.TH TORUS\-2QOS 8 "November 10, 2010" "OpenIB" "OpenIB Management"
.
.SH NAME
torus\-2QoS \- Routing engine for OpenSM subnet manager
.
.SH DESCRIPTION
.
Torus-2QoS is routing algorithm designed for large-scale 2D/3D torus fabrics.
The torus-2QoS routing engine can provide the following functionality on
a 2D/3D torus:
.br
\" roff illiteracy leads to following brain-dead list implementation
\"
.na \" otherwise line space adjustment can add spaces between dash and text
.in +2m
\[en]
'in +2m
Routing that is free of credit loops.
.in
\[en]
'in +2m
Two levels of Quality of Service (QoS), assuming switches support eight
data VLs and channel adapters support two data VLs.
.in
\[en]
'in +2m
The ability to route around a single failed switch, and/or multiple failed
links, without
.in
.in +2m
\[en]
'in +2
introducing credit loops, or
.in
\[en]
'in +2m
changing path SL values.
.in -4m
\[en]
'in +2m
Very short run times, with good scaling properties as fabric size increases.
.ad
.
.SH UNICAST ROUTING
.
Unicast routing in torus-2QoS is based on Dimension Order Routing (DOR).
It avoids the deadlocks that would otherwise occur in a DOR-routed
torus using the concept of a dateline for each torus dimension.
It encodes into a path SL which datelines the path crosses, as follows:
\f(CR
.P
.nf
sl = 0;
for (d = 0; d < torus_dimensions; d++) {
/* path_crosses_dateline(d) returns 0 or 1 */
sl |= path_crosses_dateline(d) << d;
}
.fi
\fR
.P
On a 3D torus this consumes three SL bits, leaving one SL bit unused.
Torus-2QoS uses this SL bit to implement two QoS levels.
.P
Torus-2QoS also makes use of the output port
dependence of switch SL2VL maps to encode into one VL bit the
information encoded in three SL bits.
It computes in which torus coordinate direction each inter-switch link
"points", and writes SL2VL maps for such ports as follows:
\f(CR
.P
.nf
for (sl = 0; sl < 16; sl++) {
/* cdir(port) computes which torus coordinate direction
* a switch port "points" in; returns 0, 1, or 2
*/
sl2vl(iport,oport,sl) = 0x1 & (sl >> cdir(oport));
}
.fi
\fR
.P
Thus, on a pristine 3D torus,
\fIi.e.\fR,
in the absence of failed fabric switches,
torus-2QoS consumes eight SL values (SL bits 0-2) and
two VL values (VL bit 0) per QoS level to provide deadlock-free routing.
.P
Torus-2QoS routes around link failure by "taking the long way around" any
1D ring interrupted by link failure. For example, consider the 2D 6x5
torus below, where switches are denoted by [+a-zA-Z]:
.
.
\# define macros to start and end ascii art, assuming Roman font.
\# the start macro takes an argument which is the width in ems of
\# the ascii art, and is used to center it.
\#
.de ascii_art
.nop \f(CR
.nr indent_in_ems ((((\\n[.ll] - \\n[.i]) / \\w'm') - \\$1)/2)
.in +\\n[indent_in_ems]m
.nf
..
.de end_ascii_art
.fi
.in
.nop \fR
..
\# end of macro definitions
.
.
.ascii_art 36
| | | | | |
4 --+----+----+----+----+----+--
| | | | | |
3 --+----+----+----D----+----+--
| | | | | |
2 --+----+----I----r----+----+--
| | | | | |
1 --m----S----n----T----o----p--
| | | | | |
y=0 --+----+----+----+----+----+--
| | | | | |
x=0 1 2 3 4 5
.end_ascii_art
.P
For a pristine fabric the path from S to D would be S-n-T-r-D.
In the event that either link S-n or n-T has failed, torus-2QoS would
use the path S-m-p-o-T-r-D.
Note that it can do this without changing the path SL
value; once the 1D ring m-S-n-T-o-p-m has been broken by failure, path
segments using it cannot contribute to deadlock, and the x-direction
dateline (between, say, x=5 and x=0) can be ignored for path segments on
that ring.
.P
One result of this is that torus-2QoS can route around many simultaneous
link failures, as long as no 1D ring is broken into disjoint segments.
For example, if links n-T and T-o have both failed, that ring has been broken
into two disjoint segments, T and o-p-m-S-n.
Torus-2QoS checks for such
issues, reports if they are found, and refuses to route such fabrics.
.P
Note that in the case where there are multiple parallel links between a
pair of switches, torus-2QoS will allocate routes across such links
in a round-robin fashion, based on ports at the path destination switch that
are active and not used for inter-switch links.
Should a link that is one of several such parallel links fail, routes
are redistributed across the remaining links.
When the last of such a set of parallel links fails, traffic is rerouted
as described above.
.P
Handling a failed switch under DOR requires introducing into a path at
least one turn that would be otherwise "illegal",
\fIi.e.\fR,
not allowed by DOR rules.
Torus-2QoS will introduce such a turn as close as possible to the
failed switch in order to route around it.
.P
In the above example, suppose switch T has failed, and consider the path
from S to D.
Torus-2QoS will produce the path S-n-I-r-D, rather than the
S-n-T-r-D path for a pristine torus, by introducing an early turn at n.
Normal DOR rules will cause traffic arriving at switch I to be forwarded
to switch r; for traffic arriving from I due to the "early" turn at n,
this will generate an "illegal" turn at I.
.P
Torus-2QoS will also use the input port dependence of SL2VL maps to set VL
bit 1 (which would be otherwise unused) for y-x, z-x, and z-y turns,
\fIi.e.\fR,
those turns that are illegal under DOR.
This causes the first hop after any such turn to use a separate set of
VL values, and prevents deadlock in the presence of a single failed switch.
.P
For any given path, only the hops after a turn that is illegal under DOR
can contribute to a credit loop that leads to deadlock. So in the example
above with failed switch T, the location of the illegal turn at I in the
path from S to D requires that any credit loop caused by that turn must
encircle the failed switch at T. Thus the second and later hops after the
illegal turn at I (\fIi.e.\fR, hop r-D) cannot contribute to a credit loop
because they cannot be used to construct a loop encircling T. The hop I-r
uses a separate VL, so it cannot contribute to a credit loop encircling T.
.P
Extending this argument shows that in addition to being capable of routing
around a single switch failure without introducing deadlock, torus-2QoS can
also route around multiple failed switches on the condition they are
adjacent in the last dimension routed by DOR. For example, consider the
following case on a 6x6 2D torus:
.
.ascii_art 36
| | | | | |
5 --+----+----+----+----+----+--
| | | | | |
4 --+----+----+----D----+----+--
| | | | | |
3 --+----+----I----u----+----+--
| | | | | |
2 --+----+----q----R----+----+--
| | | | | |
1 --m----S----n----T----o----p--
| | | | | |
y=0 --+----+----+----+----+----+--
| | | | | |
x=0 1 2 3 4 5
.end_ascii_art
.P
Suppose switches T and R have failed, and consider the path from S to D.
Torus-2QoS will generate the path S-n-q-I-u-D, with an illegal turn at
switch I, and with hop I-u using a VL with bit 1 set.
.P
As a further example, consider a case that torus-2QoS cannot route without
deadlock: two failed switches adjacent in a dimension that is not the last
dimension routed by DOR; here the failed switches are O and T:
.
.ascii_art 36
| | | | | |
5 --+----+----+----+----+----+--
| | | | | |
4 --+----+----+----+----+----+--
| | | | | |
3 --+----+----+----+----D----+--
| | | | | |
2 --+----+----I----q----r----+--
| | | | | |
1 --m----S----n----O----T----p--
| | | | | |
y=0 --+----+----+----+----+----+--
| | | | | |
x=0 1 2 3 4 5
.end_ascii_art
.P
In a pristine fabric, torus-2QoS would generate the path from S to D as
S-n-O-T-r-D. With failed switches O and T, torus-2QoS will generate the
path S-n-I-q-r-D, with illegal turn at switch I, and with hop I-q using a
VL with bit 1 set. In contrast to the earlier examples, the second hop
after the illegal turn, q-r, can be used to construct a credit loop
encircling the failed switches.
.
.SH MULTICAST ROUTING
.
Since torus-2QoS uses all four available SL bits, and the three data VL
bits that are typically available in current switches, there is no way
to use SL/VL values to separate multicast traffic from unicast traffic.
Thus, torus-2QoS must generate multicast routing such that credit loops
cannot arise from a combination of multicast and unicast path segments.
.P
It turns out that it is possible to construct spanning trees for multicast
routing that have that property. For the 2D 6x5 torus example above, here
is the full-fabric spanning tree that torus-2QoS will construct, where "x"
is the root switch and each "+" is a non-root switch:
.
.ascii_art 36
4 + + + + + +
| | | | | |
3 + + + + + +
| | | | | |
2 +----+----+----x----+----+
| | | | | |
1 + + + + + +
| | | | | |
y=0 + + + + + +
x=0 1 2 3 4 5
.end_ascii_art
.P
For multicast traffic routed from root to tip, every turn in the above
spanning tree is a legal DOR turn.
.P
For traffic routed from tip to root, and some traffic routed through the
root, turns are not legal DOR turns. However, to construct a credit loop,
the union of multicast routing on this spanning tree with DOR unicast
routing can only provide 3 of the 4 turns needed for the loop.
.P
In addition, if none of the above spanning tree branches crosses a dateline
used for unicast credit loop avoidance on a torus, and if multicast traffic
is confined to SL 0 or SL 8 (recall that torus-2QoS uses SL bit 3 to
differentiate QoS level), then multicast traffic also cannot contribute to
the "ring" credit loops that are otherwise possible in a torus.
.P
Torus-2QoS uses these ideas to create a master spanning tree. Every
multicast group spanning tree will be constructed as a subset of the master
tree, with the same root as the master tree.
.P
Such multicast group spanning trees will in general not be optimal for
groups which are a subset of the full fabric. However, this compromise must
be made to enable support for two QoS levels on a torus while preventing
credit loops.
.P
In the presence of link or switch failures that result in a fabric for
which torus-2QoS can generate credit-loop-free unicast routes, it is also
possible to generate a master spanning tree for multicast that retains the
required properties. For example, consider that same 2D 6x5 torus, with
the link from (2,2) to (3,2) failed. Torus-2QoS will generate the following
master spanning tree:
.
.ascii_art 36
4 + + + + + +
| | | | | |
3 + + + + + +
| | | | | |
2 --+----+----+ x----+----+--
| | | | | |
1 + + + + + +
| | | | | |
y=0 + + + + + +
x=0 1 2 3 4 5
.end_ascii_art
.P
Two things are notable about this master spanning tree. First, assuming
the x dateline was between x=5 and x=0, this spanning tree has a branch
that crosses the dateline. However, just as for unicast, crossing a
dateline on a 1D ring (here, the ring for y=2) that is broken by a failure
cannot contribute to a torus credit loop.
.P
Second, this spanning tree is no longer optimal even for multicast groups
that encompass the entire fabric. That, unfortunately, is a compromise that
must be made to retain the other desirable properties of torus-2QoS routing.
.P
In the event that a single switch fails, torus-2QoS will generate a master
spanning tree that has no "extra" turns by appropriately selecting a root
switch.
In the 2D 6x5 torus example, assume now that the switch at (3,2),
\fIi.e.\fR, the root for a pristine fabric, fails.
Torus-2QoS will generate the
following master spanning tree for that case:
.
.ascii_art 36
|
4 + + + + + +
| | | | | |
3 + + + + + +
| | | | |
2 + + + + +
| | | | |
1 +----+----x----+----+----+
| | | | | |
y=0 + + + + + +
|
x=0 1 2 3 4 5
.end_ascii_art
.P
Assuming the y dateline was between y=4 and y=0, this spanning tree has
a branch that crosses a dateline. However, again this cannot contribute
to credit loops as it occurs on a 1D ring (the ring for x=3) that is
broken by a failure, as in the above example.
.
.SH TORUS TOPOLOGY DISCOVERY
.
The algorithm used by torus-2QoS to construct the torus topology from
the undirected graph representing the fabric requires that the radix of
each dimension be configured via torus-2QoS.conf.
It also requires that the torus topology be "seeded"; for a 3D torus this
requires configuring four switches that define the three coordinate
directions of the torus.
.P
Given this starting information, the algorithm is to examine the
cube formed by the eight switch locations bounded by the corners
(x,y,z) and (x+1,y+1,z+1).
Based on switches already placed into the torus topology at some of these
locations, the algorithm examines 4-loops of inter-switch links to find the
one that is consistent with a face of the cube of switch locations,
and adds its swiches to the discovered topology in the correct locations.
.P
Because the algorithm is based on examining the topology of 4-loops of links,
a torus with one or more radix-4 dimensions requires extra initial
seed configuration.
See torus-2QoS.conf(5) for details.
Torus-2QoS will detect and report when it has insufficient configuration
for a torus with radix-4 dimensions.
.P
In the event the torus is significantly degraded, \fIi.e.\fR, there are
many missing switches or links, it may happen that torus-2QoS is unable
to place into the torus some switches and/or links that were discovered
in the fabric, and will generate a warning in that case.
A similar condition occurs if torus-2QoS is misconfigured, \fIi.e.\fR,
the radix of a torus dimension as configured does not match the radix
of that torus dimension as wired, and many switches/links in the fabric
will not be placed into the torus.
.
.SH QUALITY OF SERVICE CONFIGURATION
.
OpenSM will not program switches and channel adapters with
SL2VL maps or VL arbitration configuration unless it is invoked with -Q.
Since torus-2QoS depends on such functionality for correct operation,
always invoke OpenSM with -Q when torus-2QoS is in the list of routing
engines.
.P
Any quality of service configuration method supported by OpenSM will
work with torus-2QoS, subject to the following limitations and
considerations.
.P
For all routing engines supported by OpenSM except torus-2QoS,
there is a one-to-one correspondence between QoS level and SL.
Torus-2QoS can only support two quality of service levels, so only
the high-order bit of any SL value used for unicast QoS configuration
will be honored by torus-2QoS.
.P
For multicast QoS configuration, only SL values 0 and 8 should be used
with torus-2QoS.
.P
Since SL to VL map configuration must be under the complete control of
torus-2QoS, any configuration via qos_sl2vl, qos_swe_sl2vl,
\fIetc.\fR, must and will be ignored, and a warning will be generated.
.P
For inter-switch links, Torus-2QoS uses VL values 0-3 to implement one of
its supported QoS levels, and VL values 4-7 to implement the other. For
endport links (CA, router, switch management port), Torus-2QoS uses VL
value 0 for one of its supported QoS levels and VL value 1 to implement
the other. Hard-to-diagnose application issues may arise if traffic is
not delivered fairly across each of these two VL ranges. For
inter-switch links, Torus-2QoS will detect and warn if VL arbitration is
configured unfairly across VLs in the range 0-3, and also in the range
4-7. Note that the default OpenSM VL arbitration configuration does
not meet this constraint, so all torus-2QoS users should configure VL
arbitration via qos_ca_vlarb_high, qos_swe_vlarb_high, qos_ca_vlarb_low,
qos_swe_vlarb_low, \fIetc.\fR
.P
Note that torus-2QoS maps SL values to VL values differently
for inter-switch and endport links. This is why qos_vlarb_high and
qos_vlarb_low should not be used, as using them may result in
VL arbitration for a QoS level being different across inter-switch
links vs. across endport links.
.
.SH OPERATIONAL CONSIDERATIONS
.
Any routing algorithm for a torus IB fabric must employ path
SL values to avoid credit loops.
As a result, all applications run over such fabrics must perform a
path record query to obtain the correct path SL for connection setup.
Applications that use \fBrdma_cm\fR for connection setup will automatically
meet this requirement.
.P
If a change in fabric topology causes changes in path SL values required
to route without credit loops, in general all applications would need
to repath to avoid message deadlock. Since torus-2QoS has the ability
to reroute after a single switch failure without changing path SL values,
repathing by running applications is not required when the fabric
is routed with torus-2QoS.
.P
Torus-2QoS can provide unchanging path SL values in the presence of
subnet manager failover provided that all OpenSM instances have the
same idea of dateline location. See torus-2QoS.conf(5) for details.
.P
Torus-2QoS will detect configurations of failed switches and links
that prevent routing that is free of credit loops, and will
log warnings and refuse to route. If "no_fallback" was configured in the
list of OpenSM routing engines, then no other routing engine
will attempt to route the fabric. In that case all paths that
do not transit the failed components will continue to work, and
the subset of paths that are still operational will continue to remain
free of credit loops.
OpenSM will continue to attempt to route the fabric after every sweep
interval, and after any change (such as a link up) in the fabric topology.
When the fabric components are repaired, full functionality will be
restored.
.P
In the event OpenSM was configured to allow some other engine to
route the fabric if torus-2QoS fails, then credit loops and message
deadlock are likely if torus-2QoS had previously routed
the fabric successfully.
Even if the other engine is capable of routing a torus
without credit loops, applications that built connections with
path SL values granted under torus-2QoS will likely experience
message deadlock under routing generated by a different engine,
unless they repath.
.P
To verify that a torus fabric is routed free of credit loops,
use \fBibdmchk\fR to analyze data collected via \fBibdiagnet -vlr\fR.
.
.SH FILES
.TP
.B @OPENSM_CONFIG_DIR@/@OPENSM_CONFIG_FILE@
default OpenSM config file.
.TP
.B @OPENSM_CONFIG_DIR@/@QOS_POLICY_FILE@
default QoS policy config file.
.TP
.B @OPENSM_CONFIG_DIR@/@TORUS2QOS_CONF_FILE@
default torus-2QoS config file.
.
.SH SEE ALSO
.
opensm(8), torus-2QoS.conf(5), ibdiagnet(1), ibdmchk(1), rdma_cm(7).