinfo/lng-odp >>> >>> >>> >>> > > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org > https://lists.linaro.org/mailman/listinfo/lng-odp > >
diff --git a/include/odp/api/packet_io.h b/include/odp/api/packet_io.h index 89356a6..b97b2b8 100644 --- a/include/odp/api/packet_io.h +++ b/include/odp/api/packet_io.h @@ -111,7 +111,9 @@ int odp_pktio_recv(odp_pktio_t pktio, odp_packet_t pkt_table[], int len); * @param pkt_table[] Array of packets to send * @param len length of pkt_table[] * - * @return Number of packets sent + * @return Number of packets sent. If it is less than 'len', the remaining + * packets at the end of pkt_table[] are left intact, and caller has to take + * care of them. * @retval <0 on failure */ int odp_pktio_send(odp_pktio_t pktio, odp_packet_t pkt_table[], int len);
Currently our examples are not handling this situation as well. Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org> --- include/odp/api/packet_io.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)