-----Original Message-----
From: [email protected] <[email protected]>
Sent: Wednesday, May 06, 2020 10:10 AM
To: Christian Hopps <[email protected]>
Cc: Les Ginsberg (ginsberg) <[email protected]>; [email protected]
Subject: RE: [Lsr] Flooding across a network
From: Christian Hopps [mailto:[email protected]]
Bruno persistence has made me realize something fundamental here.
The minute the LSP originator changes the LSP and floods it you have LSDB
inconsistency.
Exactly my point. Thank you Chris.
I would even say: "The minute the LSP originator changes the LSP then you
have LSDB inconsistency." But no big deal if there is disagreement on this
detail.
That is going to last until the last node in the network has updated it's LSDB.
Absolutely.
So the faster we flood, the shorter the LSBD inconsistency.
Now IMO, even if a single/few nodes flood faster, there is a chance of
shortening the LSDB inconsistency. But in all cases, I don't see how this could
make the LSDB inconsistency longer.
Les is pointing out that LSDB inconsistency can be bad in certain
circumstances e.g., if a critical node is slow and thus inconsistent.
I believe the right way to fix this is a simple one, help the operator flag the
broken router software/hardware for replacement, but otherwise IS-IS
should just try to do the best job it can do to which is to flood around the
problem (i.e., flood as optimally as possible).
+1
On a side note, I would not call a router flooding slowly as "broken". I find it
understandable that in a given network there are different type of routers
(core vs aggregation), different roles (P having 50 IGP adjacencies with 50 PEs
vs PE having only 2 IGP adjacencies with 2 P), different hardware
generations, different software, different vendors with different
perspectives/markets.
Thank you Chris.
--Bruno
Thanks,
Chris.
[as WG member]
On May 6, 2020, at 10:33 AM, [email protected] wrote:
Les,
From: Les Ginsberg (ginsberg) [mailto:[email protected]]
Sent: Wednesday, May 6, 2020 4:14 PM
To: DECRAENE Bruno TGI/OLN
Cc: [email protected]
Subject: RE: Flooding across a network
Bruno –
I am somewhat at a loss to understand your comments.
The example is straightforward and does not need to consider FIB update
time nor the ordering of prefix updates on different nodes.
[Bruno] The example is straightforward but you are referring to FIB and IP
packets forwarding as per those FIBs.
I’d like we focus on LSP flooding and LSDB consistency.
Consider the state of Node B and Node D at various time points from the
trigger event.
T+ 2 seconds:
-----------------
B has received all LSP Updates. It triggers an SPF and for all Northbound
destinations previously reachable via C it installs paths via D.
Let’s assume it take 5 seconds to update the forwarding plane.
D has received 40 of the 1000 LSP updates. It triggers an SPF and finds
that all Northbound destinations are reachable via B-C. It makes no changes
to the forwarding plane.
T+7 seconds
-----------------
B has completed FIB updates. Traffic to all Northbound destinations is
being forwarded via D.
D has now received 140 of the 1000 LSP updates. Entries in its forwarding
plane for Northbound destinations still point to B.
We have a loop.
T + 30 seconds
--------------------
D has now received 600 of the 1000 LSP updates. Still no changes to its
forwarding plane.
Traffic to Northbound destinations is still looping.
T+ 50 seconds
-------------------
D has finally received all 1000 LSP updates..
It triggers (another) SPF and calculates paths to Northbound destinations
via E. It begins to update its forwarding plane.
Let’s assume this will take 5 seconds..
T + 55 seconds
--------------------
D has completed forwarding plane updates – no more looping.
That is all I am trying to illustrate.
If you want to start arguing that node protecting LFAs + microloop
avoidance could help (NOTE I explicitly took those out of the example for
simplicity) – it is easy enough to change the example to include multiple node
failures or a node failure plus some northbound link failures on other nodes.
[Bruno] I’m not talking about LFA/FRR. And with regards to microloops
avoidance, some algorithms can handle any graph transition so including
multiple node failures.
But again, let’s stick to LSP flooding and LSDB consistency. (you are the
one speaking about microloops in the forwarding plane).
The point here is to look at the impact of long-lived LSDB inconsistency
which results when some nodes support flooding an order of magnitude
faster flooding than other nodes – which is what you asked me to clarify.
[Bruno] No. I asked you to clarify why having a node with faster flooding
could prolongs the period of LSDB inconsistency.
Again, with you own words: “when only some nodes in the network
support faster flooding the behavior of the whole network may not be
"better" when faster flooding is enabled because it prolongs the period of
LSDB inconsistency.”
And with less words: “when only some nodes in the network support
faster flooding […] it prolongs the period of LSDB inconsistency.”
--Bruno
Les
From: [email protected] <[email protected]>
Sent: Wednesday, May 06, 2020 6:21 AM
To: Les Ginsberg (ginsberg) <[email protected]>
Cc: [email protected]
Subject: RE: Flooding across a network
Les,
From: Les Ginsberg (ginsberg) [mailto:[email protected]]
Sent: Wednesday, May 6, 2020 1:35 AM
To: DECRAENE Bruno TGI/OLN; [email protected]
Subject: RE: Flooding across a network
Bruno -
Seems like it was not too long ago that we were discussing this in person.
Ahhh...the good old days...
[Bruno] Indeed, may be not to the point of concluding. Indeed.
First, let's agree that the interesting case does not involve 1 or even a
small number of LSPs. For those cases flooding speed does not matter.
The interesting cases involve a large number of LSPs (hundreds or
thousands). And in such cases LFA/microloop avoidance techniques are not
applicable.
Take the following simple topology:
| | ... | |
+---+ +---+
| C | | E |
+---+ +---+
| | 1000
+---+ +---+
| B |-------------| D |
+---+ 1000 +---+
| |
| |
\ /
\ /
\ /
\ /
+---+
| A |
+---+
There is a topology northbound of C and E (not shown) and a topology
southbound of A (not shown).
Cost on all links is 10 except B-D and D-E where cost is high.
C is a node with 1000 neighbors.
When all links are up, shortest path for all northbound destinations is via
C.
All nodes in the network support fast flooding except for Node D.
Let’s say fast flooding is 500 LSPs/second and slow flooding (Node D) is 20
LSPs/seconds.
If Node C fails we have 1000 LSPs to flood.
All nodes except for D can receive these in 2 seconds (plus internode
delay time).
D can receive LSPs in 50 seconds.
[Bruno] Thanks for your example. Agreed so far.
When A and B and all southbound nodes receive/process the LSP
updates they will start sending traffic to Northbound destinations via D.
But for the better part of 50 seconds, Node D has yet to receive all LSP
updates and still believes that shortest path is via B-C. It will loop traffic.
[Bruno] May I remind you that we are discussing IS-IS flooding in order to
sync LSDB (LSP database). That is already a big enough subject. It does not
including FIB (updates), nor IP forwarding.
Quoting you “when only some nodes in the network support faster
flooding the behavior of the whole network may not be "better" when faster
flooding is enabled because it prolongs the period of LSDB inconsistency.”
Taking your own examples, in both cases (all nodes support fast flooding;
all nodes but D support fast flooding) the period of LSDB inconsistency is 50
seconds. Hence this example does not illustrate your statement.
Hence I’m restating my questions:
when only some nodes in the network support faster flooding the
behavior
of the whole network may not be "better" when faster flooding is
enabled
because it prolongs the period of LSDB inconsistency.
1) Do you have data on this?
2) If not, can you provide an example where increasing the flooding
rate on
one adjacency prolongs the period of LSDB inconsistency across the
network?
Had all nodes used slow flooding, it still would have taken 50 seconds to
converge, but there would be significantly less looping. There could be a
good amount of blackholing, but this is preferable to looping.
[Bruno] You are using an example where ordering FIB updates across the
network, e.g. as per [1], allows to reduce _FIB_ inconsistency across the
path/network. And you seem to conclude from this that this translates to
LSDB update ordering. Those are two different things. In this thread, I’d
suggest that we focus on IGP flooding and LSDB sync only. (*)
[1] https://tools.ietf.org/html/rfc6976
(*) We can discuss loop free IGP converge in a different thread if you
want. IMO, the use of segment routing/source routing is better than oFIB.
But at some point, it still relies on fast flooding when multiple LSPs are
involved. (and I mean _fast_ not _ordered_)
--Bruno
One can always come up with examples – based on a specific topology
and a specific failure - where things might be better/worse/unchanged in the
face of inconsistent flooding speed support.
But I hope this simple example illustrates the pitfalls.
Les
-----Original Message-----
From: [email protected] <[email protected]>
Sent: Tuesday, May 05, 2020 8:28 AM
To: Les Ginsberg (ginsberg) <[email protected]>; [email protected]
Subject: Flooding across a network
Les,
From: Lsr [mailto:[email protected]] On Behalf Of Les Ginsberg
(ginsberg)
Sent: Monday, May 4, 2020 4:39 PM
[...]
when only some nodes in the network support faster flooding the
behavior
of the whole network may not be "better" when faster flooding is
enabled
because it prolongs the period of LSDB inconsistency.
1) Do you have data on this?
2) If not, can you provide an example where increasing the flooding
rate on
one adjacency prolongs the period of LSDB inconsistency across the
network?
3) In the meantime, let's try the theoretical analysis on a simple
scenario
where a single LSP needs to be flooded across the network.
- Let's call Dij the time needed to flood the LSP from node i to the
adjacent
node j. Clearly Dij>0.
- Let's call k the node originating this LSP at t0=0s
>From t0, the LSDB is inconsistent across the network as all nodes but k
are
missing the LSP and hence only know about the 'old' topology.
Let's call SPT(k) the SPT rooted on k, using Dij as the metric between
adjacent nodes i and j. Let's call SP(k,i) the shortest path from k to i; and
D(k,i) the shortest distance between k and i.
It seems that the time needed:
- for node j to learn about the LSP, and get in sync with k, is D(k,j)
- for all nodes across the network to learn about the LSP, and get in sync
with
k, is Max[for all j] D(k,j)
Then how can reducing the flooding delay on one adjacency could
prolongs
the period of LSDB inconsistency?
It seems to me that it can only improve/decrease it. Otherwise, this
would
mean that decreasing the cost on a link can increase the cost of the
shortest
path.
Note: I agree that there are other cases, such as multiple LSPs
originated by
the same node, and multiple LSPs originated by multiple nodes, but
let's start
with the simple case.
Thanks,
--Bruno
-----Original Message-----
From: Lsr [mailto:[email protected]] On Behalf Of Les Ginsberg
(ginsberg)
Sent: Monday, May 4, 2020 4:39 PM
Henk -
Thanx for your thoughtful posts.
I have read your later posts on this thread as well - but decided to
reply to
this one.
Top posting for better readability.
There is broad agreement that faster flooding is desirable.
There are now two proposals as to how to address the issue - neither
of
which is proposing to use TCP (or equivalent).
I have commented on why IS-IS flooding requirements are
significantly
different than that for which TCP is used.
I think it is also useful to note that even the simple test case which
Bruno
reported on in last week's interim meeting demonstrated that without
any
changes to the protocol at all IS-IS was able to flood an order of
magnitude
faster than it commonly does today.
This gives me hope that we are looking at the problem correctly and
will not
need "TCP".
Introducing a TCP based solution requires:
a)A major change to the adjacency formation logic
b)Removal of the independence of the IS-IS protocol from the
address
families whose reachability advertisements it supports - something
which I
think is a great strength of the protocol - particularly in environments
where
multiple address family support is needed
I really don't want to do either of the above.
Your comments regarding PSNP response times are quite correct -
and
both of the draft proposals discuss this - though I agree more detail will
be
required.
It is intuitive that if you want to flood faster you also need to ACK
faster -
and probably even retransmit faster when that is needed.
The basic relationship between retransmit interval and PSNP interval
is
expressed in ISO 10589:
" partialSNPInterval - This is the amount of time between periodic
> action for transmission of Partial Sequence Number PDUs.
> It shall be less than minimumLSPTransmission-Interval."
Of course ISO 10589 recommended values (2 seconds and 5 seconds
respectively) associated with a much slower flooding rate and
implementations I am aware of use values in this order of magnitude.
These
numbers need to be reduced if we are to flood faster, but the
relationship
between the two needs to remain the same.
It is also true - as you state - that sending ACKs more quickly will result
in
additional PDUs which need to be received/processed by IS-IS - and this
has
some impact. But I think it is reasonable to expect that an
implementation
which can support sending and receiving LSPs at a faster rate should
also be
able to send/receive PSNPs at a faster rate. But we still need to be
smarter
than sending one PSNP/one LSP in cases where we have a burst.
LANs are a more difficult problem than P2P - and thus far draft-
ginsberg-lsr-
isis-flooding-scale has been silent on this - but not because we aren't
aware
of this - just have focused on the P2P behavior first.
What the best behavior on a LAN may be is something I am still
considering.
Slowing flooding down to the speed at which the slowest IS on the LAN
can
support may not be the best strategy - as it also slows down the
propagation
rate for systems downstream from the nodes on the LAN which can
handle
faster flooding - thereby having an impact on flooding speed
throughout the
network in a way which may be out of proportion. This is a smaller
example
of the larger issue that when only some nodes in the network support
faster
flooding the behavior of the whole network may not be "better" when
faster
flooding is enabled because it prolongs the period of LSDB
inconsistency.
More work needs to be done here...
In summary, I don't expect to have to "reinvent TCP" - but I do think
you
have provided a useful perspective for us to consider as we progress on
this
topic,
Thanx.
> Les
-----Original Message-----
From: Lsr <[email protected]> On Behalf Of Henk Smit
Sent: Thursday, April 30, 2020 6:58 AM
To: [email protected]
Subject: [Lsr] Why only a congestion-avoidance algorithm on the
sender
isn't
enough
Hello all,
Two years ago, Gunter Van de Velde and myself published this
draft:
https://tools.ietf.org/html/draft-hsmit-lsr-isis-flooding-over-tcp-00
That started this discussion about flow/congestion control and ISIS
flooding.
My thoughts were that once we start implementing new algorithms
to
optimize ISIS flooding speed, we'll end up with our own version of
TCP.
I think most people here have a good general understanding of TCP.
But if not, this is a good overview how TCP does it:
https://en.wikipedia.org/wiki/TCP_congestion_control
What does TCP do:
====
TCP does 2 things: flow control and congestion control.
1) Flow control is: the receiver trying to prevent itself from being
overloaded. The receiver indicates, through the receiver-window-
size
in the TCP acks, how much data it can or wants to receive.
2) Congestion control is: the sender trying to prevent the links
between
sender and receiver from being overloaded. The sender makes an
educated
guess at what speed it can send.
The part we seem to be missing:
====
For the sender to make a guess at what speed it can send, it looks at
how the transmission is behaving. Are there drops ? What is the RTT
?
Do drop-percentage and RTT change ? Do acks come in at the same
rate
as the sender sends segments ? Are there duplicate acks ? To be
able
to do this, the sender must know what to expect. How acks behave.
If you want an ISIS sender to make a guess at what speed it can
send,
without changing the protocol, the only thing the sender can do is
look
at the PSNPs that come back from the receiver. But the RTT of
PSNPs can
not be predicted. Because a good ISIS implementation does not
immediately
send a PSNP when it receives a LSP. 1) the receiver should jitter the
PSNP,
like it should jitter all packets. And 2) the receiver should wait a
little
to see if it can combine multiple acks into a single PSNP packet.
In TCP, if a single segment gets lost, each new segment will cause
the
receiver to send an ack with the seqnr of the last received byte. This
is called "duplicate acks". This triggers the sender to do
fast-retransmission. In ISIS, this can't be be done. The information
a sender can get from looking at incoming PSNPs is a lot less than
what
TCP can learn from incoming acks.
The problem with sender-side congestion control:
====
In ISIS, all we know is that the default retransmit-interval is 5
seconds.
And I think most implementations use that as the default. This
means
that
the receiver of an LSP has one requirement: send a PSNP within 5
seconds.
For the rest, implementations are free to send PSNPs however and
whenever
they want. This means a sender can not really make conclusions
about
flooding speed, dropped LSPs, capacity of the receiver, etc.
There is no ordering when flooding LSPs, or sending PSNPs. This
makes
a sender-side algorithm for ISIS a lot harder.
When you think about it, you realize that a sender should wait the
full 5 seconds before it can make any real conclusions about
dropped
LSPs.
If a sender looks at PSNPs to determine its flooding speed, it will
probably
not be able to react without a delay of a few seconds. A sender
might
send
hunderds or thousands of LSPs in those 5 seconds, which might all
or
partially be dropped, complicating matters even further.
A sender-sider algorithm should specify how to do PSNPs.
====
So imho a sender-side only algorithm can't work just like that in a
multi-vendor environment. We must not only specify a congestion-
control
algorithm for the sender. We must also specify for the receiver a
more
specific algorithm how and when to send PSNPs. At least how to do
PSNPs
under load.
Note that this might result in the receiver sending more (and
smaller)
PSNPs.
More packets might mean more congestion (inside routers).
Will receiver-side flow-control work ?
====
I don't know if that's enough. It will certainly help.
I think to tackle this problem, we need 3 parts:
1) sender-side congestion-control algorithm
2) more detailed algorithm on receiver when and how to send
PSNPs
3) receiver-side flow-control mechanism
As discussed at length, I don't know if the ISIS process on the
receiving
router can actually know if its running out of resources (buffers on
interfaces, linecards, etc). That's implementation dependent. A
receiver
can definitely advertise a fixed value. So the sender has an upper
bound
to use when doing congestion-control. Just like TCP has both a
flow-control
window and a congestion-control window, and a sender uses both.
Maybe
the
receiver can even advertise a dynamic value. Maybe now, maybe
only in
the
future. An advertised upper limit seems useful to me today.
What I didn't like about our own proposal (flooding over TCP):
====
The problem I saw with flooding over TCP concerns multi-point
networks
(LANs).
When flooding over a multi-point network, setting up TCP
connections
introduces serious challenges. Who are the endpoints of the TCP
connections ?
Full mesh ? Or do all ISes on a LAN create a TCP-connection to the
DIS ?
There is no backup DIS in ISIS (unlike OSPF). Things get messy
quickly.
However, the other two proposals do not solve this problem either.
How will a sender-side congestion-avoidence algorithm determine
whether
there were drops ? There are no acks (PSNPs) on a LAN. We assume
most
LSPs
that are broadcasted are received by all other ISes on the LAN.
There
are
no acks. Only after the DIS has sent its periodic CSNPs, ISes can send
PSNPs to request retransmissions. It seems impossible (or very
hard) to
me for all ISes on a LAN to keep track of dropped LSPs and adjust
their
sending speed accordingly..
When flooding on a LAN, the receiver-side algorithm seems best.
Because
all ISes can see what the lowest advertised sending-speed is. And
make
sure they send slow enough to not overload the slowest IS. I'm not
sure
this is a good solution, but is seems easier and more realistic than
ISIS-flooding-over-TCP or sender-side congestion-avoidance.
My conclusion:
====
Sender-side congestion-control won't work without specifying in
more
detail how and when to send PSNPs.
Receiver-side flow-control will certainly help. I dont' know if it's
good enough. I don't know if advertising a static value is good
enough.
But it's a start.
I still think we'll end up re-implementing a new (and weaker) TCP.
henk.
_______________________________________________
Lsr mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/lsr
_______________________________________________
Lsr mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/lsr
__________________________________________________________
__________________________________________________________
_____
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.
__________________________________________________________
__________________________________________________________
_____
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.
__________________________________________________________
__________________________________________________________
_____
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.
_______________________________________________
Lsr mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/lsr
__________________________________________________________
__________________________________________________________
_____
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.
