On 21 May 2016 at 11:48, Darrell Ball <dlu...@gmail.com> wrote:
> I made some modifications to code in Patches 1 and 2 to remove the Transit
> LS
> requirements.
>
These are the reasons for the need of a LS to be able to be connected to
multiple routers.
1. I think it should be left to the upstream user on how they want to
connect their DRs with GRs. On a 1000 node k8s cluster using peering would
mean that I need to add 1000 DR router ports and manage 1000 subnets. If I
use a LS in-between I need to add only one router port for the DR and
manage only one subnet.
2. The ability to connect multiple routers to a switch is needed on the
north side of the GR as we will need to connect multiple GRs to a switch to
be able to access the physical network for ARP resolution. This is for both
north-south as well as east-west.
3. A Transit LS is needed for the final patch in this series to work (i.e
actual DNAT and SNAT). The final patch needs the packet to enter the
ingress pipeline of a router. The current implementation cannot handle
peering as packets enter the egress pipeline of the router. To support
peering, it will need further enhancements.
>
> In summary:
>
> I removed all changes to lflow.c thereby reinstating the previous
> optimization.
>
> I made some modifications to ovn-northd.c changes to remove the Transit LS
> special
> aspects and additional arp flows.
>
> I left the other code changes in Patches 1 and 2 as they were.
>
> The overall resulting diff to support both patches 1 and 2 is reduced in
> ovn-northd.c
> and becomes:
>
> diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c
> index b271f7f..2e2236b 100644
> --- a/ovn/northd/ovn-northd.c
> +++ b/ovn/northd/ovn-northd.c
> @@ -702,11 +702,25 @@ ovn_port_update_sbrec(const struct ovn_port *op)
> {
> sbrec_port_binding_set_datapath(op->sb, op->od->sb);
> if (op->nbr) {
> - sbrec_port_binding_set_type(op->sb, "patch");
> + /* If the router is for l3 gateway, it resides on a chassis
> + * and its port type is "gateway". */
> + const char *chassis = smap_get(&op->od->nbr->options, "chassis");
> +
> + if (chassis && op->peer && op->peer->od && op->peer->od->nbs){
> + sbrec_port_binding_set_type(op->sb, "gateway");
> + } else {
> + sbrec_port_binding_set_type(op->sb, "patch");
> + }
>
> const char *peer = op->peer ? op->peer->key : "<error>";
> - const struct smap ids = SMAP_CONST1(&ids, "peer", peer);
> - sbrec_port_binding_set_options(op->sb, &ids);
> + struct smap new;
> + smap_init(&new);
> + smap_add(&new, "peer", peer);
> + if (chassis) {
> + smap_add(&new, "gateway-chassis", chassis);
> + }
> + sbrec_port_binding_set_options(op->sb, &new);
> + smap_destroy(&new);
>
> sbrec_port_binding_set_parent_port(op->sb, NULL);
> sbrec_port_binding_set_tag(op->sb, NULL, 0);
> @@ -716,15 +730,31 @@ ovn_port_update_sbrec(const struct ovn_port *op)
> sbrec_port_binding_set_type(op->sb, op->nbs->type);
> sbrec_port_binding_set_options(op->sb, &op->nbs->options);
> } else {
> - sbrec_port_binding_set_type(op->sb, "patch");
> + const char *chassis = NULL;
> + if (op->peer && op->peer->od && op->peer->od->nbr) {
> + chassis = smap_get(&op->peer->od->nbr->options,
> "chassis");
> + }
> + /* A switch port connected to a gateway router is also of
> + * type "gateway". */
> + if (chassis) {
> + sbrec_port_binding_set_type(op->sb, "gateway");
> + } else {
> + sbrec_port_binding_set_type(op->sb, "patch");
> + }
>
> const char *router_port = smap_get(&op->nbs->options,
> "router-port");
> if (!router_port) {
> router_port = "<error>";
> }
> - const struct smap ids = SMAP_CONST1(&ids, "peer",
> router_port);
> - sbrec_port_binding_set_options(op->sb, &ids);
> + struct smap new;
> + smap_init(&new);
> + smap_add(&new, "peer", router_port);
> + if (chassis) {
> + smap_add(&new, "gateway-chassis", chassis);
> + }
> + sbrec_port_binding_set_options(op->sb, &new);
> + smap_destroy(&new);
> }
> sbrec_port_binding_set_parent_port(op->sb, op->nbs->parent_name);
> sbrec_port_binding_set_tag(op->sb, op->nbs->tag, op->nbs->n_tag);
>
>
> I added a new test to demonstrate direct DR<->GR connectivity.
>
>
> AT_SETUP([ovn -- 2 HVs, 3 LRs, 1 DR directly connected to 2 gateway routers
> ])
> AT_KEYWORDS([ovndirectlyconnectedrouters])
> AT_SKIP_IF([test $HAVE_PYTHON = no])
> ovn_start
>
> # Logical network:
> # Three LRs - R1, R2 and R3 that are connected to each other directly
> # in 20.0.0.2/31 and 21.0.0.2/31 networks. R1 has switch foo (
> 192.168.1.0/24
> )
> # connected to it. R2 has alice (172.16.1.0/24) and R3 has bob (
> 10.32.1.0/24
> )
> # connected to it.
>
> ovn-nbctl create Logical_Router name=R1
> ovn-nbctl create Logical_Router name=R2 options:chassis="hv2"
> ovn-nbctl create Logical_Router name=R3 options:chassis="hv2"
>
> ovn-nbctl lswitch-add foo
> ovn-nbctl lswitch-add alice
> ovn-nbctl lswitch-add bob
>
> # Connect foo to R1
> ovn-nbctl -- --id=@lrp create Logical_Router_port name=foo \
> network=192.168.1.1/24 mac=\"00:00:01:01:02:03\" -- add Logical_Router R1
> \
> ports @lrp -- lport-add foo rp-foo
>
> ovn-nbctl set Logical_port rp-foo type=router options:router-port=foo \
> addresses=\"00:00:01:01:02:03\"
>
> # Connect alice to R2
> ovn-nbctl -- --id=@lrp create Logical_Router_port name=alice \
> network=172.16.1.1/24 mac=\"00:00:02:01:02:03\" -- add Logical_Router R2 \
> ports @lrp -- lport-add alice rp-alice
>
> ovn-nbctl set Logical_port rp-alice type=router options:router-port=alice \
> addresses=\"00:00:02:01:02:03\"
>
> # Connect bob to R3
> ovn-nbctl -- --id=@lrp create Logical_Router_port name=bob \
> network=10.32.1.1/24 mac=\"00:00:03:01:02:03\" -- add Logical_Router R3 \
> ports @lrp -- lport-add bob rp-bob
>
> ovn-nbctl set Logical_port rp-bob type=router options:router-port=bob \
> addresses=\"00:00:03:01:02:03\"
>
> # Interconnect R1 and R2
> lrp1_uuid_2_R2=`ovn-nbctl -- --id=@lrp create Logical_Router_port
> name=R1_R2 \
> network="20.0.0.2/31" mac=\"00:00:00:02:03:04\" \
> -- add Logical_Router R1 ports @lrp`
>
> lrp2_uuid_2_R1=`ovn-nbctl -- --id=@lrp create Logical_Router_port
> name=R2_R1 \
> network="20.0.0.3/31" mac=\"00:00:00:02:03:05\" \
> -- add Logical_Router R2 ports @lrp`
>
> ovn-nbctl set logical_router_port $lrp1_uuid_2_R2 peer="R2_R1"
> ovn-nbctl set logical_router_port $lrp2_uuid_2_R1 peer="R1_R2"
>
> # Interconnect R1 and R3
> lrp1_uuid_2_R3=`ovn-nbctl -- --id=@lrp create Logical_Router_port
> name=R1_R3 \
> network="21.0.0.2/31" mac=\"00:00:21:02:03:04\" \
> -- add Logical_Router R1 ports @lrp`
>
> lrp3_uuid_2_R1=`ovn-nbctl -- --id=@lrp create Logical_Router_port
> name=R3_R1 \
> network="21.0.0.3/31" mac=\"00:00:21:02:03:05\" \
> -- add Logical_Router R3 ports @lrp`
>
> ovn-nbctl set logical_router_port $lrp1_uuid_2_R3 peer="R3_R1"
> ovn-nbctl set logical_router_port $lrp3_uuid_2_R1 peer="R1_R3"
>
> #install static route in R1 to get to alice
> ovn-nbctl -- --id=@lrt create Logical_Router_Static_Route \
> ip_prefix=172.16.1.0/24 nexthop=20.0.0.3 -- add Logical_Router \
> R1 static_routes @lrt
>
> #install static route in R1 to get to bob
> ovn-nbctl -- --id=@lrt create Logical_Router_Static_Route \
> ip_prefix=10.32.1.0/24 nexthop=21.0.0.3 -- add Logical_Router \
> R1 static_routes @lrt
>
> #install static route in R2 to get to foo
> ovn-nbctl -- --id=@lrt create Logical_Router_Static_Route \
> ip_prefix=192.168.1.0/24 nexthop=20.0.0.2 -- add Logical_Router \
> R2 static_routes @lrt
>
> # Create terminal logical ports
> # Create logical port foo1 in foo
> ovn-nbctl lport-add foo foo1 \
> -- lport-set-addresses foo1 "f0:00:00:01:02:03 192.168.1.2"
>
> # Create logical port alice1 in alice
> ovn-nbctl lport-add alice alice1 \
> -- lport-set-addresses alice1 "f0:00:00:01:02:04 172.16.1.2"
>
> # Create logical port bob1 in bob
> ovn-nbctl lport-add bob bob1 \
> -- lport-set-addresses bob1 "f0:00:00:01:02:05 10.32.1.2"
>
> # Create two hypervisor and create OVS ports corresponding to logical
> ports.
> net_add n1
>
> sim_add hv1
> as hv1
> ovs-vsctl add-br br-phys
> ovn_attach n1 br-phys 192.168.0.1
> ovs-vsctl -- add-port br-int hv1-vif1 -- \
> set interface hv1-vif1 external-ids:iface-id=foo1 \
> options:tx_pcap=hv1/vif1-tx.pcap \
> options:rxq_pcap=hv1/vif1-rx.pcap \
> ofport-request=1
>
> sim_add hv2
> as hv2
> ovs-vsctl add-br br-phys
> ovn_attach n1 br-phys 192.168.0.2
> ovs-vsctl -- add-port br-int hv2-vif1 -- \
> set interface hv2-vif1 external-ids:iface-id=bob1 \
> options:tx_pcap=hv2/vif1-tx.pcap \
> options:rxq_pcap=hv2/vif1-rx.pcap \
> ofport-request=1
>
> ovs-vsctl -- add-port br-int hv2-vif2 -- \
> set interface hv2-vif2 external-ids:iface-id=alice1 \
> options:tx_pcap=hv2/vif2-tx.pcap \
> options:rxq_pcap=hv2/vif2-rx.pcap \
> ofport-request=2
>
> # Pre-populate the hypervisors' ARP tables so that we don't lose any
> # packets for ARP resolution (native tunneling doesn't queue packets
> # for ARP resolution).
> ovn_populate_arp
>
> # Allow some time for ovn-northd and ovn-controller to catch up.
> # XXX This should be more systematic.
> sleep 1
>
> ip_to_hex() {
> printf "%02x%02x%02x%02x" "$@"
> }
> trim_zeros() {
> sed 's/\(00\)\{1,\}$//'
> }
>
> # Send ip packets between foo1 and alice1
> src_mac="f00000010203"
> dst_mac="000001010203"
> src_ip=`ip_to_hex 192 168 1 2`
> dst_ip=`ip_to_hex 172 16 1 2`
>
> packet=${dst_mac}${src_mac}08004500001c0000000040110000${src_ip}${dst_ip}0035111100080000
> as hv1 ovs-appctl netdev-dummy/receive hv1-vif1 $packet
> as hv1 ovs-appctl ofproto/trace br-int in_port=1 $packet
>
> # Send ip packets between foo1 and bob1
> src_mac="f00000010203"
> dst_mac="000001010203"
> src_ip=`ip_to_hex 192 168 1 2`
> dst_ip=`ip_to_hex 10 32 1 2`
>
> packet=${dst_mac}${src_mac}08004500001c0000000040110000${src_ip}${dst_ip}0035111100080000
> as hv1 ovs-appctl netdev-dummy/receive hv1-vif1 $packet
>
> # Send ip packets from alice1 to foo1
> src_mac="f00000010204"
> dst_mac="000002010203"
> src_ip=`ip_to_hex 172 16 1 2`
> dst_ip=`ip_to_hex 192 168 1 2`
>
> packet=${dst_mac}${src_mac}08004500001c0000000040110000${src_ip}${dst_ip}0035111100080000
> as hv2 ovs-appctl netdev-dummy/receive hv2-vif2 $packet
>
> echo "---------NB dump-----"
> ovn-nbctl show
> echo "---------------------"
> ovn-nbctl list logical_router
> echo "---------------------"
> ovn-nbctl list logical_router_port
> echo "---------------------"
>
> echo "---------SB dump-----"
> ovn-sbctl list datapath_binding
> echo "---------------------"
> ovn-sbctl list port_binding
> echo "---------------------"
> #ovn-sbctl dump-flows
> echo "---------------------"
>
> echo "------ hv1 dump ----------"
> as hv1 ovs-vsctl show
> as hv1 ovs-ofctl show br-int
> as hv1 ovs-ofctl dump-flows br-int
> echo "------ hv2 dump ----------"
> as hv2 ovs-vsctl show
> as hv2 ovs-ofctl show br-int
> as hv2 ovs-ofctl dump-flows br-int
> echo "----------------------------"
>
> # Packet to Expect at alice1
> src_mac="000002010203"
> dst_mac="f00000010204"
> src_ip=`ip_to_hex 192 168 1 2`
> dst_ip=`ip_to_hex 172 16 1 2`
>
> expected=${dst_mac}${src_mac}08004500001c000000003e110200${src_ip}${dst_ip}0035111100080000
>
> $PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv2/vif2-tx.pcap | trim_zeros
> >
> received.packets
> echo $expected | trim_zeros > expout
> AT_CHECK([cat received.packets], [0], [expout])
>
> # Packet to Expect at bob1
> src_mac="000003010203"
> dst_mac="f00000010205"
> src_ip=`ip_to_hex 192 168 1 2`
> dst_ip=`ip_to_hex 10 32 1 2`
>
> expected=${dst_mac}${src_mac}08004500001c000000003e110200${src_ip}${dst_ip}0035111100080000
>
> $PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv2/vif1-tx.pcap | trim_zeros
> >
> received1.packets
> echo $expected | trim_zeros > expout
> AT_CHECK([cat received1.packets], [0], [expout])
>
> # Packet to Expect at foo1
> src_mac="000001010203"
> dst_mac="f00000010203"
> src_ip=`ip_to_hex 172 16 1 2`
> dst_ip=`ip_to_hex 192 168 1 2`
>
> expected=${dst_mac}${src_mac}08004500001c000000003e110200${src_ip}${dst_ip}0035111100080000
>
> $PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/vif1-tx.pcap | trim_zeros
> >
> received2.packets
> echo $expected | trim_zeros > expout
> AT_CHECK([cat received2.packets], [0], [expout])
>
> for sim in hv1 hv2; do
> as $sim
> OVS_APP_EXIT_AND_WAIT([ovn-controller])
> OVS_APP_EXIT_AND_WAIT([ovs-vswitchd])
> OVS_APP_EXIT_AND_WAIT([ovsdb-server])
> done
>
> as ovn-sb
> OVS_APP_EXIT_AND_WAIT([ovsdb-server])
>
> as ovn-nb
> OVS_APP_EXIT_AND_WAIT([ovsdb-server])
>
> as northd
> OVS_APP_EXIT_AND_WAIT([ovn-northd])
>
> as main
> OVS_APP_EXIT_AND_WAIT([ovs-vswitchd])
> OVS_APP_EXIT_AND_WAIT([ovsdb-server])
>
> AT_CLEANUP
>
> On Thu, May 19, 2016 at 1:02 PM, Gurucharan Shetty <g...@ovn.org> wrote:
>
> > Currently OVN has distributed switches and routers. When a packet
> > exits a container or a VM, the entire lifecycle of the packet
> > through multiple switches and routers are calculated in source
> > chassis itself. When the destination endpoint resides on a different
> > chassis, the packet is sent to the other chassis and it only goes
> > through the egress pipeline of that chassis once and eventually to
> > the real destination.
> >
> > When the packet returns back, the same thing happens. The return
> > packet leaves the VM/container on the chassis where it resides.
> > The packet goes through all the switches and routers in the logical
> > pipleline on that chassis and then sent to the eventual destination
> > over the tunnel.
> >
> > The above makes the logical pipeline very flexible and easy. But,
> > creates a problem for cases where you need to add stateful services
> > (via conntrack) on switches and routers.
> >
> > For l3 gateways, we plan to leverage DNAT and SNAT functionality
> > and we want to apply DNAT and SNAT rules on a router. So we ideally need
> > the packet to go through that router in both directions in the same
> > chassis. To achieve this, this commit introduces a new gateway router
> > which is
> > static and can be connected to your distributed router via a switch.
> >
> > To make minimal changes in OVN's logical pipeline, this commit
> > tries to make the switch port connected to a l3 gateway router look like
> > a container/VM endpoint for every other chassis except the chassis
> > on which the l3 gateway router resides. On the chassis where the
> > gateway router resides, the connection looks just like a patch port.
> >
> > This is achieved by the doing the following:
> > Introduces a new type of port_binding record called 'gateway'.
> > On the chassis where the gateway router resides, this port behaves just
> > like the port of type 'patch'. The ovn-controller on that chassis
> > populates the "chassis" column for this record as an indication for
> > other ovn-controllers of its physical location. Other ovn-controllers
> > treat this port as they would treat a VM/Container port on a different
> > chassis.
> >
> > Signed-off-by: Gurucharan Shetty <g...@ovn.org>
> > ---
> > ovn/controller/binding.c | 3 +-
> > ovn/controller/ovn-controller.c | 5 +-
> > ovn/controller/patch.c | 29 ++++++-
> > ovn/controller/patch.h | 3 +-
> > ovn/northd/ovn-northd.c | 42 +++++++--
> > ovn/ovn-nb.ovsschema | 9 +-
> > ovn/ovn-nb.xml | 15 ++++
> > ovn/ovn-sb.xml | 35 +++++++-
> > tests/ovn.at | 184
> > ++++++++++++++++++++++++++++++++++++++++
> > 9 files changed, 309 insertions(+), 16 deletions(-)
> >
> > diff --git a/ovn/controller/binding.c b/ovn/controller/binding.c
> > index a0d8b96..e5e55b1 100644
> > --- a/ovn/controller/binding.c
> > +++ b/ovn/controller/binding.c
> > @@ -200,7 +200,8 @@ binding_run(struct controller_ctx *ctx, const struct
> > ovsrec_bridge *br_int,
> > }
> > sbrec_port_binding_set_chassis(binding_rec,
> chassis_rec);
> > }
> > - } else if (chassis_rec && binding_rec->chassis == chassis_rec) {
> > + } else if (chassis_rec && binding_rec->chassis == chassis_rec
> > + && strcmp(binding_rec->type, "gateway")) {
> > if (ctx->ovnsb_idl_txn) {
> > VLOG_INFO("Releasing lport %s from this chassis.",
> > binding_rec->logical_port);
> > diff --git a/ovn/controller/ovn-controller.c
> > b/ovn/controller/ovn-controller.c
> > index 511b184..bc4c24f 100644
> > --- a/ovn/controller/ovn-controller.c
> > +++ b/ovn/controller/ovn-controller.c
> > @@ -364,8 +364,9 @@ main(int argc, char *argv[])
> > &local_datapaths);
> > }
> >
> > - if (br_int) {
> > - patch_run(&ctx, br_int, &local_datapaths,
> &patched_datapaths);
> > + if (br_int && chassis_id) {
> > + patch_run(&ctx, br_int, chassis_id, &local_datapaths,
> > + &patched_datapaths);
> >
> > struct lport_index lports;
> > struct mcgroup_index mcgroups;
> > diff --git a/ovn/controller/patch.c b/ovn/controller/patch.c
> > index 4808146..e8abe30 100644
> > --- a/ovn/controller/patch.c
> > +++ b/ovn/controller/patch.c
> > @@ -267,12 +267,28 @@ add_patched_datapath(struct hmap
> *patched_datapaths,
> > static void
> > add_logical_patch_ports(struct controller_ctx *ctx,
> > const struct ovsrec_bridge *br_int,
> > + const char *local_chassis_id,
> > struct shash *existing_ports,
> > struct hmap *patched_datapaths)
> > {
> > + const struct sbrec_chassis *chassis_rec;
> > + chassis_rec = get_chassis(ctx->ovnsb_idl, local_chassis_id);
> > + if (!chassis_rec) {
> > + return;
> > + }
> > +
> > const struct sbrec_port_binding *binding;
> > SBREC_PORT_BINDING_FOR_EACH (binding, ctx->ovnsb_idl) {
> > - if (!strcmp(binding->type, "patch")) {
> > + bool local_port = false;
> > + if (!strcmp(binding->type, "gateway")) {
> > + const char *chassis = smap_get(&binding->options,
> > + "gateway-chassis");
> > + if (!strcmp(local_chassis_id, chassis)) {
> > + local_port = true;
> > + }
> > + }
> > +
> > + if (!strcmp(binding->type, "patch") || local_port) {
> > const char *local = binding->logical_port;
> > const char *peer = smap_get(&binding->options, "peer");
> > if (!peer) {
> > @@ -287,13 +303,19 @@ add_logical_patch_ports(struct controller_ctx *ctx,
> > free(dst_name);
> > free(src_name);
> > add_patched_datapath(patched_datapaths, binding);
> > + if (local_port) {
> > + if (binding->chassis != chassis_rec &&
> > ctx->ovnsb_idl_txn) {
> > + sbrec_port_binding_set_chassis(binding,
> chassis_rec);
> > + }
> > + }
> > }
> > }
> > }
> >
> > void
> > patch_run(struct controller_ctx *ctx, const struct ovsrec_bridge
> *br_int,
> > - struct hmap *local_datapaths, struct hmap *patched_datapaths)
> > + const char *chassis_id, struct hmap *local_datapaths,
> > + struct hmap *patched_datapaths)
> > {
> > if (!ctx->ovs_idl_txn) {
> > return;
> > @@ -313,7 +335,8 @@ patch_run(struct controller_ctx *ctx, const struct
> > ovsrec_bridge *br_int,
> > * 'existing_ports' any patch ports that do exist in the database
> and
> > * should be there. */
> > add_bridge_mappings(ctx, br_int, &existing_ports, local_datapaths);
> > - add_logical_patch_ports(ctx, br_int, &existing_ports,
> > patched_datapaths);
> > + add_logical_patch_ports(ctx, br_int, chassis_id, &existing_ports,
> > + patched_datapaths);
> >
> > /* Now 'existing_ports' only still contains patch ports that exist
> in
> > the
> > * database but shouldn't. Delete them from the database. */
> > diff --git a/ovn/controller/patch.h b/ovn/controller/patch.h
> > index d5d842e..7920a48 100644
> > --- a/ovn/controller/patch.h
> > +++ b/ovn/controller/patch.h
> > @@ -27,6 +27,7 @@ struct hmap;
> > struct ovsrec_bridge;
> >
> > void patch_run(struct controller_ctx *, const struct ovsrec_bridge
> > *br_int,
> > - struct hmap *local_datapaths, struct hmap
> > *patched_datapaths);
> > + const char *chassis_id, struct hmap *local_datapaths,
> > + struct hmap *patched_datapaths);
> >
> > #endif /* ovn/patch.h */
> > diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c
> > index f469e89..7852d83 100644
> > --- a/ovn/northd/ovn-northd.c
> > +++ b/ovn/northd/ovn-northd.c
> > @@ -690,11 +690,24 @@ ovn_port_update_sbrec(const struct ovn_port *op)
> > {
> > sbrec_port_binding_set_datapath(op->sb, op->od->sb);
> > if (op->nbr) {
> > - sbrec_port_binding_set_type(op->sb, "patch");
> > + /* If the router is for l3 gateway, it resides on a chassis
> > + * and its port type is "gateway". */
> > + const char *chassis = smap_get(&op->od->nbr->options,
> "chassis");
> > + if (chassis) {
> > + sbrec_port_binding_set_type(op->sb, "gateway");
> > + } else {
> > + sbrec_port_binding_set_type(op->sb, "patch");
> > + }
> >
> > const char *peer = op->peer ? op->peer->key : "<error>";
> > - const struct smap ids = SMAP_CONST1(&ids, "peer", peer);
> > - sbrec_port_binding_set_options(op->sb, &ids);
> > + struct smap new;
> > + smap_init(&new);
> > + smap_add(&new, "peer", peer);
> > + if (chassis) {
> > + smap_add(&new, "gateway-chassis", chassis);
> > + }
> > + sbrec_port_binding_set_options(op->sb, &new);
> > + smap_destroy(&new);
> >
> > sbrec_port_binding_set_parent_port(op->sb, NULL);
> > sbrec_port_binding_set_tag(op->sb, NULL, 0);
> > @@ -704,15 +717,32 @@ ovn_port_update_sbrec(const struct ovn_port *op)
> > sbrec_port_binding_set_type(op->sb, op->nbs->type);
> > sbrec_port_binding_set_options(op->sb, &op->nbs->options);
> > } else {
> > - sbrec_port_binding_set_type(op->sb, "patch");
> > + const char *chassis = NULL;
> > + if (op->peer && op->peer->od && op->peer->od->nbr) {
> > + chassis = smap_get(&op->peer->od->nbr->options,
> > "chassis");
> > + }
> > +
> > + /* A switch port connected to a gateway router is also of
> > + * type "gateway". */
> > + if (chassis) {
> > + sbrec_port_binding_set_type(op->sb, "gateway");
> > + } else {
> > + sbrec_port_binding_set_type(op->sb, "patch");
> > + }
> >
> > const char *router_port = smap_get(&op->nbs->options,
> > "router-port");
> > if (!router_port) {
> > router_port = "<error>";
> > }
> > - const struct smap ids = SMAP_CONST1(&ids, "peer",
> > router_port);
> > - sbrec_port_binding_set_options(op->sb, &ids);
> > + struct smap new;
> > + smap_init(&new);
> > + smap_add(&new, "peer", router_port);
> > + if (chassis) {
> > + smap_add(&new, "gateway-chassis", chassis);
> > + }
> > + sbrec_port_binding_set_options(op->sb, &new);
> > + smap_destroy(&new);
> > }
> > sbrec_port_binding_set_parent_port(op->sb,
> op->nbs->parent_name);
> > sbrec_port_binding_set_tag(op->sb, op->nbs->tag,
> op->nbs->n_tag);
> > diff --git a/ovn/ovn-nb.ovsschema b/ovn/ovn-nb.ovsschema
> > index 8163f6a..fa21b30 100644
> > --- a/ovn/ovn-nb.ovsschema
> > +++ b/ovn/ovn-nb.ovsschema
> > @@ -1,7 +1,7 @@
> > {
> > "name": "OVN_Northbound",
> > - "version": "2.1.1",
> > - "cksum": "2615511875 5108",
> > + "version": "2.1.2",
> > + "cksum": "429668869 5325",
> > "tables": {
> > "Logical_Switch": {
> > "columns": {
> > @@ -78,6 +78,11 @@
> > "max": "unlimited"}},
> > "default_gw": {"type": {"key": "string", "min": 0,
> "max":
> > 1}},
> > "enabled": {"type": {"key": "boolean", "min": 0, "max":
> > 1}},
> > + "options": {
> > + "type": {"key": "string",
> > + "value": "string",
> > + "min": 0,
> > + "max": "unlimited"}},
> > "external_ids": {
> > "type": {"key": "string", "value": "string",
> > "min": 0, "max": "unlimited"}}},
> > diff --git a/ovn/ovn-nb.xml b/ovn/ovn-nb.xml
> > index d7fd595..d239499 100644
> > --- a/ovn/ovn-nb.xml
> > +++ b/ovn/ovn-nb.xml
> > @@ -630,6 +630,21 @@
> > column is set to <code>false</code>, the router is disabled. A
> > disabled
> > router has all ingress and egress traffic dropped.
> > </column>
> > +
> > + <group title="Options">
> > + <p>
> > + Additional options for the logical router.
> > + </p>
> > +
> > + <column name="options" key="chassis">
> > + If set, indicates that the logical router in question is
> > + non-distributed and resides in the set chassis. The same
> > + value is also used by <code>ovn-controller</code> to
> > + uniquely identify the chassis in the OVN deployment and
> > + comes from <code>external_ids:system-id</code> in the
> > + <code>Open_vSwitch</code> table of Open_vSwitch database.
> > + </column>
> > + </group>
> >
> > <group title="Common Columns">
> > <column name="external_ids">
> > diff --git a/ovn/ovn-sb.xml b/ovn/ovn-sb.xml
> > index efd2f9a..741228c 100644
> > --- a/ovn/ovn-sb.xml
> > +++ b/ovn/ovn-sb.xml
> > @@ -1220,7 +1220,12 @@ tcp.flags = RST;
> > which <code>ovn-controller</code>/<code>ovn-controller-vtep</code>
> > in
> > turn finds out by monitoring the local hypervisor's Open_vSwitch
> > database, which identifies logical ports via the conventions
> > described
> > - in <code>IntegrationGuide.md</code>.
> > + in <code>IntegrationGuide.md</code>. (The exceptions are for
> > + <code>Port_Binding</code> records of <code>type</code> 'gateway',
> > + whose locations are identified by <code>ovn-northd</code> via
> > + the <code>options:gateway-chassis</code> column in this table.
> > + <code>ovn-controller</code> is still responsible to populate the
> > + <code>chassis</code> column.)
> > </p>
> >
> > <p>
> > @@ -1298,6 +1303,14 @@ tcp.flags = RST;
> > a logical router to a logical switch or to another logical
> > router.
> > </dd>
> >
> > + <dt><code>gateway</code></dt>
> > + <dd>
> > + One of a pair of logical ports that act as if connected by a
> > patch
> > + cable across multiple chassis. Useful for connecting a
> > logical
> > + switch with a gateway router (which is only resident on a
> > + particular chassis).
> > + </dd>
> > +
> > <dt><code>localnet</code></dt>
> > <dd>
> > A connection to a locally accessible network from each
> > @@ -1336,6 +1349,26 @@ tcp.flags = RST;
> > </column>
> > </group>
> >
> > + <group title="Gateway Options">
> > + <p>
> > + These options apply to logical ports with <ref column="type"/>
> of
> > + <code>gateway</code>.
> > + </p>
> > +
> > + <column name="options" key="peer">
> > + The <ref column="logical_port"/> in the <ref
> > table="Port_Binding"/>
> > + record for the other side of the 'gateway' port. The named <ref
> > + column="logical_port"/> must specify this <ref
> > column="logical_port"/>
> > + in its own <code>peer</code> option. That is, the two 'gateway'
> > + logical ports must have reversed <ref column="logical_port"/>
> and
> > + <code>peer</code> values.
> > + </column>
> > +
> > + <column name="options" key="gateway-chassis">
> > + The <code>chassis</code> in which the port resides.
> > + </column>
> > + </group>
> > +
> > <group title="Localnet Options">
> > <p>
> > These options apply to logical ports with <ref column="type"/>
> of
> > diff --git a/tests/ovn.at b/tests/ovn.at
> > index a827b71..9d93064 100644
> > --- a/tests/ovn.at
> > +++ b/tests/ovn.at
> > @@ -2848,3 +2848,187 @@ OVS_APP_EXIT_AND_WAIT([ovs-vswitchd])
> > OVS_APP_EXIT_AND_WAIT([ovsdb-server])
> >
> > AT_CLEANUP
> > +
> > +
> > +AT_SETUP([ovn -- 2 HVs, 2 LRs connected via LS, gateway router])
> > +AT_KEYWORDS([ovngatewayrouter])
> > +AT_SKIP_IF([test $HAVE_PYTHON = no])
> > +ovn_start
> > +
> > +# Logical network:
> > +# Two LRs - R1 and R2 that are connected to each other via LS "join"
> > +# in 20.0.0.0/24 network. R1 has switchess foo (192.168.1.0/24)
> > +# connected to it. R2 has alice (172.16.1.0/24) connected to it.
> > +# R2 is a gateway router.
> > +
> > +
> > +
> > +# Create two hypervisor and create OVS ports corresponding to logical
> > ports.
> > +net_add n1
> > +
> > +sim_add hv1
> > +as hv1
> > +ovs-vsctl add-br br-phys
> > +ovn_attach n1 br-phys 192.168.0.1
> > +ovs-vsctl -- add-port br-int hv1-vif1 -- \
> > + set interface hv1-vif1 external-ids:iface-id=foo1 \
> > + options:tx_pcap=hv1/vif1-tx.pcap \
> > + options:rxq_pcap=hv1/vif1-rx.pcap \
> > + ofport-request=1
> > +
> > +
> > +sim_add hv2
> > +as hv2
> > +ovs-vsctl add-br br-phys
> > +ovn_attach n1 br-phys 192.168.0.2
> > +ovs-vsctl -- add-port br-int hv2-vif1 -- \
> > + set interface hv2-vif1 external-ids:iface-id=alice1 \
> > + options:tx_pcap=hv2/vif1-tx.pcap \
> > + options:rxq_pcap=hv2/vif1-rx.pcap \
> > + ofport-request=1
> > +
> > +# Pre-populate the hypervisors' ARP tables so that we don't lose any
> > +# packets for ARP resolution (native tunneling doesn't queue packets
> > +# for ARP resolution).
> > +ovn_populate_arp
> > +
> > +ovn-nbctl create Logical_Router name=R1
> > +ovn-nbctl create Logical_Router name=R2 options:chassis="hv2"
> > +
> > +ovn-nbctl lswitch-add foo
> > +ovn-nbctl lswitch-add alice
> > +ovn-nbctl lswitch-add join
> > +
> > +# Connect foo to R1
> > +ovn-nbctl -- --id=@lrp create Logical_Router_port name=foo \
> > +network=192.168.1.1/24 mac=\"00:00:01:01:02:03\" -- add Logical_Router
> > R1 \
> > +ports @lrp -- lport-add foo rp-foo
> > +
> > +ovn-nbctl set Logical_port rp-foo type=router options:router-port=foo \
> > +addresses=\"00:00:01:01:02:03\"
> > +
> > +# Connect alice to R2
> > +ovn-nbctl -- --id=@lrp create Logical_Router_port name=alice \
> > +network=172.16.1.1/24 mac=\"00:00:02:01:02:03\" -- add Logical_Router
> R2
> > \
> > +ports @lrp -- lport-add alice rp-alice
> > +
> > +ovn-nbctl set Logical_port rp-alice type=router
> options:router-port=alice
> > \
> > +addresses=\"00:00:02:01:02:03\"
> > +
> > +
> > +# Connect R1 to join
> > +ovn-nbctl -- --id=@lrp create Logical_Router_port name=R1_join \
> > +network=20.0.0.1/24 mac=\"00:00:04:01:02:03\" -- add Logical_Router R1
> \
> > +ports @lrp -- lport-add join r1-join
> > +
> > +ovn-nbctl set Logical_port r1-join type=router
> > options:router-port=R1_join \
> > +addresses='"00:00:04:01:02:03"'
> > +
> > +# Connect R2 to join
> > +ovn-nbctl -- --id=@lrp create Logical_Router_port name=R2_join \
> > +network=20.0.0.2/24 mac=\"00:00:04:01:02:04\" -- add Logical_Router R2
> \
> > +ports @lrp -- lport-add join r2-join
> > +
> > +ovn-nbctl set Logical_port r2-join type=router
> > options:router-port=R2_join \
> > +addresses='"00:00:04:01:02:04"'
> > +
> > +
> > +#install static routes
> > +ovn-nbctl -- --id=@lrt create Logical_Router_Static_Route \
> > +ip_prefix=172.16.1.0/24 nexthop=20.0.0.2 -- add Logical_Router \
> > +R1 static_routes @lrt
> > +
> > +ovn-nbctl -- --id=@lrt create Logical_Router_Static_Route \
> > +ip_prefix=192.168.1.0/24 nexthop=20.0.0.1 -- add Logical_Router \
> > +R2 static_routes @lrt
> > +
> > +# Create logical port foo1 in foo
> > +ovn-nbctl lport-add foo foo1 \
> > +-- lport-set-addresses foo1 "f0:00:00:01:02:03 192.168.1.2"
> > +
> > +# Create logical port alice1 in alice
> > +ovn-nbctl lport-add alice alice1 \
> > +-- lport-set-addresses alice1 "f0:00:00:01:02:04 172.16.1.2"
> > +
> > +
> > +# Allow some time for ovn-northd and ovn-controller to catch up.
> > +# XXX This should be more systematic.
> > +sleep 2
> > +
> > +ip_to_hex() {
> > + printf "%02x%02x%02x%02x" "$@"
> > +}
> > +trim_zeros() {
> > + sed 's/\(00\)\{1,\}$//'
> > +}
> > +
> > +# Send ip packets between foo1 and alice1
> > +src_mac="f00000010203"
> > +dst_mac="000001010203"
> > +src_ip=`ip_to_hex 192 168 1 2`
> > +dst_ip=`ip_to_hex 172 16 1 2`
> >
> >
> +packet=${dst_mac}${src_mac}08004500001c0000000040110000${src_ip}${dst_ip}0035111100080000
> > +
> > +echo "---------NB dump-----"
> > +ovn-nbctl show
> > +echo "---------------------"
> > +ovn-nbctl list logical_router
> > +echo "---------------------"
> > +ovn-nbctl list logical_router_port
> > +echo "---------------------"
> > +
> > +echo "---------SB dump-----"
> > +ovn-sbctl list datapath_binding
> > +echo "---------------------"
> > +ovn-sbctl list port_binding
> > +echo "---------------------"
> > +ovn-sbctl dump-flows
> > +echo "---------------------"
> > +ovn-sbctl list chassis
> > +ovn-sbctl list encap
> > +echo "---------------------"
> > +
> > +echo "------ hv1 dump ----------"
> > +as hv1 ovs-ofctl show br-int
> > +as hv1 ovs-ofctl dump-flows br-int
> > +echo "------ hv2 dump ----------"
> > +as hv2 ovs-ofctl show br-int
> > +as hv2 ovs-ofctl dump-flows br-int
> > +echo "----------------------------"
> > +
> > +# Packet to Expect at alice1
> > +src_mac="000002010203"
> > +dst_mac="f00000010204"
> > +src_ip=`ip_to_hex 192 168 1 2`
> > +dst_ip=`ip_to_hex 172 16 1 2`
> >
> >
> +expected=${dst_mac}${src_mac}08004500001c000000003e110200${src_ip}${dst_ip}0035111100080000
> > +
> > +
> > +as hv1 ovs-appctl netdev-dummy/receive hv1-vif1 $packet
> > +as hv1 ovs-appctl ofproto/trace br-int in_port=1 $packet
> > +
> > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv2/vif1-tx.pcap |
> > trim_zeros > received1.packets
> > +echo $expected | trim_zeros > expout
> > +AT_CHECK([cat received1.packets], [0], [expout])
> > +
> > +for sim in hv1 hv2; do
> > + as $sim
> > + OVS_APP_EXIT_AND_WAIT([ovn-controller])
> > + OVS_APP_EXIT_AND_WAIT([ovs-vswitchd])
> > + OVS_APP_EXIT_AND_WAIT([ovsdb-server])
> > +done
> > +
> > +as ovn-sb
> > +OVS_APP_EXIT_AND_WAIT([ovsdb-server])
> > +
> > +as ovn-nb
> > +OVS_APP_EXIT_AND_WAIT([ovsdb-server])
> > +
> > +as northd
> > +OVS_APP_EXIT_AND_WAIT([ovn-northd])
> > +
> > +as main
> > +OVS_APP_EXIT_AND_WAIT([ovs-vswitchd])
> > +OVS_APP_EXIT_AND_WAIT([ovsdb-server])
> > +
> > +AT_CLEANUP
> > --
> > 1.9.1
> >
> > _______________________________________________
> > dev mailing list
> > dev@openvswitch.org
> > http://openvswitch.org/mailman/listinfo/dev
> >
> _______________________________________________
> dev mailing list
> dev@openvswitch.org
> http://openvswitch.org/mailman/listinfo/dev
>
_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
