<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<p><font face="Ubuntu">Jeff,</font></p>
<p><font face="Ubuntu">We don't yet conduct performance impact
because we are considering it as negligible.</font></p>
<p><font face="Ubuntu">Indeed, a label is 4 bytes. 16 labels = 64
bytes, so equivalent to a IP + TCP header, or an IPv6 header,
so comparable to what's the Kernel do when it uses Ipv4 into
IPv6 GRE tunnel or VxLan encapsulation or equivalent
encapsulation. And 16 labels is the maximum necessary to express
100,00% of routes disregarding the network topologies we tested.<br>
</font></p>
<p><font face="Ubuntu">In addition, this encapsulation is done at
the Edge. Then, only PoP of top of stack is performed by
subsequent router independently of the size of label stack.</font></p>
<p><font face="Ubuntu">IMHO, the impact is on the total size of the
packet. The overhead introduced by the stack of labels will
reduce the goodput of the connexion, but not much more than
other kind of encapsulation.</font></p>
<p><font face="Ubuntu">Regards</font></p>
<p><font face="Ubuntu">Olivier</font><br>
</p>
<br>
<div class="moz-cite-prefix">Le 23/03/2017 à 18:32, Jeff Tantsura a
écrit :<br>
</div>
<blockquote
cite="mid:BECDAC1F-289A-4D6E-996D-ACC9309F57D0@gmail.com"
type="cite">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
Haha :)
<div class=""><br class="">
</div>
<div class="">On a serious note - what are the implications of
increasing labels stack (latency/throughput/etc)?</div>
<div class="">Where is the sweet spot?</div>
<div class="">
<div class="">
<br class="Apple-interchange-newline">
<span style="color: rgb(0, 0, 0); font-family: Helvetica;
font-size: 12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent: 0px;
text-transform: none; white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width: 0px; display:
inline !important; float: none;" class="">Cheers,</span><br
style="color: rgb(0, 0, 0); font-family: Helvetica;
font-size: 12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent: 0px;
text-transform: none; white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
<span style="color: rgb(0, 0, 0); font-family: Helvetica;
font-size: 12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent: 0px;
text-transform: none; white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width: 0px; display:
inline !important; float: none;" class="">Jeff</span><br
style="color: rgb(0, 0, 0); font-family: Helvetica;
font-size: 12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent: 0px;
text-transform: none; white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
<br style="color: rgb(0, 0, 0); font-family: Helvetica;
font-size: 12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent: 0px;
text-transform: none; white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
</div>
<br class="">
<div>
<blockquote type="cite" class="">
<div class="">On Mar 23, 2017, at 10:28, <<a
moz-do-not-send="true"
href="mailto:olivier.dugeon@orange.com" class="">olivier.dugeon@orange.com</a>>
<<a moz-do-not-send="true"
href="mailto:olivier.dugeon@orange.com" class="">olivier.dugeon@orange.com</a>>
wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div bgcolor="#FFFFFF" text="#000000" class="">
<p class=""><i class=""><font class="" face="Ubuntu">grep
'#define MAX_NEW_LABELS' internal.h | awk -e
'{print $3}'</font></i></p>
<p class="">But I'm not sure it answers your question <span
class="moz-smiley-s3"><span class="">;-)</span></span><br
class="">
</p>
<p class="">Olivier<br class="">
</p>
<br class="">
<div class="moz-cite-prefix">Le 23/03/2017 à 18:21, Jeff
Tantsura a écrit :<br class="">
</div>
<blockquote
cite="mid:05006AE4-B015-4442-B095-53B354CDC973@gmail.com"
type="cite" class=""> while on topic, can I please get
an API to query data plane for MSD supported?
<div class="">Use
case: draft-ietf-isis-segment-routing-msd/ draft-ietf-ospf-segment-routing-msd/ draft-tantsura-idr-bgp-ls-segment-routing-msd<br
class="">
<div class="">
<div class=""><br class="webkit-block-placeholder">
</div>
<div class=""> Many thanks!</div>
<div class=""><br
class="Apple-interchange-newline">
<span style="font-family: Helvetica; font-size:
12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing:
normal; orphans: auto; text-align: start;
text-indent: 0px; text-transform: none;
white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width:
0px; float: none; display: inline !important;"
class="">Cheers,</span><br style="font-family:
Helvetica; font-size: 12px; font-style:
normal; font-variant-caps: normal;
font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent:
0px; text-transform: none; white-space:
normal; widows: auto; word-spacing: 0px;
-webkit-text-stroke-width: 0px;" class="">
<span style="font-family: Helvetica; font-size:
12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing:
normal; orphans: auto; text-align: start;
text-indent: 0px; text-transform: none;
white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width:
0px; float: none; display: inline !important;"
class="">Jeff</span><br style="font-family:
Helvetica; font-size: 12px; font-style:
normal; font-variant-caps: normal;
font-weight: normal; letter-spacing: normal;
orphans: auto; text-align: start; text-indent:
0px; text-transform: none; white-space:
normal; widows: auto; word-spacing: 0px;
-webkit-text-stroke-width: 0px;" class="">
<br style="font-family: Helvetica; font-size:
12px; font-style: normal; font-variant-caps:
normal; font-weight: normal; letter-spacing:
normal; orphans: auto; text-align: start;
text-indent: 0px; text-transform: none;
white-space: normal; widows: auto;
word-spacing: 0px; -webkit-text-stroke-width:
0px;" class="">
</div>
<br class="">
<div class="">
<blockquote type="cite" class="">
<div class="">On Mar 23, 2017, at 10:07,
Vincent Jardin <<a moz-do-not-send="true"
href="mailto:vincent.jardin@6wind.com"
class="">vincent.jardin@6wind.com</a>>
wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div class="">
<div style="" class="">
<p style="margin: 0px 0px 1em;" class="">+Jeff</p>
<div style="margin: 0px 0px 1em;
font-family: sans-serif;" class=""><br
class="webkit-block-placeholder">
</div>
<p style="margin: 0px 0px 1em;
font-family: sans-serif;" class="">Le
23 mars 2017 5:59:21 PM Amine
Kherbouche <<a
moz-do-not-send="true"
href="mailto:amine.kherbouche@6wind.com"
class="">amine.kherbouche@6wind.com</a>>
a écrit :</p>
<p style="margin: 0px 0px 1em;
font-family: sans-serif;" class="">>
Hi David,<br class="">
><br class="">
> I think that 8 stacked labels are
more than enough, I cannot imagine a
core<br class="">
> network with 8 stacked MPLS-VPNs.<br
class="">
> Let's see the others if they
share my opinions.</p>
<p style="margin: 0px 0px 1em;" class=""><br
class="">
</p>
<p style="margin: 0px 0px 1em;" class="">I
think too that 8 is a good upper
limit. </p>
<p style="margin: 0px 0px 1em;
font-family: sans-serif;" class=""><br
class="">
><br class="">
><br class="">
> Regards,<br class="">
> Amine<br class="">
><br class="">
> On 23 March 2017 at 17:47, David
Ahern <<a moz-do-not-send="true"
href="mailto:dsa@cumulusnetworks.com"
class="">dsa@cumulusnetworks.com</a>>
wrote:<br class="">
><br class="">
>> I have the MPLS code changes
to bump the number of labels. What did
we<br class="">
>> want to use for the max? 12?
16?<br class="">
>><br class="">
>> This limit is really only
capping what we take from userspace.
Kernel<br class="">
>> side memory allocations are
done based on the actual number of
labels in<br class="">
>> the route.<br class="">
>><br class="">
>><br class="">
>> On 3/16/17 10:49 AM, Olivier
Dugeon wrote:<br class="">
>> > Hi David,<br class="">
>> ><br class="">
>> > Well, frankly speaking,
I don't see where is the problem
regarding the<br class="">
>> > performance.<br class="">
>> ><br class="">
>> > IMHO, the patch add an
extra size of the array i.e. from 8
bytes (2<br class="">
>> > labels) to 64 bytes (16
labels) which is completely negligible
compared<br class="">
>> > to the size of a IP
packet, and of same magnitude order as
a VxLan<br class="">
>> > encapsulation and twice
less as an IPv6 header.<br class="">
>> ><br class="">
>> > In addition, only the
edge router as to push the label
stack. Then,<br class="">
>> > subsequent router just
look at the top label. So, no more no
less that a<br class="">
>> > packet with only 2
labels in the stack.<br class="">
>> ><br class="">
>> > I think that dealing
with a dynamic MPLS STACK DEPTH i.e.
dynamic memory<br class="">
>> > allocation of space
regarding the number of labels are
push in from of<br class="">
>> > the IP packet will
certainly add more overhead and more
CPU cycles<br class="">
>> > rather than just manage
a fix amount of byte in an array.<br
class="">
>> ><br class="">
>> > Finally, the default
value for the MPLS_LABEL_STACK could
be equal to 2<br class="">
>> > and let peoples want to
deal with Segment Routing recompile
the kernel<br class="">
>> > with a larger value.<br
class="">
>> ><br class="">
>> > From my side, your patch
will not only increase the label
stack, it also<br class="">
>> > re-arrange the MPLS
structure in order to solve the
problem of corrupted<br class="">
>> > third label. And, this
is the more important things.<br
class="">
>> ><br class="">
>> > In any case, let me know
what I can do to help you.<br class="">
>> ><br class="">
>> > Regards<br class="">
>> ><br class="">
>> > Olivier<br class="">
>> ><br class="">
>> ><br class="">
>> > Le 16/03/2017 à 16:10,
David Ahern a écrit :<br class="">
>> >> I made the kernel
patch to help you move along with your
MPLS work.<br class="">
>> >><br class="">
>> >> In the kernel thread
discussing the increase in number of
labels Eric<br class="">
>> >> Biederman mentions
performance concerns about just
increasing the size<br class="">
>> >> of the array; he
wanted a much more complicated change
and I have not<br class="">
>> >> gotten around to it.<br
class="">
>> >><br class="">
>> >><br class="">
>> >> On 3/16/17 3:31 AM,
Olivier Dugeon wrote:<br class="">
>> >>> Hi all,<br
class="">
>> >>><br class="">
>> >>> The problem is
not between the kernel and iproute2.
The problem comes<br class="">
>> >>> when stacking
more than 2 labels: the LSB byte of
the third label is<br class="">
>> >>> replaced by 0x03
value i.e. the implicit Null Label
value. See attached<br class="">
>> >>> thread.<br
class="">
>> >>><br class="">
>> >>> Following this,
David propose a new patch that we
integrated and tested<br class="">
>> >>> successfully
(See second and third attached mail).<br
class="">
>> >>><br class="">
>> >>> But, after that,
I got no news and never seen this
patch merge into the<br class="">
>> >>> Linux Kernel
release. So, we just ask when this
patch could be merge<br class="">
>> >>> into the Linux
Kernel.<br class="">
>> >>><br class="">
>> >>> For the second
problem about PHP, it is also
described in the first<br class="">
>> >>> attached thread.
But, agree, that this issue is more
tricking to solve.<br class="">
>> >>><br class="">
>> >>> Regards,<br
class="">
>> >>><br class="">
>> >>> Olivier<br
class="">
>> >>><br class="">
>> >>><br class="">
>> >>> Le 15/03/2017 à
16:59, David Ahern a écrit :<br
class="">
>> >>>> On 3/15/17
9:57 AM, Amine Kherbouche wrote:<br
class="">
>> >>>>> >
1) More than 2 labels in the kernel at
a time, when will this<br class="">
>> be<br class="">
>> >>>>> >
allowed in the kernel?<br class="">
>> >>>>> ><br
class="">
>> >>>>><br
class="">
>> >>>>> I don't
understand why iproute2 and kernel are
not sync when it<br class="">
>> comes to<br class="">
>> >>>>> the max
stacked labels, iproute2 should export
kernel headers.<br class="">
>> >>>>><br
class="">
>> >>>> <a
moz-do-not-send="true"
href="https://marc.info/?l=linux-netdev&m=146913202123729&w=2"
class="">https://marc.info/?l=linux-netdev&m=146913202123729&w=2</a><br
class="">
>> >>>><br class="">
>> ><br class="">
>><br class="">
><br class="">
><br class="">
><br class="">
> -- <br class="">
> Amine<br class="">
><br class="">
><br class="">
><br class="">
> ----------<br class="">
>
_______________________________________________<br
class="">
> frr mailing list<br class="">
> <a moz-do-not-send="true"
href="mailto:frr@lists.nox.tf"
class="">frr@lists.nox.tf</a><br
class="">
> <a moz-do-not-send="true"
href="https://lists.nox.tf/listinfo/frr"
class="">https://lists.nox.tf/listinfo/frr</a><br
class="">
</p>
</div>
</div>
</div>
</blockquote>
</div>
<br class="">
</div>
</div>
<br class="">
<fieldset class="mimeAttachmentHeader"></fieldset>
<br class="">
<pre class="" wrap="">_______________________________________________
frr mailing list
<a moz-do-not-send="true" class="moz-txt-link-abbreviated" href="mailto:frr@lists.nox.tf">frr@lists.nox.tf</a>
<a moz-do-not-send="true" class="moz-txt-link-freetext" href="https://lists.nox.tf/listinfo/frr">https://lists.nox.tf/listinfo/frr</a>
</pre>
</blockquote>
<br class="">
<pre class="">_________________________________________________________________________________________________________________________
Ce message et ses pieces jointes peuvent contenir des informations confidentielles ou privilegiees et ne doivent donc
pas etre diffuses, exploites ou copies sans autorisation. Si vous avez recu ce message par erreur, veuillez le signaler
a l'expediteur et le detruire ainsi que les pieces jointes. Les messages electroniques etant susceptibles d'alteration,
Orange decline toute responsabilite si ce message a ete altere, deforme ou falsifie. Merci.
This message and its attachments may contain confidential or privileged information that may be protected by law;
they should not be distributed, used or copied without authorisation.
If you have received this email in error, please notify the sender and delete this message and its attachments.
As emails may be altered, Orange is not liable for messages that have been modified, changed or falsified.
Thank you.
</pre>
</div>
</div>
</blockquote>
</div>
<br class="">
</div>
</blockquote>
<br>
<PRE>_________________________________________________________________________________________________________________________
Ce message et ses pieces jointes peuvent contenir des informations confidentielles ou privilegiees et ne doivent donc
pas etre diffuses, exploites ou copies sans autorisation. Si vous avez recu ce message par erreur, veuillez le signaler
a l'expediteur et le detruire ainsi que les pieces jointes. Les messages electroniques etant susceptibles d'alteration,
Orange decline toute responsabilite si ce message a ete altere, deforme ou falsifie. Merci.
This message and its attachments may contain confidential or privileged information that may be protected by law;
they should not be distributed, used or copied without authorisation.
If you have received this email in error, please notify the sender and delete this message and its attachments.
As emails may be altered, Orange is not liable for messages that have been modified, changed or falsified.
Thank you.
</PRE></body>
</html>