Hi Sasha, thanks for the new version! It looks all good to me.

Acked-by: Rosemarie O'Riorden <[email protected]>

On 11/18/26 10:43 AM, Alexandra Rukomoinikova wrote:
> If all the health-checked backends of a VIP are down, traffic to the
> VIP is dropped (or rejected).
> 
> Add the "fail_open" option to the NB Load_Balancer_Health_Check table.
> If it is set to true and all the backends of the VIP are down, traffic
> is load balanced across all the backends that have health checks
> configured.  As soon as one backend is back online, only the online
> backends are used.  Since newly created Service_Monitor rows start in the
> "offline" state, a VIP whose backends are all new is load balanced
> across all of them until the first health check succeeds.
> 
> Signed-off-by: Alexandra Rukomoinikova <[email protected]>
> ---
> v1 --> v2: Rename option from fail-open to fail_open in the same pattern
>            as all other option for LB
>            Changed the northd check as discussed with Rosemarie.
>            Removed unused code in northd.
> v2 --> v3: rebased
> ---
>  NEWS                |   5 ++
>  northd/lb.c         |   4 ++
>  northd/lb.h         |   1 +
>  northd/northd.c     |  86 +++++++++++++++++-------------
>  ovn-nb.xml          |  27 +++++++++-
>  tests/ovn-northd.at | 125 ++++++++++++++++++++++++++++++++++++++++++++
>  6 files changed, 212 insertions(+), 36 deletions(-)
> 
> diff --git a/NEWS b/NEWS
> index b2416f98b..d40974837 100644
> --- a/NEWS
> +++ b/NEWS
> @@ -77,6 +77,11 @@ Post v26.09.0
>       the replies from the backends of its load balancers.  The CMS must make
>       sure that the replies re-enter the router on the chassis that load
>       balanced the request.  See ovn-nb(5).
> +   - Added a new "options:fail_open" key to the Load_Balancer_Health_Check
> +     table.  If set to true and all the backends of the VIP are detected as
> +     down, traffic is load balanced across all of them instead of being
> +     dropped or rejected.  As soon as at least one backend is online again,
> +     only the online backends are used.
>  
>  OVN v26.09.0 - xxx xx xxxx
>  --------------------------
> diff --git a/northd/lb.c b/northd/lb.c
> index 5ff9d1fad..0f6d93091 100644
> --- a/northd/lb.c
> +++ b/northd/lb.c
> @@ -104,6 +104,10 @@ ovn_northd_lb_vip_init(struct ovn_northd_lb_vip 
> *lb_vip_nb,
>                                       sizeof *lb_vip_nb->backends_nb);
>      lb_vip_nb->lb_health_check =
>          ovn_lb_get_health_check(nbrec_lb, vip_port_str, template);
> +    lb_vip_nb->fail_open =
> +        lb_vip_nb->lb_health_check
> +        && smap_get_bool(&lb_vip_nb->lb_health_check->options,
> +                         "fail_open", false);
>  }
>  
>  /*
> diff --git a/northd/lb.h b/northd/lb.h
> index 7a98c2f55..6ed3c1ed8 100644
> --- a/northd/lb.h
> +++ b/northd/lb.h
> @@ -91,6 +91,7 @@ struct ovn_northd_lb_vip {
>      size_t n_backends;
>  
>      struct nbrec_load_balancer_health_check *lb_health_check;
> +    bool fail_open;
>  };
>  
>  struct ovn_northd_lb_backend {
> diff --git a/northd/northd.c b/northd/northd.c
> index e4acb11ab..f2575e2f1 100644
> --- a/northd/northd.c
> +++ b/northd/northd.c
> @@ -3570,6 +3570,45 @@ backend_is_available(const struct ovn_northd_lb *lb,
>             false : true;
>  }
>  
> +static size_t
> +build_lb_vip_backends(const struct ovn_northd_lb *lb,
> +                      const struct ovn_lb_vip *lb_vip,
> +                      const struct ovn_northd_lb_vip *lb_vip_nb,
> +                      struct ds *action,
> +                      const struct svc_monitors_map_data *svc_mons_data,
> +                      bool ignore_health_status)
> +{
> +    const struct ovn_lb_backend *backend;
> +    size_t n_backends = 0;
> +    size_t i = 0;
> +
> +    VECTOR_FOR_EACH_PTR (&lb_vip->backends, backend) {
> +        struct ovn_northd_lb_backend *backend_nb =
> +            &lb_vip_nb->backends_nb[i++];
> +        bool ipv6_backend = !IN6_IS_ADDR_V4MAPPED(&backend->ip);
> +
> +        if (!backend_nb->logical_port) {
> +            continue;
> +        }
> +
> +        if (!ignore_health_status && backend_nb->health_check
> +            && !backend_is_available(lb, backend, backend_nb,
> +                                     svc_mons_data)) {
> +            continue;
> +        }
> +
> +        if (backend_nb->distributed_backend) {
> +            ds_put_format(action, "\"%s\":", backend_nb->logical_port);
> +        }
> +        ds_put_format(action,
> +                      ipv6_backend ? "[%s]:%"PRIu16"," : "%s:%"PRIu16",",
> +                      backend->ip_str, backend->port);
> +        n_backends++;
> +    }
> +
> +    return n_backends;
> +}
> +
>  static bool
>  build_lb_vip_actions(const struct ovn_northd_lb *lb,
>                       const struct ovn_lb_vip *lb_vip,
> @@ -3600,41 +3639,18 @@ build_lb_vip_actions(const struct ovn_northd_lb *lb,
>                    : "ct_lb_mark(backends=");
>  
>      if (lb_vip_nb->lb_health_check || lb->is_distributed) {
> -        size_t i = 0;
> -        size_t n_active_backends = 0;
> -        const struct ovn_lb_backend *backend;
> -        VECTOR_FOR_EACH_PTR (&lb_vip->backends, backend) {
> -            struct ovn_northd_lb_backend *backend_nb =
> -                &lb_vip_nb->backends_nb[i++];
> -            bool ipv6_backend = !IN6_IS_ADDR_V4MAPPED(&backend->ip);
> -
> -            /* XXX: Remove these checks: by changing the iteration
> -             * only for selected backends. */
> -            if (lb_vip_nb->lb_health_check &&
> -                !backend_nb->health_check) {
> -                continue;
> -            }
> -
> -            if (lb->is_distributed &&
> -                !backend_nb->distributed_backend) {
> -                continue;
> -            }
> -
> -            if (backend_nb->health_check &&
> -                !backend_is_available(lb,
> -                                      backend,
> -                                      backend_nb,
> -                                      svc_mons_data)) {
> -                continue;
> -            }
> -
> -            if (backend_nb->distributed_backend) {
> -                ds_put_format(action, "\"%s\":", backend_nb->logical_port);
> -            }
> -            ds_put_format(action,
> -                          ipv6_backend ? "[%s]:%"PRIu16"," : "%s:%"PRIu16",",
> -                          backend->ip_str, backend->port);
> -            n_active_backends++;
> +        size_t n_active_backends =
> +            build_lb_vip_backends(lb, lb_vip, lb_vip_nb, action,
> +                                  svc_mons_data, false);
> +
> +        /* If all the health-checked backends are offline and "fail_open" is
> +         * enabled, use all of them instead of dropping (or rejecting) the
> +         * traffic.  As soon as at least one backend is reported online
> +         * again, only the online ones are used. */
> +        if (!n_active_backends && lb_vip_nb->fail_open) {
> +            n_active_backends =
> +                build_lb_vip_backends(lb, lb_vip, lb_vip_nb, action,
> +                                      svc_mons_data, true);
>          }
>          ds_chomp(action, ',');
>  
> diff --git a/ovn-nb.xml b/ovn-nb.xml
> index 0d18010aa..2cca3691e 100644
> --- a/ovn-nb.xml
> +++ b/ovn-nb.xml
> @@ -2656,7 +2656,9 @@
>      <group title="Health Checks">
>        <p>
>          OVN supports health checks for load balancer endpoints. When health
> -        checks are enabled, the load balancer uses only healthy endpoints.
> +        checks are enabled, the load balancer uses only healthy endpoints,
> +        unless <ref table="Load_Balancer_Health_Check" column="options"
> +        key="fail_open"/> is enabled and no endpoint is healthy.
>        </p>
>  
>        <p>
> @@ -2981,6 +2983,29 @@ or
>          The number of failure checks after which the endpoint is considered
>          offline.
>        </column>
> +
> +      <column name="options" key="fail_open" type='{"type": "boolean"}'>
> +        <p>
> +          If set to <code>true</code> and none of the VIP's endpoints is
> +          healthy, traffic is load balanced across all the endpoints that
> +          have health checks configured, instead of being dropped or
> +          rejected.  In that case this option takes precedence over the
> +          <ref table="Load_Balancer" column="options" key="reject"/> option.
> +          As soon as at least one endpoint is healthy again, only the
> +          healthy endpoints are used.
> +        </p>
> +
> +        <p>
> +          A newly added endpoint is considered offline until its first
> +          health check succeeds.  Therefore, when all the endpoints of a VIP
> +          are new, traffic is load balanced across all of them until the
> +          first health check succeeds.
> +        </p>
> +
> +        <p>
> +          The default is <code>false</code>.
> +        </p>
> +      </column>
>      </group>
>  
>      <group title="Common Columns">
> diff --git a/tests/ovn-northd.at b/tests/ovn-northd.at
> index f1e88b4bd..96f167206 100644
> --- a/tests/ovn-northd.at
> +++ b/tests/ovn-northd.at
> @@ -26191,3 +26191,128 @@ AT_CHECK([grep "lr_out_undnat" lr0flows | 
> ovn_strip_lflows | sort], [0], [dnl
>  OVN_CLEANUP_NORTHD
>  AT_CLEANUP
>  ])
> +
> +OVN_FOR_EACH_NORTHD_NO_HV([
> +AT_SETUP([Load balancer health check fail_open])
> +ovn_start
> +# 30.0.0.3 has no ip_port_mappings entry, so it is never used, not even
> +# when fail_open is in effect.
> +check ovn-nbctl lb-add lb1 10.0.0.10:80 10.0.0.3:80,20.0.0.3:80,30.0.0.3:80
> +
> +check ovn-nbctl ls-add sw0
> +check ovn-nbctl lsp-add sw0 sw0-p1 -- lsp-set-addresses sw0-p1 \
> +"00:00:00:00:00:03 10.0.0.3"
> +check ovn-nbctl ls-add sw1
> +check ovn-nbctl --wait=sb lsp-add sw1 sw1-p1 -- lsp-set-addresses sw1-p1 \
> +"02:00:00:00:00:03 20.0.0.3"
> +
> +check ovn-sbctl chassis-add hv1 geneve 127.0.0.1
> +check ovn-sbctl lsp-bind sw0-p1 hv1
> +check ovn-sbctl lsp-bind sw1-p1 hv1
> +wait_row_count nb:Logical_Switch_Port 1 name=sw0-p1 'up=true'
> +wait_row_count nb:Logical_Switch_Port 1 name=sw1-p1 'up=true'
> +
> +check ovn-nbctl set load_balancer . ip_port_mappings:10.0.0.3=sw0-p1:10.0.0.2
> +check ovn-nbctl --wait=sb set load_balancer . \
> +ip_port_mappings:20.0.0.3=sw1-p1:20.0.0.2
> +
> +check_uuid ovn-nbctl --wait=sb -- --id=@hc create \
> +Load_Balancer_Health_Check vip="10.0.0.10\:80" -- add Load_Balancer . \
> +health_check @hc
> +wait_row_count Service_Monitor 2
> +
> +check ovn-nbctl lr-add lr0
> +check ovn-nbctl lr-lb-add lr0 lb1
> +check ovn-nbctl --wait=sb ls-lb-add sw0 lb1
> +
> +sm_sw0_p1=$(fetch_column Service_Monitor _uuid logical_port=sw0-p1)
> +sm_sw1_p1=$(fetch_column Service_Monitor _uuid logical_port=sw1-p1)
> +
> +AS_BOX([Both backends online])
> +check ovn-sbctl set service_monitor $sm_sw0_p1 status=online
> +check ovn-sbctl set service_monitor $sm_sw1_p1 status=online
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'priority=120.*backends' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(reg4 = 
> 10.0.0.10; reg2[[0..15]] = 80; ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +
> +AT_CHECK([ovn-sbctl dump-flows lr0 | grep 'lr_in_dnat.*priority=120' | 
> ovn_strip_lflows], [0], [dnl
> +  table=??(lr_in_dnat         ), priority=120  , match=(ct.new && !ct.rel && 
> ip4 && ip4.dst == 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), 
> action=(ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +
> +AS_BOX([All backends offline without fail_open - traffic is dropped])
> +check ovn-sbctl set service_monitor $sm_sw0_p1 status=offline
> +check ovn-sbctl set service_monitor $sm_sw1_p1 status=offline
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'ls_in_lb.*priority=120' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(drop;)
> +])
> +
> +AT_CHECK([ovn-sbctl dump-flows lr0 | grep 'lr_in_dnat.*priority=120' | 
> ovn_strip_lflows], [0], [dnl
> +  table=??(lr_in_dnat         ), priority=120  , match=(ct.new && !ct.rel && 
> ip4 && ip4.dst == 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), 
> action=(drop;)
> +])
> +
> +AS_BOX([All backends offline with fail_open - all mapped backends are used])
> +check ovn-nbctl --wait=sb set load_balancer_health_check . \
> +options:fail_open=true
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'priority=120.*backends' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(reg4 = 
> 10.0.0.10; reg2[[0..15]] = 80; ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +
> +AT_CHECK([ovn-sbctl dump-flows lr0 | grep 'lr_in_dnat.*priority=120' | 
> ovn_strip_lflows], [0], [dnl
> +  table=??(lr_in_dnat         ), priority=120  , match=(ct.new && !ct.rel && 
> ip4 && ip4.dst == 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), 
> action=(ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +
> +AS_BOX([fail_open takes precedence over the reject option])
> +check ovn-nbctl --wait=sb set load_balancer . options:reject=true
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'ls_in_lb.*priority=120' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(reg4 = 
> 10.0.0.10; reg2[[0..15]] = 80; ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +
> +AT_CHECK([ovn-sbctl dump-flows lr0 | grep 'lr_in_dnat.*priority=120' | 
> ovn_strip_lflows], [0], [dnl
> +  table=??(lr_in_dnat         ), priority=120  , match=(ct.new && !ct.rel && 
> ip4 && ip4.dst == 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), 
> action=(ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +check ovn-nbctl --wait=sb remove load_balancer . options reject
> +
> +AS_BOX([One backend back online - only the online one is used])
> +check ovn-sbctl set service_monitor $sm_sw1_p1 status=online
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'priority=120.*backends' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(reg4 = 
> 10.0.0.10; reg2[[0..15]] = 80; ct_lb_mark(backends=20.0.0.3:80);)
> +])
> +
> +AT_CHECK([ovn-sbctl dump-flows lr0 | grep 'lr_in_dnat.*priority=120' | 
> ovn_strip_lflows], [0], [dnl
> +  table=??(lr_in_dnat         ), priority=120  , match=(ct.new && !ct.rel && 
> ip4 && ip4.dst == 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), 
> action=(ct_lb_mark(backends=20.0.0.3:80);)
> +])
> +
> +AS_BOX([Last backend goes down again - all mapped backends are used])
> +check ovn-sbctl set service_monitor $sm_sw1_p1 status=offline
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'priority=120.*backends' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(reg4 = 
> 10.0.0.10; reg2[[0..15]] = 80; ct_lb_mark(backends=10.0.0.3:80,20.0.0.3:80);)
> +])
> +
> +AS_BOX([Disabling fail_open restores the drop behavior])
> +check ovn-nbctl --wait=sb set load_balancer_health_check . \
> +options:fail_open=false
> +
> +OVS_WAIT_FOR_OUTPUT(
> +  [ovn-sbctl dump-flows sw0 | grep 'ls_in_lb.*priority=120' | 
> ovn_strip_lflows], 0, [dnl
> +  table=??(ls_in_lb           ), priority=120  , match=(ct.new && ip4.dst == 
> 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), action=(drop;)
> +])
> +
> +AT_CHECK([ovn-sbctl dump-flows lr0 | grep 'lr_in_dnat.*priority=120' | 
> ovn_strip_lflows], [0], [dnl
> +  table=??(lr_in_dnat         ), priority=120  , match=(ct.new && !ct.rel && 
> ip4 && ip4.dst == 10.0.0.10 && reg1[[16..23]] == 6 && reg1[[0..15]] == 80), 
> action=(drop;)
> +])
> +
> +OVN_CLEANUP_NORTHD
> +AT_CLEANUP
> +])

_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Reply via email to