Hi Dumitru Thanks again for looking at this.
On Fri, Mar 27, 2026 at 12:38 PM Dumitru Ceara <[email protected]> wrote: > On 3/26/26 5:16 PM, Xavier Simonart wrote: > > If a server unexpectedly rebooted, OVS, when restarted, sets BFD > > UP on bfd-enabled geneve tunnels. > > However, if it takes time to restart OVN, an HA gw chassis > > would attract the traffic while being unable to handle it > > (as no flows), resulting in traffic loss. > > > > This is fixed by re-using ovs flow-restore-wait. > > If set, OVS waits (prevents upcalls, ignores bfd, ...) until reset. > > Once OVS receives the notification of flow-restore-wait being false, > > it restarts handling upcalls, bfd... and ignores any new change to > > flow-restore-wait. > > > > Hence, on chassis hosting ha gateways, OVN toggles flow-restore-wait: > > it set it to false, waits for ack from OVS and then sets it back to true. > > If server reboots, OVS will see flow-restore-wait being true. > > > > OVN also sets external_ids->ovn-managed-flow-restore-wait when setting > > flow-restore-wait. When set, it tells that OVN once set > flow-restore-wait. > > > > "ovs-ctl restart" also uses flow-restore-wait: when called, it saves the > > flows, stops "ovs-vswitchd", sets "flow-restore-wait" to true, restarts > > "ovs-vswitchd", restores the flows and finally removes > "flow-restore-wait". > > So OVS will wait either for "ovs-ctl restart" to remove > "flow-restore-wait" > > or for OVN to set "flow-restore-wait" to false. > > > > Reported-at: https://issues.redhat.com/browse/FDP-3075 > > Signed-off-by: Xavier Simonart <[email protected]> > > > > --- > > -v2 : - Updated based on Mark's feedback (commit message, comments). > > - Avoid setting flow-restore-wait for computes. > > - Add external_ids->ovn-managed-flow-restore-wait. > > - Updated test: add test for compute update + nits (variable name > changes) > > -v3 : - Fix test failing on CI (using wrong host socket) > > - Address nits from Dumitru + few more nits (related to comments). > > - Increased tolerated loss (and add comment) to avoid flakiness. > > - Rebased. > > --- > > Hi Xavier, > > Thanks for the v3! > > > controller/bfd.c | 5 +- > > controller/bfd.h | 4 +- > > controller/ovn-controller.8.xml | 11 + > > controller/ovn-controller.c | 173 +++++++++- > > tests/multinode-macros.at | 46 +++ > > tests/multinode.at | 548 ++++++++++++++++++++++---------- > > 6 files changed, 612 insertions(+), 175 deletions(-) > > > > diff --git a/controller/bfd.c b/controller/bfd.c > > index 3b0c3f6da..56bfa4936 100644 > > --- a/controller/bfd.c > > +++ b/controller/bfd.c > > @@ -117,13 +117,14 @@ bfd_calculate_active_tunnels(const struct > ovsrec_bridge *br_int, > > * > > * If 'our_chassis' is C5 then this function returns empty bfd set. > > */ > > -void > > +bool > > bfd_calculate_chassis( > > const struct sbrec_chassis *our_chassis, > > const struct sbrec_ha_chassis_group_table *ha_chassis_grp_table, > > struct sset *bfd_chassis) > > { > > const struct sbrec_ha_chassis_group *ha_chassis_grp; > > + bool chassis_is_ha_gw = false; > > SBREC_HA_CHASSIS_GROUP_TABLE_FOR_EACH (ha_chassis_grp, > > ha_chassis_grp_table) { > > bool is_ha_chassis = false; > > @@ -143,6 +144,7 @@ bfd_calculate_chassis( > > sset_add(&grp_chassis, ha_ch->chassis->name); > > if (our_chassis == ha_ch->chassis) { > > is_ha_chassis = true; > > + chassis_is_ha_gw = true; > > bfd_setup_required = true; > > } > > } > > @@ -178,6 +180,7 @@ bfd_calculate_chassis( > > } > > sset_destroy(&grp_chassis); > > } > > + return chassis_is_ha_gw; > > } > > > > void > > diff --git a/controller/bfd.h b/controller/bfd.h > > index f8fece5a5..3e3384891 100644 > > --- a/controller/bfd.h > > +++ b/controller/bfd.h > > @@ -16,6 +16,8 @@ > > #ifndef OVN_BFD_H > > #define OVN_BFD_H 1 > > > > +#include <stdbool.h> > > + > > struct hmap; > > struct ovsdb_idl; > > struct ovsdb_idl_index; > > @@ -36,7 +38,7 @@ void bfd_run(const struct ovsrec_interface_table *, > > const struct sbrec_sb_global_table *, > > const struct ovsrec_open_vswitch_table *); > > > > -void bfd_calculate_chassis( > > +bool bfd_calculate_chassis( > > const struct sbrec_chassis *, > > const struct sbrec_ha_chassis_group_table *, > > struct sset *); > > diff --git a/controller/ovn-controller.8.xml > b/controller/ovn-controller.8.xml > > index 57e7cf5dd..33281a4d6 100644 > > --- a/controller/ovn-controller.8.xml > > +++ b/controller/ovn-controller.8.xml > > @@ -531,6 +531,17 @@ > > 65535. > > </dd> > > > > + <dt> > > + <code>external_ids:ovn-managed-flow-restore-wait</code> in the > > + <code>Open_vSwitch</code> table > > + </dt> > > + <dd> > > + When set to true, this key indicates that > <code>ovn-controller</code> > > + has set the <code>other_config:flow-restore-wait</code> option. > > + The key is set when <code>ovn-controller</code> enables > > + flow-restore-wait and removed when it clears it. > > + </dd> > > + > > <dt> > > <code>external_ids:ct-zone-*</code> in the <code>Bridge</code> > table > > </dt> > > diff --git a/controller/ovn-controller.c b/controller/ovn-controller.c > > index 4161fe2b3..da43051ed 100644 > > --- a/controller/ovn-controller.c > > +++ b/controller/ovn-controller.c > > @@ -211,6 +211,152 @@ static char *get_file_system_id(void) > > free(filename); > > return ret; > > } > > + > > +/* Set/unset flow-restore-wait, and inc ovs next_cfg if false > > + * When set to true, also sets ovn-managed-flow-restore-wait to true to > > + * indicate ownership */ > > +static void > > +set_flow_restore_wait(struct ovsdb_idl_txn *ovs_idl_txn, > > + const struct ovsrec_open_vswitch *cfg, > > + const struct smap *other_config, > > + const bool val, bool ovn_managed) > > +{ > > + struct smap new_config; > > + smap_clone(&new_config, other_config); > > + smap_replace(&new_config, "flow-restore-wait", val ? "true": > "false"); > > + ovsrec_open_vswitch_set_other_config(cfg, &new_config); > > + if (val) { > > + ovsrec_open_vswitch_update_external_ids_setkey( > > + cfg, "ovn-managed-flow-restore-wait", "true"); > > + } else if (ovn_managed) { > > + ovsrec_open_vswitch_update_external_ids_delkey( > > + cfg, "ovn-managed-flow-restore-wait"); > > + } > > + ovsdb_idl_txn_increment(ovs_idl_txn, &cfg->header_, > > + &ovsrec_open_vswitch_col_next_cfg, true); > > + smap_destroy(&new_config); > > +} > > + > > +static void > > +manage_flow_restore_wait(struct ovsdb_idl_txn *ovs_idl_txn, > > + const struct ovsrec_open_vswitch *cfg, > > + uint64_t ofctrl_cur_cfg, uint64_t ovs_next_cfg, > > + int ovs_txn_status, bool is_ha_gw) > > +{ > > + enum flow_restore_wait_state { > > + FRW_INIT, /* Initial state */ > > + FRW_WAIT_TXN_COMPLETE, /* Sent false, waiting txn to complete */ > > + FRW_TXN_SUCCESS, /* Txn completed. Waiting for OVS Ack. */ > > + FRW_DONE /* Everything completed */ > > + }; > > + > > + static int64_t frw_next_cfg; > > + static enum flow_restore_wait_state frw_state; > > + static bool ofctrl_was_connected = false; > > + > > + bool ofctrl_connected = ofctrl_is_connected(); > > + > > + if (!ovs_idl_txn || !cfg) { > > + return; > > + } > > + > > + /* If OVS is stopped/started, make sure flow-restore-wait is > toggled. */ > > + if (ofctrl_connected && !ofctrl_was_connected) { > > + frw_state = FRW_INIT; > > + } > > + ofctrl_was_connected = ofctrl_connected; > > + > > + if (!ofctrl_connected) { > > + return; > > + } > > + > > + bool frw = smap_get_bool(&cfg->other_config, "flow-restore-wait", > false); > > + bool ovn_managed_once = smap_get_bool(&cfg->external_ids, > > + > "ovn-managed-flow-restore-wait", > > + false); > > + > > + if (frw && !ovn_managed_once) { > > + /* frw has been set by ovs-ctl. Do not touch. */ > > + return; > > + } > > + > > + if (!is_ha_gw) { > > + if (frw) { > > + /* frw has once been set by OVN. We are now not an HA > chassis > > + * anymore, unset it. */ > > + set_flow_restore_wait(ovs_idl_txn, cfg, &cfg->other_config, > > + false, ovn_managed_once); > > + } > > + /* else we are not an HA chassis and frw is false. Ignore it. */ > > + return; > > + } > > + > > + switch (frw_state) { > > + case FRW_INIT: > > + if (ofctrl_cur_cfg > 0) { > > + set_flow_restore_wait(ovs_idl_txn, cfg, &cfg->other_config, > > + false, ovn_managed_once); > > + frw_state = FRW_WAIT_TXN_COMPLETE; > > + VLOG_INFO("Setting flow-restore-wait=false " > > + "(cur_cfg=%"PRIu64")", ofctrl_cur_cfg); > > + } > > + break; > > + > > + case FRW_WAIT_TXN_COMPLETE: > > + /* if (ovs_idl_txn != NULL), the transaction completed. > > + * When the transaction completed, it either failed > > + * (ovs_txn_status == 0) or succeeded (ovs_txn_status != 0). */ > > + if (ovs_txn_status == 0) { > > + /* Previous transaction failed. */ > > + set_flow_restore_wait(ovs_idl_txn, cfg, &cfg->other_config, > > + false, ovn_managed_once); > > + break; > > + } > > + /* txn succeeded, get next_cfg */ > > + frw_next_cfg = ovs_next_cfg; > > + frw_state = FRW_TXN_SUCCESS; > > + /* fall through */ > > I also asked a helpful assistant :) (gemini-3) to review this code and > it complained here with: > > "I think there is a potential issue here when `ovs_txn_status` is `-1`. > In `main()`, `manage_flow_restore_wait` is called only when > `ovs_idl_txn` is NOT NULL. > > If `ovs_txn_status` was `-1` in the previous iteration, it means we were > waiting for a transaction. > > If `ovs_idl_txn` is now NOT NULL, it means `ovsdb_idl_loop_run()` > processed the completion of that transaction. > > However, `ovs_txn_status` still holds `-1` because it's only updated at > the end of the loop by `ovsdb_idl_loop_commit_and_wait()`. > > The current logic treats `-1` as success (since it's not `0`). If the > transaction actually failed, we might move to `FRW_TXN_SUCCESS` > prematurely. > > Should we wait for `ovs_txn_status` to be something other than `-1`? Or > can we reliably determine success/failure from the IDL state?" > " > > This does sound legit to me, ovs_txn_status may still be -1 because when > we tried to commit frw=false we couldn't immediately asses whether the > transaction would succeed or not (in most cases that's what happens) but > then the transaction failed for some reason on the server side. > > At this point, in the new loop, "ovs_idl_txn" is not NULL because we can > try a new transaction (nothing is in flight anymore) but we assume the > previous one succeeded. > > Then we fall through.. > > > + > > + case FRW_TXN_SUCCESS: > > + if (ovs_next_cfg < frw_next_cfg) { > > + /* DB was reset, next_cfg went backwards. */ > > + VLOG_INFO("OVS DB reset (next_cfg %"PRId64" -> %"PRIu64"), " > > + "resetting state", > > + frw_next_cfg, ovs_next_cfg); > > + set_flow_restore_wait(ovs_idl_txn, cfg, &cfg->other_config, > > + false, ovn_managed_once); > > + frw_state = FRW_WAIT_TXN_COMPLETE; > > + break; > > + } > > + > > frw is still "true" because we failed to set it to "false" (the > transaction failed server side). > > > + if (!frw) { > > + if (cfg->cur_cfg >= frw_next_cfg) { > > + set_flow_restore_wait(ovs_idl_txn, cfg, > &cfg->other_config, > > + true, ovn_managed_once); > > + frw_state = FRW_DONE; > > + VLOG_INFO("Setting flow-restore-wait=true"); > > + } > > + } else { > > So we enter here where we assume "another task already set it to true". > > But it was actually just never changed. > > Is this analysis correct? Do we need a way to get the ovs_txn_status in > the beginning of the current loop iteration? > I do not think so because of how ovsdb_idl_loop_runs. Loop 1 ---------- - We try to set frw to false - We commit (at the end of the loop, ovsdb_idl_loop_commit_and_wait) - We have txn_status = -1 (in_progress). Loop 2 ---------- - The txn fails in ovsdb_idl_loop_run. - Looking at ovsdb_idl_loop_run: - We call ovsdb_idl_run (which gets the status) - The txn failed, so commiting_txn != NULL. - We do not ovsdb_idl_try_commit_loop_txn (which would set committing_txn to NULL) as txn failed. - So loop->open_txn is NULL in this loop - We do not see the txn as completed in this loop. End of the loop 2 (ovsdb_idl_loop_commit_and_wait) - txn_status is set to 0. - loop->committing_txn is set to NULL Loop 3 ---------- - We have a txn - We still have status == 0, so in FRW_WAIT_TXN_COMPLETE we handle the failure. So, it looks OK to me > > > + /* The transaction to false succeeded but frw is true. > > + * So, another task already set it to true. */ > > + frw_state = FRW_DONE; > > + VLOG_INFO("flow-restore-wait was already true"); > > + } > > + break; > > + case FRW_DONE: > > + if (!frw) { > > + /* frw has been removed (e.g. by ovs-ctl restart) or is > false > > + * (e.g. txn failed.) */ > > + set_flow_restore_wait(ovs_idl_txn, cfg, &cfg->other_config, > > + false, ovn_managed_once); > > + frw_state = FRW_WAIT_TXN_COMPLETE; > > + VLOG_INFO("OVS frw cleared, restarting flow-restore-wait > sequence " > > + "(cur_cfg=%"PRIu64")", ofctrl_cur_cfg); > > + } > > + break; > > + } > > +} > > + > > /* Only set monitor conditions on tables that are available in the > > * server schema. > > */ > > @@ -3381,6 +3527,7 @@ en_mac_cache_cleanup(void *data) > > > > struct ed_type_bfd_chassis { > > struct sset bfd_chassis; > > + bool is_ha_gw; > > }; > > > > static void * > > @@ -3409,8 +3556,9 @@ en_bfd_chassis_run(struct engine_node *node, void > *data OVS_UNUSED) > > = chassis_lookup_by_name(sbrec_chassis_by_name, chassis_id); > > > > sset_clear(&bfd_chassis->bfd_chassis); > > - bfd_calculate_chassis(chassis, ha_chassis_grp_table, > > - &bfd_chassis->bfd_chassis); > > + bfd_chassis->is_ha_gw = bfd_calculate_chassis(chassis, > > + ha_chassis_grp_table, > > + > &bfd_chassis->bfd_chassis); > > return EN_UPDATED; > > } > > > > @@ -7117,6 +7265,7 @@ main(int argc, char *argv[]) > > struct unixctl_server *unixctl; > > struct ovn_exit_args exit_args = {0}; > > struct br_int_remote br_int_remote = {0}; > > + static uint64_t next_cfg = 0; > > int retval; > > > > /* Read from system-id-override file once on startup. */ > > @@ -7444,6 +7593,7 @@ main(int argc, char *argv[]) > > > > /* Main loop. */ > > int ovnsb_txn_status = 1; > > + int ovs_txn_status = 1; > > bool sb_monitor_all = false; > > struct tracked_acl_ids *tracked_acl_ids = NULL; > > while (!exit_args.exiting) { > > @@ -7545,6 +7695,11 @@ main(int argc, char *argv[]) > > pinctrl_update_swconn(br_int_remote.target, > > br_int_remote.probe_interval); > > > > + if (cfg && ovs_idl_txn && ovs_txn_status == -1) { > > + /* txn was in progress and is now completed */ > > + next_cfg = cfg->next_cfg; > > + } > > + > > /* Enable ACL matching for double tagged traffic. */ > > if (ovs_idl_txn && cfg) { > > int vlan_limit = smap_get_int( > > @@ -7894,6 +8049,13 @@ main(int argc, char *argv[]) > > stopwatch_start(OFCTRL_SEQNO_RUN_STOPWATCH_NAME, > > time_msec()); > > ofctrl_seqno_run(ofctrl_get_cur_cfg()); > > + if (ovs_idl_txn && bfd_chassis_data) { > > + manage_flow_restore_wait(ovs_idl_txn, cfg, > > + ofctrl_get_cur_cfg(), > > + next_cfg, > ovs_txn_status, > > + > bfd_chassis_data->is_ha_gw); > > + } > > + > > stopwatch_stop(OFCTRL_SEQNO_RUN_STOPWATCH_NAME, > > time_msec()); > > stopwatch_start(IF_STATUS_MGR_RUN_STOPWATCH_NAME, > > @@ -7993,7 +8155,7 @@ main(int argc, char *argv[]) > > OVS_NOT_REACHED(); > > } > > > > - int ovs_txn_status = > ovsdb_idl_loop_commit_and_wait(&ovs_idl_loop); > > + ovs_txn_status = ovsdb_idl_loop_commit_and_wait(&ovs_idl_loop); > > if (!ovs_txn_status) { > > /* The transaction failed. */ > > vif_plug_clear_deleted( > > @@ -8012,6 +8174,9 @@ main(int argc, char *argv[]) > > &vif_plug_deleted_iface_ids); > > vif_plug_finish_changed( > > &vif_plug_changed_iface_ids); > > + if (cfg) { > > + next_cfg = cfg->next_cfg; > > + } > > } else if (ovs_txn_status == -1) { > > /* The commit is still in progress */ > > } else { > > @@ -8085,7 +8250,7 @@ loop_done: > > } > > > > ovsdb_idl_loop_commit_and_wait(&ovnsb_idl_loop); > > - int ovs_txn_status = > ovsdb_idl_loop_commit_and_wait(&ovs_idl_loop); > > + ovs_txn_status = > ovsdb_idl_loop_commit_and_wait(&ovs_idl_loop); > > if (!ovs_txn_status) { > > /* The transaction failed. */ > > vif_plug_clear_deleted( > > diff --git a/tests/multinode-macros.at b/tests/multinode-macros.at > > index 4a74d5127..596de4c3a 100644 > > --- a/tests/multinode-macros.at > > +++ b/tests/multinode-macros.at > > @@ -41,6 +41,28 @@ m4_define([M_START_TCPDUMP], > > ] > > ) > > > > +m4_define([M_START_TCPDUMPS_RECURSIVE_], [ > > + m4_if(m4_eval($# > 3), [1], [dnl > > + names="$names $3" > > + echo "Running podman exec $1 tcpdump -l $2 >$3.tcpdump > 2>$3.stderr" > > + podman exec $1 tcpdump -l $2 >$3.tcpdump 2>$3.stderr & > > + echo "podman exec $1 ps -ef | grep -v grep | grep tcpdump && > podman exec $1 killall tcpdump" >> cleanup > > + M_START_TCPDUMPS_RECURSIVE_(m4_shift(m4_shift(m4_shift($@)))) > > + ]) > > + ] > > +) > > + > > +# Start Multiple tcpdump. Useful to speed up when many tcpdump > > +# must be started as waiting for "listening" takes usually 1 second. > > +m4_define([M_START_TCPDUMPS], > > + [ > > + names="" > > + M_START_TCPDUMPS_RECURSIVE_($@) > > + for name in $names; do > > + OVS_WAIT_UNTIL([grep -q "listening" ${name}.stderr]) > > + done > > + ] > > +) > > > > # M_FORMAT_CT([ip-addr]) > > # > > @@ -480,6 +502,30 @@ m_is_fedora() { > > m_central_as grep -qi fedora /etc/os-release > > } > > > > +# Run ovs-vsctl using Host socket > > +host_ovs_vsctl() { > > + # Discover host OVS socket on first call > > + if [[ -z "$HOST_OVS_SOCK" ]]; then > > + for sock in /run/openvswitch/db.sock > /var/run/openvswitch/db.sock /usr/local/var/run/openvswitch/db.sock; do > > + if [[ -S "$sock" ]]; then > > + HOST_OVS_SOCK=$sock > > + break > > + fi > > + done > > + # Fallback on unusual prefix: discover from running process > > + if [[ -z "$HOST_OVS_SOCK" ]]; then > > + HOST_OVS_SOCK=$(ps aux | grep '[o]vsdb-server' | grep -oP > 'punix:\K[^, ]+' | while read s; do > > + [[ -S "$s" ]] && [[ "$s" != *"$OVS_RUNDIR"* ]] && echo > "$s" && break > > + done) > > + fi > > + if [[ -z "$HOST_OVS_SOCK" ]]; then > > + echo "ERROR: Could not find host OVS socket" >&2 > > + AT_FAIL_IF([:]) > > + fi > > + fi > > + ovs-vsctl --db=unix:$HOST_OVS_SOCK "$@" > > +} > > + > > # M_START_L4_SERVER([fake_node], [namespace], [ip_addr], [port], > [reply_string], [pidfile]) > > # > > # Helper to properly start l4 server in inside 'fake_node''s namespace'. > > diff --git a/tests/multinode.at b/tests/multinode.at > > index bc1eb7a7c..c2587b68a 100644 > > --- a/tests/multinode.at > > +++ b/tests/multinode.at > > @@ -2986,42 +2986,42 @@ AT_CLEANUP > > > > AT_SETUP([HA: Check for missing garp on leader when BFD goes back up]) > > # Network topology > > -# > ┌────────────────────────────────────────────────────────────────────────────────────────────────────────┐ > > -# │ > │ > > -# │ ┌───────────────────┐ ┌───────────────────┐ > ┌───────────────────┐ ┌───────────────────┐ │ > > -# │ │ ovn-chassis-1 │ │ ovn-gw-1 │ │ > ovn-gw-2 │ │ ovn-chassis-2 │ │ > > -# │ └─────────┬─────────┘ └───────────────────┘ > └───────────────────┘ └───────────────────┘ │ > > -# │ ┌─────────┴─────────┐ > │ > > -# │ │ inside1 │ > │ > > -# │ │ 192.168.1.1/24 │ > │ > > -# │ └─────────┬─────────┘ > │ > > -# │ ┌─────────┴─────────┐ > │ > > -# │ │ inside │ > │ > > -# │ └─────────┬─────────┘ > │ > > -# │ ┌─────────┴─────────┐ > │ > > -# │ │ 192.168.1.254 │ > │ > > -# │ │ R1 │ > │ > > -# │ │ 192.168.0.254 │ > │ > > -# │ └─────────┬─────────┘ > │ > > -# │ > └------eth1---------------┬--------eth1-----------┐ > │ > > -# │ ┌──────────┴────────┐ > ┌─────────┴─────────┐ │ > > -# │ │ 192.168.1.254 │ │ > 192.168.1.254 │ │ > > -# │ │ R1 │ │ > R1 │ │ > > -# │ │ 192.168.0.254 │ │ > 192.168.0.254 │ │ > > -# │ └─────────┬─────────┘ > └─────────┬─────────┘ │ > > -# │ │ > │ ┌───────────────────┐ │ > > -# │ ┌─────────┴─────────┐ > ┌─────────┴─────────┐ │ 192.168.0.1 │ │ > > -# │ │ outside │ │ > outside │ │ ext1 │ │ > > -# │ └─────────┬─────────┘ > └─────────┬─────────┘ └─────────┬─────────┘ │ > > -# │ ┌─────────┴─────────┐ > ┌─────────┴─────────┐ ┌─────────┴─────────┐ │ > > -# │ │ ln-outside │ │ > ln-outside │ │ ln-ext1 │ │ > > -# │ └─────────┬─────────┘ > └─────────┬─────────┘ └─────────┬─────────┘ │ > > -# │ ┌─────────┴─────────┐ > ┌─────────┴─────────┐ ┌─────────┴─────────┐ │ > > -# │ │ br-ex │ │ > br-ex │ │ br-ex │ │ > > -# │ └─────────┬─────────┘ > └─────────┬─────────┘ └─────────┬─────────┘ │ > > -# │ > └---------eth2-----------┴-------eth2-------------┘ │ > > -# │ > │ > > -# > └────────────────────────────────────────────────────────────────────────────────────────────────────────┘ > > +# > ┌────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐ > > +# │ > │ > > +# │ ┌───────────────────┐ ┌───────────────────┐ > ┌───────────────────┐ ┌───────────────────┐ ┌───────────────────┐ │ > > +# │ │ ovn-chassis-1 │ │ ovn-chassis-2 │ │ ovn-gw-1 > │ │ ovn-gw-2 │ │ ovn-chassis-3 │ │ > > +# │ └─────────┬─────────┘ └─────────┬─────────┘ > └───────────────────┘ └───────────────────┘ └───────────────────┘ │ > > +# │ ┌─────────┴─────────┐ ┌─────────┴─────────┐ > │ > > +# │ │ inside1 │ │ inside2 │ > │ > > +# │ │ 192.168.1.1/24 │ │ 192.168.1.2/24 │ > │ > > +# │ └─────────┬─────────┘ └─────────┬─────────┘ > │ > > +# │ ┌─┴────────────────────────┴─┐ > │ > > +# │ │ inside │ > │ > > +# │ └──────────────┬─────────────┘ > │ > > +# │ ┌─────────┴─────────┐ > │ > > +# │ │ 192.168.1.254 │ > │ > > +# │ │ R1 │ > │ > > +# │ │ 192.168.0.254 │ > │ > > +# │ └─────────┬─────────┘ > │ > > +# │ > └------eth1---------------------------┬--------eth1-----------┐ > │ > > +# │ > ┌──────────┴────────┐ ┌─────────┴─────────┐ > │ > > +# │ │ > 192.168.1.254 │ │ 192.168.1.254 │ │ > > +# │ │ > R1 │ │ R1 │ │ > > +# │ │ > 192.168.0.254 │ │ 192.168.0.254 │ │ > > +# │ > └─────────┬─────────┘ └─────────┬─────────┘ > │ > > +# │ │ > │ ┌───────────────────┐ │ > > +# │ > ┌─────────┴─────────┐ ┌─────────┴─────────┐ │ 192.168.0.1 │ > │ > > +# │ │ > outside │ │ outside │ │ ext1 │ │ > > +# │ > └─────────┬─────────┘ └─────────┬─────────┘ └─────────┬─────────┘ > │ > > +# │ > ┌─────────┴─────────┐ ┌─────────┴─────────┐ ┌─────────┴─────────┐ > │ > > +# │ │ > ln-outside │ │ ln-outside │ │ ln-ext1 │ │ > > +# │ > └─────────┬─────────┘ └─────────┬─────────┘ └─────────┬─────────┘ > │ > > +# │ > ┌─────────┴─────────┐ ┌─────────┴─────────┐ ┌─────────┴─────────┐ > │ > > +# │ │ > br-ex │ │ br-ex │ │ br-ex │ │ > > +# │ > └─────────┬─────────┘ └─────────┬─────────┘ └─────────┬─────────┘ > │ > > +# │ > └---------eth2-----------┴-------eth2-------------┘ │ > > +# │ > │ > > +# > └────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘ > > > > # The goal of this test is the check that GARP are properly generated > by higest priority traffic when > > # BFD goes down, and back up, and this whether the BFD event is due > either to some bfd packet lost > > @@ -3030,6 +3030,12 @@ AT_SETUP([HA: Check for missing garp on leader > when BFD goes back up]) > > # So gw3 should in this test neither send garp or receive packets. > > # > > # Enable vconn so we can check the GARP from a log perspective. > > +on_exit "podman exec ovn-gw-1 ovn-appctl vlog/set info" > > +on_exit "podman exec ovn-gw-1 ovn-appctl vlog/enable-rate-limit" > > +on_exit "podman exec ovn-gw-2 ovn-appctl vlog/set info" > > +on_exit "podman exec ovn-gw-2 ovn-appctl vlog/enable-rate-limit" > > +on_exit "podman exec ovn-gw-3 ovn-appctl vlog/set info" > > +on_exit "podman exec ovn-gw-3 ovn-appctl vlog/enable-rate-limit" > > m_as ovn-gw-1 ovn-appctl vlog/set vconn:dbg > > m_as ovn-gw-2 ovn-appctl vlog/set vconn:dbg > > m_as ovn-gw-3 ovn-appctl vlog/set vconn:dbg > > @@ -3037,12 +3043,17 @@ m_as ovn-gw-1 ovn-appctl vlog/disable-rate-limit > > m_as ovn-gw-2 ovn-appctl vlog/disable-rate-limit > > m_as ovn-gw-3 ovn-appctl vlog/disable-rate-limit > > > > +# Decrease revalidation time on ovs switch simulating ToR. > > +check host_ovs_vsctl set Open_vSwitch . other_config:max-revalidator=100 > > +on_exit "check host_ovs_vsctl remove Open_vSwitch . other_config > max-revalidator" > > + > > check_fake_multinode_setup > > > > # Delete the multinode NB and OVS resources before starting the test. > > cleanup_multinode_resources > > > > ip_ch1=$(m_as ovn-chassis-1 ip a show dev eth1 | grep "inet " | awk > '{print $2}'| cut -d '/' -f1) > > +ip_ch2=$(m_as ovn-chassis-2 ip a show dev eth1 | grep "inet " | awk > '{print $2}'| cut -d '/' -f1) > > ip_gw1=$(m_as ovn-gw-1 ip a show dev eth1 | grep "inet " | awk '{print > $2}'| cut -d '/' -f1) > > ip_gw2=$(m_as ovn-gw-2 ip a show dev eth1 | grep "inet " | awk '{print > $2}'| cut -d '/' -f1) > > ip_gw3=$(m_as ovn-gw-3 ip a show dev eth1 | grep "inet " | awk '{print > $2}'| cut -d '/' -f1) > > @@ -3050,25 +3061,35 @@ ip_gw3=$(m_as ovn-gw-3 ip a show dev eth1 | grep > "inet " | awk '{print $2}'| cut > > from_gw1_to_gw2=$(m_as ovn-gw-1 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_gw2) > > from_gw1_to_gw3=$(m_as ovn-gw-1 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_gw3) > > from_gw1_to_ch1=$(m_as ovn-gw-1 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_ch1) > > +from_gw1_to_ch2=$(m_as ovn-gw-1 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_ch2) > > from_gw2_to_gw1=$(m_as ovn-gw-2 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_gw1) > > from_gw2_to_gw3=$(m_as ovn-gw-2 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_gw3) > > from_gw2_to_ch1=$(m_as ovn-gw-2 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_ch1) > > +from_gw2_to_ch2=$(m_as ovn-gw-2 ovs-vsctl --bare --columns=name find > interface options:remote_ip=$ip_ch2) > > from_ch1_to_gw1=$(m_as ovn-chassis-1 ovs-vsctl --bare --columns=name > find interface options:remote_ip=$ip_gw1) > > from_ch1_to_gw2=$(m_as ovn-chassis-1 ovs-vsctl --bare --columns=name > find interface options:remote_ip=$ip_gw2) > > +from_ch2_to_gw1=$(m_as ovn-chassis-2 ovs-vsctl --bare --columns=name > find interface options:remote_ip=$ip_gw1) > > +from_ch2_to_gw2=$(m_as ovn-chassis-2 ovs-vsctl --bare --columns=name > find interface options:remote_ip=$ip_gw2) > > > > m_as ovn-chassis-1 ip link del hv1-vif1-p > > -m_as ovn-chassis-2 ip link del ext1-p > > +m_as ovn-chassis-2 ip link del hv2-vif1-p > > +m_as ovn-chassis-3 ip link del ext1-p > > > > OVS_WAIT_UNTIL([m_as ovn-chassis-1 ip link show | grep -q genev_sys]) > > OVS_WAIT_UNTIL([m_as ovn-chassis-2 ip link show | grep -q genev_sys]) > > +OVS_WAIT_UNTIL([m_as ovn-chassis-3 ip link show | grep -q genev_sys]) > > OVS_WAIT_UNTIL([m_as ovn-gw-1 ip link show | grep -q genev_sys]) > > OVS_WAIT_UNTIL([m_as ovn-gw-2 ip link show | grep -q genev_sys]) > > OVS_WAIT_UNTIL([m_as ovn-gw-3 ip link show | grep -q genev_sys]) > > > > +# Use "aggressive" bfd parameters > > +check multinode_nbctl set NB_Global . options:"bfd-min-rx"=500 > > +check multinode_nbctl set NB_Global . options:"bfd-min-tx"=100 > > check multinode_nbctl ls-add inside > > check multinode_nbctl ls-add outside > > check multinode_nbctl ls-add ext > > check multinode_nbctl lsp-add inside inside1 -- lsp-set-addresses > inside1 "f0:00:c0:a8:01:01 192.168.1.1" > > +check multinode_nbctl lsp-add inside inside2 -- lsp-set-addresses > inside2 "f0:00:c0:a8:01:02 192.168.1.2" > > check multinode_nbctl lsp-add ext ext1 -- lsp-set-addresses ext1 > "00:00:c0:a8:00:01 192.168.0.1" > > > > multinode_nbctl create Logical_Router name=R1 > > @@ -3100,12 +3121,14 @@ m_as ovn-gw-3 ovs-vsctl remove open . > external_ids garp-max-timeout-sec > > > > m_as ovn-chassis-1 ovs-vsctl set open . > external-ids:ovn-bridge-mappings=public:br-ex > > m_as ovn-chassis-2 ovs-vsctl set open . > external-ids:ovn-bridge-mappings=public:br-ex > > +m_as ovn-chassis-3 ovs-vsctl set open . > external-ids:ovn-bridge-mappings=public:br-ex > > m_as ovn-gw-1 ovs-vsctl set open . > external-ids:ovn-bridge-mappings=public:br-ex > > m_as ovn-gw-2 ovs-vsctl set open . > external-ids:ovn-bridge-mappings=public:br-ex > > m_as ovn-gw-3 ovs-vsctl set open . > external-ids:ovn-bridge-mappings=public:br-ex > > > > m_as ovn-chassis-1 /data/create_fake_vm.sh inside1 hv1-vif1 > f0:00:c0:a8:01:01 1500 192.168.1.1 24 192.168.1.254 2000::1/64 2000::a > > -m_as ovn-chassis-2 /data/create_fake_vm.sh ext1 ext1 00:00:c0:a8:00:01 > 1500 192.168.0.1 24 192.168.0.254 1000::3/64 1000::a > > +m_as ovn-chassis-2 /data/create_fake_vm.sh inside2 hv2-vif1 > f0:00:c0:a8:01:02 1500 192.168.1.2 24 192.168.1.254 2000::2/64 2000::a > > +m_as ovn-chassis-3 /data/create_fake_vm.sh ext1 ext1 00:00:c0:a8:00:01 > 1500 192.168.0.1 24 192.168.0.254 1000::3/64 1000::a > > > > # There should be one ha_chassis_group with the name "R1_outside" > > m_check_row_count HA_Chassis_Group 1 name=R1_outside > > @@ -3160,53 +3183,67 @@ for chassis in $from_ch1_to_gw1 > $from_ch1_to_gw2; do > > wait_bfd_enabled ovn-chassis-1 $chassis > > done > > > > +# check BFD enablement on tunnel ports from ovn-chassis-2 ########### > > +for chassis in $from_ch2_to_gw1 $from_ch2_to_gw2; do > > + echo "checking ovn-chassis-2 -> $chassis" > > + wait_bfd_enabled ovn-chassis-2 $chassis > > +done > > + > > # Make sure there is no nft table left. Do not use nft directly as > might not be installed in container. > > gw1_pid=$(podman inspect -f '{{.State.Pid}}' ovn-gw-1) > > nsenter --net=/proc/$gw1_pid/ns/net nft list tables | grep ovn-test && > nsenter --net=/proc/$gw1_pid/ns/net nft delete table ip ovn-test > > -on_exit "nsenter --net=/proc/$gw1_pid/ns/net nft list tables | grep > ovn-test && nsenter --net=/proc/$gw1_pid/ns/net nft delete table ip > ovn-test" > > +on_exit "if [[ -d "/proc/$gw1_pid" ]]; then nsenter > --net=/proc/$gw1_pid/ns/net nft list tables | grep ovn-test && nsenter > --net=/proc/$gw1_pid/ns/net nft delete table ip ovn-test; fi" > > > > -for chassis in $from_gw1_to_gw2 $from_gw1_to_gw3 $from_gw1_to_ch1; do > > +for chassis in $from_gw1_to_gw2 $from_gw1_to_gw3 $from_gw1_to_ch1 > $from_gw1_to_ch2; do > > wait_bfd_up ovn-gw-1 $chassis > > done > > -for chassis in $from_gw2_to_gw1 $from_gw2_to_gw3 $from_gw2_to_ch1; do > > +for chassis in $from_gw2_to_gw1 $from_gw2_to_gw3 $from_gw2_to_ch1 > $from_gw2_to_ch2; do > > wait_bfd_up ovn-gw-2 $chassis > > done > > for chassis in $from_ch1_to_gw1 $from_ch1_to_gw2; do > > wait_bfd_up ovn-chassis-1 $chassis > > done > > +for chassis in $from_ch2_to_gw1 $from_ch2_to_gw2; do > > + wait_bfd_up ovn-chassis-2 $chassis > > +done > > > > m_wait_row_count Port_Binding 1 logical_port=cr-R1_outside > chassis=$gw1_chassis > > check multinode_nbctl --wait=hv sync > > > > start_tcpdump() { > > echo "$(date +%H:%M:%S.%03N) Starting tcpdump" > > - M_START_TCPDUMP([ovn-chassis-1], [-neei hv1-vif1-p], [ch1]) > > - M_START_TCPDUMP([ovn-chassis-2], [-neei eth2], [ch2]) > > - M_START_TCPDUMP([ovn-gw-1], [-neei eth2], [gw1]) > > - M_START_TCPDUMP([ovn-gw-1], [-neei eth2 -Q out], [gw1_out]) > > - M_START_TCPDUMP([ovn-gw-2], [-neei eth2], [gw2]) > > - M_START_TCPDUMP([ovn-gw-2], [-neei eth2 -Q out], [gw2_out]) > > - M_START_TCPDUMP([ovn-gw-3], [-neei eth2], [gw3]) > > - M_START_TCPDUMP([ovn-gw-3], [-neei eth2 -Q out], [gw3_out]) > > + M_START_TCPDUMPS([ovn-chassis-1], [-neei hv1-vif1-p], [ch1], > > + [ovn-chassis-2], [-neei hv2-vif1-p], [ch2], > > + [ovn-chassis-3], [-neei eth2], [ch3], > > + [ovn-gw-1], [-neei eth2], [gw1], > > + [ovn-gw-1], [-neei eth2 -Q out], [gw1_out], > > + [ovn-gw-2], [-neei eth2], [gw2], > > + [ovn-gw-2], [-neei eth2 -Q out], [gw2_out], > > + [ovn-gw-3], [-neei eth2], [gw3], > > + [ovn-gw-3], [-neei eth2 -Q out], [gw3_out], > > + [ovn-gw-1], [-neei eth1], [gw1_eth1], > > + [ovn-gw-2], [-neei eth1], [gw2_eth1], > > + [ovn-chassis-1], [-neei eth1], [ch1_eth1], > > + [ovn-chassis-2], [-neei eth1], [ch2_eth1]) > > } > > > > stop_tcpdump() { > > echo "$(date +%H:%M:%S.%03N) Stopping tcpdump" > > - m_kill 'ovn-gw-1 ovn-gw-2 ovn-gw-3 ovn-chassis-1 ovn-chassis-2' > tcpdump > > + m_kill 'ovn-gw-1 ovn-gw-2 ovn-gw-3 ovn-chassis-1 ovn-chassis-2 > ovn-chassis-3' tcpdump > > } > > > > -# Send packets from chassis2 (ext1) to chassis1 > > +# Send packets from ovn-chassis-3 (ext1) to ovn-chassis-1 > > send_background_packets() { > > echo "$(date +%H:%M:%S.%03N) Sending packets in Background" > > start_tcpdump > > - M_NS_DAEMONIZE([ovn-chassis-2], [ext1], [ping -f -i 0.1 > 192.168.1.1], [ping.pid]) > > + M_NS_DAEMONIZE([ovn-chassis-3], [ext1], [ping -f -i 0.1 > 192.168.1.1], [ping.pid]) > > } > > > > stop_sending_background_packets() { > > echo "$(date +%H:%M:%S.%03N) Stopping Background process" > > m_as ovn-chassis-1 ps -ef | grep -v grep | grep -q ping && \ > > m_as ovn-chassis-1 echo "Stopping ping on ovn-chassis-1" && > killall ping > > - m_as ovn-chassis-2 ps -ef | grep -v grep | grep -q ping && \ > > + m_as ovn-chassis-3 ps -ef | grep -v grep | grep -q ping && \ > > m_as ovn-chassis-2 echo "Stopping ping on ovn-chassis-2" && > killall ping > > stop_tcpdump > > } > > @@ -3216,8 +3253,8 @@ check_for_new_garps() { > > expecting_garp=$2 > > n_new_garps=$(cat ${hv}_out.tcpdump | grep -c "f0:00:c0:a8:00:fe > > Broadcast, ethertype ARP (0x0806), length 42: Request who-has 192.168.0.254 > tell 192.168.0.254, length 28") > > > > - if [ "$expecting_garp" == "true" ]; then > > - AS_BOX([$(date +%H:%M:%S.%03N) Waiting/checking for garp from > $hv - Starting with $n_new_garps]) > > + if [[ "$expecting_garp" == "true" ]]; then > > + echo "$(date +%H:%M:%S.%03N) Waiting/checking for garp from $hv > - Starting with $n_new_garps" > > OVS_WAIT_UNTIL([ > > n_garps=$n_new_garps > > n_new_garps=$(cat ${hv}_out.tcpdump | grep -c > "f0:00:c0:a8:00:fe > Broadcast, ethertype ARP (0x0806), length 42: Request > who-has 192.168.0.254 tell 192.168.0.254, length 28") > > @@ -3225,7 +3262,7 @@ check_for_new_garps() { > > test "$n_garps" -ne "$n_new_garps" > > ]) > > else > > - AS_BOX([$(date +%H:%M:%S.%03N) Checking no garp from ${hv}]) > > + echo "$(date +%H:%M:%S.%03N) Checking no garp from ${hv}" > > # Waiting a few seconds to get a chance to see unexpected garps. > > sleep 3 > > n_garps=$(cat ${hv}_out.tcpdump | grep -c "f0:00:c0:a8:00:fe > > Broadcast, ethertype ARP (0x0806), length 42: Request who-has 192.168.0.254 > tell 192.168.0.254, length 28") > > @@ -3241,8 +3278,8 @@ check_for_new_echo_pkts() { > > n_new_echo_req=$(cat ${hv}.tcpdump | grep -c "$mac_src > $mac_dst, > ethertype IPv4 (0x0800), length 98: 192.168.0.1 > 192.168.1.1: ICMP echo > request") > > n_new_echo_rep=$(cat ${hv}.tcpdump | grep -c "$mac_dst > $mac_src, > ethertype IPv4 (0x0800), length 98: 192.168.1.1 > 192.168.0.1: ICMP echo > reply") > > > > - if [ "$expecting_pkts" == "true" ]; then > > - AS_BOX([$(date +%H:%M:%S.%03N) Waiting/checking for echo pkts > through ${hv}]) > > + if [[ "$expecting_pkts" == "true" ]]; then > > + echo "$(date +%H:%M:%S.%03N) Waiting/checking for echo pkts > through ${hv}" > > echo "Starting with $n_new_echo_req requests and > $n_new_echo_rep replies so far on ${hv}." > > OVS_WAIT_UNTIL([ > > n_echo_req=$n_new_echo_req > > @@ -3253,7 +3290,7 @@ check_for_new_echo_pkts() { > > test "$n_echo_req" -ne "$n_new_echo_req" && test > "$n_echo_rep" -ne "$n_new_echo_rep" > > ]) > > else > > - AS_BOX([$(date +%H:%M:%S.%03N) Checking no pkts from ${hv}]) > > + echo "$(date +%H:%M:%S.%03N) Checking no pkts from ${hv}" > > # Waiting a few seconds to get a chance to see unexpected pkts. > > sleep 3 > > n_echo_req=$(cat ${hv}.tcpdump | grep -c "$mac_src > $mac_dst, > ethertype IPv4 (0x0800), length 98: 192.168.0.1 > 192.168.1.1: ICMP echo > request") > > @@ -3271,22 +3308,44 @@ dump_statistics() { > > ch1_rep=$(grep -c "ICMP echo reply" ch1.tcpdump) > > ch2_req=$(grep -c "ICMP echo request" ch2.tcpdump) > > ch2_rep=$(grep -c "ICMP echo reply" ch2.tcpdump) > > + ch3_req=$(grep -c "ICMP echo request" ch3.tcpdump) > > + ch3_rep=$(grep -c "ICMP echo reply" ch3.tcpdump) > > gw1_req=$(grep -c "ICMP echo request" gw1.tcpdump) > > gw1_rep=$(grep -c "ICMP echo reply" gw1.tcpdump) > > gw2_req=$(grep -c "ICMP echo request" gw2.tcpdump) > > gw2_rep=$(grep -c "ICMP echo reply" gw2.tcpdump) > > gw3_req=$(grep -c "ICMP echo request" gw3.tcpdump) > > gw3_rep=$(grep -c "ICMP echo reply" gw3.tcpdump) > > - echo "$n1 claims in gw1, $n2 in gw2 and $n3 on gw3" > > - echo "ch2_request=$ch2_req gw1_request=$gw1_req > gw2_request=$gw2_req gw3_request=$gw3_req ch1_request=$ch1_req > ch1_reply=$ch1_rep gw1_reply=$gw1_rep gw2_reply=$gw2_rep gw3_reply=$gw3_rep > ch2_reply=$ch2_rep" > > + echo "$n1 claims in gw1, $n2 in gw2 and $n3 on gw3" >&2 > > + echo "ch3_req=$ch3_req gw_req=($gw1_req + $gw2_req +$gw3_req) > ch1_req=$ch1_req ch1_rep=$ch1_rep gw_rep=($gw1_rep + $gw2_rep + $gw3_rep) > ch3_rep=$ch3_rep ch2=($ch2_req+$ch2_rep)" >&2 > > + echo "$((ch3_req - ch3_rep))" > > } > > > > -check_migration_between_gw1_and_gw2() { > > - action=$1 > > - send_background_packets > > +add_port() { > > + bridge=$1 > > + interface=$2 > > + address=$3 > > + echo "Adding $bridge $interface $address" > > + > > + pid=$(podman inspect -f '{{.State.Pid}}' ovn-gw-1) > > + ln -sf /proc/$pid/ns/net /var/run/netns/$pid > > + port=$(host_ovs_vsctl --data=bare --no-heading --columns=name find > interface \ > > + external_ids:container_id=ovn-gw-1 > external_ids:container_iface="$interface") > > + port="${port:0:13}" > > + ip link add "${port}_l" type veth peer name "${port}_c" > > + ip link set "${port}_l" up > > + ip link set "${port}_c" netns $pid > > + ip netns exec $pid ip link set dev "${port}_c" name "$interface" > > + ip netns exec $pid ip link set "$interface" up > > + if [[ -n "$address" ]]; then > > + ip netns exec $pid ip addr add "$address" dev "$interface" > > + fi > > +} > > > > +prepare() { > > + send_background_packets > > # We make sure gw1 is leader since enough time that it generated > all its garps. > > - AS_BOX([$(date +%H:%M:%S.%03N) Waiting all garps sent by gw1]) > > + echo $(date +%H:%M:%S.%03N) Waiting all garps sent by gw1 > > n_new_garps=$(cat gw1_out.tcpdump | grep -c "f0:00:c0:a8:00:fe > > Broadcast, ethertype ARP (0x0806), length 42: Request who-has 192.168.0.254 > tell 192.168.0.254, length 28") > > OVS_WAIT_UNTIL([ > > n_garps=$n_new_garps > > @@ -3302,130 +3361,269 @@ check_migration_between_gw1_and_gw2() { > > check_for_new_echo_pkts gw2 "00:00:c0:a8:00:01" "f0:00:c0:a8:00:fe" > "false" > > check_for_new_echo_pkts gw3 "00:00:c0:a8:00:01" "f0:00:c0:a8:00:fe" > "false" > > > > + # All packets should go through gw1, and none through gw2 or gw3. > > + check_packets "true" "false" "false" "true" > > flap_count_gw_1=$(m_as ovn-gw-1 ovs-vsctl get interface > $from_gw1_to_gw2 bfd_status | sed 's/.*flap_count=\"\([[0-9]]*\).*/\1/g') > > flap_count_gw_2=$(m_as ovn-gw-2 ovs-vsctl get interface > $from_gw2_to_gw1 bfd_status | sed 's/.*flap_count=\"\([[0-9]]*\).*/\1/g') > > +} > > > > - if [ test "$action" == "stop_bfd" ]; then > > - AS_BOX([$(date +%H:%M:%S.%03N) Blocking bfd on gw1 (from > $ip_gw1 to $ip_gw2)]) > > - nsenter --net=/proc/$gw1_pid/ns/net nft add table ip ovn-test > > - nsenter --net=/proc/$gw1_pid/ns/net nft 'add chain ip ovn-test > INPUT { type filter hook input priority 0; policy accept; }' > > - # Drop BFD from gw-1 to gw-2: geneve port (6081), inner port > 3784 (0xec8), Session state Up, Init, Down. > > - nsenter --net=/proc/$gw1_pid/ns/net nft add rule ip ovn-test > INPUT ip daddr $ip_gw1 ip saddr $ip_gw2 udp dport 6081 '@th,416,16 == > 0x0ec8 @th,472,8 == 0xc0 counter drop' > > - nsenter --net=/proc/$gw1_pid/ns/net nft add rule ip ovn-test > INPUT ip daddr $ip_gw1 ip saddr $ip_gw2 udp dport 6081 '@th,416,16 == > 0x0ec8 @th,472,8 == 0x80 counter drop' > > - nsenter --net=/proc/$gw1_pid/ns/net nft add rule ip ovn-test > INPUT ip daddr $ip_gw1 ip saddr $ip_gw2 udp dport 6081 '@th,416,16 == > 0x0ec8 @th,472,8 == 0x40 counter drop' > > - > > - # We do not check that packets go through gw2 as BFD between > chassis-2 and gw1 is still up > > - fi > > - > > - if [ test "$action" == "kill_gw2" ]; then > > - AS_BOX([$(date +%H:%M:%S.%03N) Killing gw2 ovn-controller]) > > - on_exit 'm_as ovn-gw-2 /usr/share/openvswitch/scripts/ovs-ctl > status || > > - m_as ovn-gw-2 /usr/share/openvswitch/scripts/ovs-ctl > start --system-id=ovn-gw-2' > > - on_exit 'm_as ovn-gw-2 /usr/share/ovn/scripts/ovn-ctl > status_controller || > > - m_as ovn-gw-2 /usr/share/ovn/scripts/ovn-ctl > start_controller ${CONTROLLER_SSL_ARGS}' > > - > > - m_as ovn-gw-2 kill -9 $(m_as ovn-gw-2 cat > /run/ovn/ovn-controller.pid) > > - m_as ovn-gw-2 kill -9 $(m_as ovn-gw-2 cat > /run/openvswitch/ovs-vswitchd.pid) > > - m_as ovn-gw-2 kill -9 $(m_as ovn-gw-2 cat > /run/openvswitch/ovsdb-server.pid) > > - # Also delete datapath (flows) > > - m_as ovn-gw-2 ovs-dpctl del-dp system@ovs-system > > - fi > > - > > - if [ test "$action" == "kill_gw1" ]; then > > - AS_BOX([$(date +%H:%M:%S.%03N) Killing gw1 ovn-controller]) > > - on_exit 'm_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl > status || > > - m_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl > start --system-id=ovn-gw-1' > > - on_exit 'm_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl > status_controller || > > - m_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl > start_controller ${CONTROLLER_SSL_ARGS}' > > - > > - m_as ovn-gw-1 kill -9 $(m_as ovn-gw-1 cat > /run/ovn/ovn-controller.pid) > > - m_as ovn-gw-1 kill -9 $(m_as ovn-gw-1 cat > /run/openvswitch/ovs-vswitchd.pid) > > - m_as ovn-gw-1 kill -9 $(m_as ovn-gw-1 cat > /run/openvswitch/ovsdb-server.pid) > > - # Also delete datapath (flows) > > - m_as ovn-gw-1 ovs-dpctl del-dp system@ovs-system > > - fi > > +check_loss_after_flap() > > +{ > > + dead=$1 > > + max_expected_loss=$2 > > > > - if [ test "$action" == "kill_gw2" ]; then > > - AS_BOX([$(date +%H:%M:%S.%03N) Waiting for flap count between > gw1 and gw2 to increase]) > > + if [[ "$dead" == "gw2" ]]; then > > + echo "$(date +%H:%M:%S.%03N) Waiting for flap count between gw1 > and gw2 to increase" > > OVS_WAIT_UNTIL([ > > new_flap_count=$(m_as ovn-gw-1 ovs-vsctl get interfac > $from_gw1_to_gw2 bfd_status | sed 's/.*flap_count=\"\([[0-9]]*\).*/\1/g') > > echo "Comparing $new_flap_count versus $flap_count_gw_1" > > test "$new_flap_count" -gt "$((flap_count_gw_1))" > > ]) > > else > > - AS_BOX([$(date +%H:%M:%S.%03N) Waiting for flap count between > gw2 and gw1 to increase]) > > + echo "$(date +%H:%M:%S.%03N) Waiting for flap count between gw2 > and gw1 to increase])" > > OVS_WAIT_UNTIL([ > > new_flap_count=$(m_as ovn-gw-2 ovs-vsctl get interfac > $from_gw2_to_gw1 bfd_status | sed 's/.*flap_count=\"\([[0-9]]*\).*/\1/g') > > echo "Comparing $new_flap_count versus $flap_count_gw_2" > > test "$new_flap_count" -gt "$((flap_count_gw_2))" > > ]) > > - > > fi > > - AS_BOX([$(date +%H:%M:%S.%03N) Flapped!]) > > > > + echo "$(date +%H:%M:%S.%03N) Flapped!" > > # Wait a few more second for the fight. > > + sleep 4 > > + > > + echo "$(date +%H:%M:%S.%03N) Statistics after flapping" > > + lost=$(dump_statistics) > > + echo "===> $lost packet lost while handling migration" > > + AT_CHECK([test "$lost" -le "$max_expected_loss"]) > > +} > > + > > +final_check() > > +{ > > + action=$1 > > + lost=$2 > > + max_expected_loss_after_restoration=$3 > > + > > + # Wait a little more to get packets while network is restored > > sleep 2 > > - AS_BOX([$(date +%H:%M:%S.%03N) Statistics after flapping]) > > - dump_statistics > > - > > - if [ test "$action" == "stop_bfd" ]; then > > - # gw1 still alive and gw2 tried to claim => gw1 should restart > generating garps. > > - check_for_new_garps gw1 "true" > > - check_for_new_garps gw2 "false" > > - check_for_new_garps gw3 "false" > > - check_for_new_echo_pkts gw1 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "true" > > - check_for_new_echo_pkts gw2 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts gw3 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts ch1 f0:00:c0:a8:01:fe f0:00:c0:a8:01:01 > "true" > > - AS_BOX([$(date +%H:%M:%S.%03N) Unblocking bfd on gw1]) > > - nsenter --net=/proc/$gw1_pid/ns/net nft -a list ruleset > > - nsenter --net=/proc/$gw1_pid/ns/net nft delete table ip ovn-test > > - fi > > + echo "$(date +%H:%M:%S.%03N) Statistics after network restored > (after $action)" > > + new_lost=$(dump_statistics) > > + echo "===> $((new_lost - lost)) packets lost during network > restoration" > > + AT_CHECK([test "$((new_lost - lost))" -le > "$max_expected_loss_after_restoration"]) > > + stop_sending_background_packets > > +} > > > > - if [ test "$action" == "kill_gw2" ]; then > > - # gw1 still alive, but gw2 did not try to claim => gw1 should > not generate new garps. > > - check_for_new_garps gw1 "false" > > - check_for_new_garps gw2 "false" > > - check_for_new_garps gw3 "false" > > - check_for_new_echo_pkts gw1 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "true" > > - check_for_new_echo_pkts gw2 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts gw3 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts ch1 f0:00:c0:a8:01:fe f0:00:c0:a8:01:01 > "true" > > - AS_BOX([$(date +%H:%M:%S.%03N) Restarting gw2 ovn-vswitchd]) > > - m_as ovn-gw-2 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-2 > > - > > - AS_BOX([$(date +%H:%M:%S.%03N) Restarting gw2 ovn-controller]) > > - m_as ovn-gw-2 /usr/share/ovn/scripts/ovn-ctl start_controller > ${CONTROLLER_SSL_ARGS} > > - fi > > +check_garps() > > +{ > > + check_for_new_garps gw1 "$1" > > + check_for_new_garps gw2 "$2" > > + check_for_new_garps gw3 "$3" > > +} > > > > - if [ test "$action" == "kill_gw1" ]; then > > - # gw1 died => gw2 should generate garps. > > - check_for_new_garps gw1 "false" > > - check_for_new_garps gw2 "true" > > - check_for_new_garps gw3 "false" > > - check_for_new_echo_pkts gw1 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts gw2 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "true" > > - check_for_new_echo_pkts gw3 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts ch1 f0:00:c0:a8:01:fe f0:00:c0:a8:01:01 > "true" > > - AS_BOX([$(date +%H:%M:%S.%03N) Restarting gw1 ovn-vswitchd]) > > - m_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-1 > > - > > - AS_BOX([$(date +%H:%M:%S.%03N) Restarting gw1 ovn-controller]) > > - m_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl start_controller > ${CONTROLLER_SSL_ARGS} > > - fi > > +check_packets() > > +{ > > + check_for_new_echo_pkts gw1 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe "$1" > > + check_for_new_echo_pkts gw2 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe "$2" > > + check_for_new_echo_pkts gw3 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe "$3" > > + check_for_new_echo_pkts ch1 f0:00:c0:a8:01:fe f0:00:c0:a8:01:01 "$4" > > +} > > + > > +check_migration_between_gw1_and_gw2_bfd_stop() > > +{ > > + AS_BOX([$(date +%H:%M:%S.%03N) Testing migration after bfd_stop]) > > + max_expected_max_expected_loss1=$1 > > + max_expected_max_expected_loss2=$2 > > + prepare > > + > > + echo "$(date +%H:%M:%S.%03N) Blocking bfd on gw1 (from $ip_gw1 to > $ip_gw2)" > > + nsenter --net=/proc/$gw1_pid/ns/net nft add table ip ovn-test > > + nsenter --net=/proc/$gw1_pid/ns/net nft 'add chain ip ovn-test > INPUT { type filter hook input priority 0; policy accept; }' > > + # Drop BFD from gw-1 to gw-2: geneve port (6081), inner port 3784 > (0xec8), Session state Up, Init, Down. > > + nsenter --net=/proc/$gw1_pid/ns/net nft add rule ip ovn-test INPUT > ip daddr $ip_gw1 ip saddr $ip_gw2 udp dport 6081 '@th,416,16 == 0x0ec8 > @th,472,8 == 0xc0 counter drop' > > + nsenter --net=/proc/$gw1_pid/ns/net nft add rule ip ovn-test INPUT > ip daddr $ip_gw1 ip saddr $ip_gw2 udp dport 6081 '@th,416,16 == 0x0ec8 > @th,472,8 == 0x80 counter drop' > > + nsenter --net=/proc/$gw1_pid/ns/net nft add rule ip ovn-test INPUT > ip daddr $ip_gw1 ip saddr $ip_gw2 udp dport 6081 '@th,416,16 == 0x0ec8 > @th,472,8 == 0x40 counter drop' > > + > > + check_loss_after_flap "gw1" $max_expected_max_expected_loss1 > > + > > + # gw1 still alive and gw2 tried to claim => gw1 should restart > generating garps. > > + check_garps "true" "false" "false" > > + check_packets "true" "false" "false" "true" > > + > > + echo "$(date +%H:%M:%S.%03N) Unblocking bfd on gw1" > > + nsenter --net=/proc/$gw1_pid/ns/net nft -a list ruleset > > + nsenter --net=/proc/$gw1_pid/ns/net nft delete table ip ovn-test > > > > # The network is now restored => packets should go through gw1 and > reach chassis-1. > > - check_for_new_echo_pkts gw1 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "true" > > - check_for_new_echo_pkts gw2 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts gw3 00:00:c0:a8:00:01 f0:00:c0:a8:00:fe > "false" > > - check_for_new_echo_pkts ch1 f0:00:c0:a8:01:fe f0:00:c0:a8:01:01 > "true" > > - AS_BOX([$(date +%H:%M:%S.%03N) Statistics after network restored]) > > - dump_statistics > > - stop_sending_background_packets > > + check_packets "true" "false" "false" "true" > > + final_check "bfd_stop" $lost $max_expected_max_expected_loss2 > > +} > > + > > +check_migration_between_gw1_and_gw2_kill_gw2() { > > + AS_BOX([$(date +%H:%M:%S.%03N) Check migration after killing gw2 > ovn-controller & vswitchd]) > > + max_expected_loss1=$1 > > + max_expected_loss2=$2 > > + prepare > > + > > + on_exit 'm_as ovn-gw-2 /usr/share/openvswitch/scripts/ovs-ctl > status || > > + m_as ovn-gw-2 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-2' > > + on_exit 'm_as ovn-gw-2 /usr/share/ovn/scripts/ovn-ctl > status_controller || > > + m_as ovn-gw-2 /usr/share/ovn/scripts/ovn-ctl > start_controller ${CONTROLLER_SSL_ARGS}' > > + > > + m_as ovn-gw-2 kill -9 $(m_as ovn-gw-2 cat > /run/ovn/ovn-controller.pid) > > + m_as ovn-gw-2 kill -9 $(m_as ovn-gw-2 cat > /run/openvswitch/ovs-vswitchd.pid) > > + m_as ovn-gw-2 kill -9 $(m_as ovn-gw-2 cat > /run/openvswitch/ovsdb-server.pid) > > + m_as ovn-gw-2 ovs-dpctl del-dp system@ovs-system > > + > > + check_loss_after_flap "gw2" $max_expected_loss1 > > + > > + # gw1 still alive, but gw2 did not try to claim => gw1 should not > generate new garps. > > + check_garps "false" "false" "false" > > + check_packets "true" "fals" "false" "true" > > + > > + echo "$(date +%H:%M:%S.%03N) Restarting gw2 ovn-vswitchd]" > > + m_as ovn-gw-2 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-2 > > + > > + echo "$(date +%H:%M:%S.%03N) Restarting gw2 ovn-controller" > > + m_as ovn-gw-2 /usr/share/ovn/scripts/ovn-ctl start_controller > ${CONTROLLER_SSL_ARGS} > > + > > + # The network is now restored => packets should go through gw1 and > reach chassis-1. > > + check_packets "true" "false" "false" "true" > > + final_check "kill_gw2" $lost $max_expected_loss2 > > +} > > + > > +check_migration_between_gw1_and_gw2_update_ovs() { > > + AS_BOX([$(date +%H:%M:%S.%03N) Check migration after restarting gw1 > ovs-vswitchd ("update")]) > > + max_expected_loss1=$1 > > + max_expected_loss2=$2 > > + prepare > > + > > + m_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl restart > --system-id=ovn-gw-1 > > + > > + check_loss_after_flap "gw1" $max_expected_loss1 > > + > > + # The network is now restored => packets should go through gw1 and > reach chassis-1. > > + check_packets "true" "false" "false" "true" > > + final_check "ovs_update" $lost $max_expected_loss2 > > +} > > + > > +check_migration_between_gw1_and_gw2_kill_gw1() { > > + AS_BOX([$(date +%H:%M:%S.%03N) Killing gw1 ovn-controller and > ovs-vswitchd]) > > + max_expected_loss1=$1 > > + max_expected_loss2=$2 > > + prepare > > + > > + on_exit 'm_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl > status || > > + m_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-1' > > + on_exit 'm_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl > status_controller || > > + m_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl > start_controller ${CONTROLLER_SSL_ARGS}' > > + > > + m_as ovn-gw-1 kill -9 $(m_as ovn-gw-1 cat > /run/ovn/ovn-controller.pid) > > + m_as ovn-gw-1 kill -9 $(m_as ovn-gw-1 cat > /run/openvswitch/ovs-vswitchd.pid) > > + m_as ovn-gw-1 kill -9 $(m_as ovn-gw-1 cat > /run/openvswitch/ovsdb-server.pid) > > + # Also delete datapath (flows) > > + m_as ovn-gw-1 ovs-dpctl del-dp system@ovs-system > > + > > + check_loss_after_flap "gw1" $max_expected_loss1 > > + > > + # gw1 died => gw2 should generate garps. > > + check_garps "false" "true" "false" > > + check_packets "false" "true" "false" "true" > > + echo "$(date +%H:%M:%S.%03N) Restarting gw1 ovn-vswitchd after > killing gw1" > > + m_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-1 > > + > > + # Wait some long time before restarting ovn-controller > > + sleep 10 > > + > > + # gw2 should still be handling packets as OVN not restarted on gw1 > > + check_packets "false" "true" "false" "true" > > + > > + echo "$(date +%H:%M:%S.%03N) Restarting gw1 ovn-controller after > killing gw1" > > + m_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl start_controller > ${CONTROLLER_SSL_ARGS} > > + > > + # The network is now restored => packets should go through gw1 and > reach chassis-1. > > + check_packets "true" "false" "false" "true" > > + final_check "kill_gw1" $lost $max_expected_loss2 > > +} > > + > > +check_migration_between_gw1_and_gw2_reboot_gw1() { > > + ip_gw1_eth1=$(podman exec ovn-gw-1 ip -brief address show eth1 | > awk '{print $3}' | cut -d/ -f1) > > + cidr=$(podman exec ovn-gw-1 ip -brief address show eth1 | awk > '{print $3}' | cut -d/ -f2) > > + AS_BOX([$(date +%H:%M:%S.%03N) Rebooting ovn-gw-1 with > $ip_gw1_eth1/$cidr]) > > + max_expected_loss1=$1 > > + max_expected_loss2=$2 > > + prepare > > + > > + podman stop -t 0 ovn-gw-1 > > + (exec 3>&- 4>&- 5>&- 6>&-; podman start ovn-gw-1) > > + > > + # As ovn-gw-1 got stopped and restarted, its ports (added by fake > > + # multinode) got deleted. Add them back. > > + add_port br-ovn eth1 $ip_gw1_eth1/$cidr > > + add_port br-ovn-ext eth2 > > + M_START_TCPDUMPS([ovn-gw-1], [-neei eth2], [gw1], [ovn-gw-1], > [-neei eth1], [gw1_eth1], [ovn-gw-1], [-neei eth2 -Q out], [gw1_out]) > > + check_loss_after_flap "gw1" $max_expected_loss1 > > + > > + # gw1 died => gw2 should generate garps. > > + check_garps "false" "true" "false" > > + check_packets "false" "true" "false" "true" > > + > > + echo "$(date +%H:%M:%S.%03N) Restarting gw1 ovn-vswitchd after > rebooting gw1" > > + m_as ovn-gw-1 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-gw-1 > > + > > + # Wait some long time before restarting ovn-controller > > + sleep 10 > > + > > + # gw2 should still be handling packets as OVN not restarted on gw1 > > + check_packets "false" "true" "false" "true" > > + > > + echo "$(date +%H:%M:%S.%03N) Restarting gw1 ovn-controller after > rebooting gw1" > > + m_as ovn-gw-1 /usr/share/ovn/scripts/ovn-ctl start_controller > ${CONTROLLER_SSL_ARGS} > > + > > + # The network is now restored => packets should go through gw1 and > reach chassis-1. > > + check_packets "true" "false" "false" "true" > > + final_check "kill_gw1" $lost $max_expected_loss2 > > +} > > + > > +check_compute_restart() { > > + AS_BOX([$(date +%H:%M:%S.%03N) Killing ovn-chassis-1 ovn-controller > and ovs-vswitchd]) > > + max_expected_loss=$1 > > + prepare > > + > > + # Kill ovn-chassis-1 > > + echo "$(date +%H:%M:%S.%03N) Killing chassis-1" > > + on_exit 'm_as ovn-chassis-1 /usr/share/openvswitch/scripts/ovs-ctl > status || > > + m_as ovn-chassis-1 /usr/share/openvswitch/scripts/ovs-ctl > start --system-id=ovn-chassis-1' > > + on_exit 'm_as ovn-chassis-1 /usr/share/ovn/scripts/ovn-ctl > status_controller || > > + m_as ovn-chassis-1 /usr/share/ovn/scripts/ovn-ctl > start_controller ${CONTROLLER_SSL_ARGS}' > > + > > + m_as ovn-chassis-1 kill -9 $(m_as ovn-chassis-1 cat > /run/ovn/ovn-controller.pid) > > + m_as ovn-chassis-1 kill -9 $(m_as ovn-chassis-1 cat > /run/openvswitch/ovs-vswitchd.pid) > > + m_as ovn-chassis-1 kill -9 $(m_as ovn-chassis-1 cat > /run/openvswitch/ovsdb-server.pid) > > + > > + # Now restart chassis-1 > > + flap_count=$(m_as ovn-gw-2 ovs-vsctl get interfac $from_gw2_to_ch1 > bfd_status | sed 's/.*flap_count=\"\([[0-9]]*\).*/\1/g') > > + echo "$(date +%H:%M:%S.%03N) Restarting ovn-chassis-1 ovn-vswitchd." > > + m_as ovn-chassis-1 /usr/share/openvswitch/scripts/ovs-ctl start > --system-id=ovn-chassis-1 > > + > > + echo "$(date +%H:%M:%S.%03N) Waiting for flap count between gw-1 > and chassis-1 to increase" > > + OVS_WAIT_UNTIL([ > > + new_flap_count=$(m_as ovn-gw-1 ovs-vsctl get interfac > $from_gw1_to_ch1 bfd_status | sed 's/.*flap_count=\"\([[0-9]]*\).*/\1/g') > > + echo "Comparing $new_flap_count versus $flap_count" > > + test "$new_flap_count" -gt "$((flap_count))" > > + ]) > > + > > + wait_bfd_up ovn-chassis-1 $from_ch1_to_gw1 > > + > > + echo "$(date +%H:%M:%S.%03N) Restarting ovn-chassis-1 > ovn-controller." > > + m_as ovn-chassis-1 /usr/share/ovn/scripts/ovn-ctl start_controller > ${CONTROLLER_SSL_ARGS} > > + > > + # Wait a long time to catch losses > > + sleep 5 > > + final_check "compute" 0 $max_expected_loss > > } > > > > start_tcpdump > > -AS_BOX([$(date +%H:%M:%S.%03N) Sending packet from hv1-vif1(inside1) to > ext1]) > > +echo "$(date +%H:%M:%S.%03N) Sending packet from hv1-vif1(inside1) to > ext1" > > M_NS_CHECK_EXEC([ovn-chassis-1], [hv1-vif1], [ping -c3 -q -i 0.1 > 192.168.0.1 | FORMAT_PING], > > [0], [dnl > > 3 packets transmitted, 3 received, 0% packet loss, time 0ms > > @@ -3433,7 +3631,7 @@ M_NS_CHECK_EXEC([ovn-chassis-1], [hv1-vif1], [ping > -c3 -q -i 0.1 192.168.0.1 | F > > stop_tcpdump > > > > # It should have gone through gw1 and not gw2 > > -AS_BOX([$(date +%H:%M:%S.%03N) Checking it went through gw1 and not > gw2]) > > +echo "$(date +%H:%M:%S.%03N) Checking it went through gw1 and not gw2" > > AT_CHECK([cat gw2.tcpdump | grep "ICMP echo"], [1], [dnl > > ]) > > > > @@ -3446,17 +3644,29 @@ f0:00:c0:a8:00:fe > 00:00:c0:a8:00:01, ethertype > IPv4 (0x0800), length 98: 192.1 > > 00:00:c0:a8:00:01 > f0:00:c0:a8:00:fe, ethertype IPv4 (0x0800), length > 98: 192.168.0.1 > 192.168.1.1: ICMP echo reply, > > ]) > > > > -# We stop bfd between gw1 & gw2, but keep gw1 & gw2 running. > > -check_migration_between_gw1_and_gw2 "stop_bfd" > > +# We stop bfd between gw1 & gw2, but keep gw1 & gw2 running. We should > not lose packets. > > +check_migration_between_gw1_and_gw2_bfd_stop 1 1 > > > > # We simulate death of gw2. It should not have any effect. > > -check_migration_between_gw1_and_gw2 "kill_gw2" > > +check_migration_between_gw1_and_gw2_kill_gw2 1 1 > > + > > +# We simulate ovs update on gw1. When ovs is stopped, flows should > still be handled by Kernel datapath. > > +# When OVS is restarted, BFD should go down immediately, and gw2 will > start handling packets. > > +# There will be packet losses as gw2 will usually see BFD from gw1 up > (and hence relase port) before gw1 sees > > +# BFD up (and claim port). > > +check_migration_between_gw1_and_gw2_update_ovs 20 1 > > + > > +# We simulate restart of both OVS & OVN gw1. gw2 should take over. > > +check_migration_between_gw1_and_gw2_kill_gw1 40 20 > > > > # We simulate death of gw1. gw2 should take over. > > -check_migration_between_gw1_and_gw2 "kill_gw1" > > +check_migration_between_gw1_and_gw2_reboot_gw1 40 20 > > + > > +# We simulate restart of ovn-chassis-1. We expect for ~4 sec losses as > we wait for bfd up before starting > > +# ovn-controller (1 sec to restart ovs, 2 sec for bfd to go up, 1 sec > to detect it). > > +check_compute_restart 40 > > > > AT_CLEANUP > > -]) > > > > AT_SETUP([ovn multinode bgp L2 EVPN]) > > check_fake_multinode_setup > > Regards, > Dumitru > Thanks Xavier _______________________________________________ dev mailing list [email protected] https://mail.openvswitch.org/mailman/listinfo/ovs-dev
