Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add port flap count and last flap timestamp to APPL_DB #3052

Merged
merged 6 commits into from
Mar 12, 2024
Merged

Add port flap count and last flap timestamp to APPL_DB #3052

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
edd4ed7
Add port flap count and last flap timestamp
prgeor Mar 2, 2024
b51da11
Address comments
prgeor Mar 4, 2024
d303988
Fix dvs test failure
prgeor Mar 6, 2024
28687eb
Address review comments
prgeor Mar 6, 2024
8ccf70d
Address review comment
prgeor Mar 11, 2024
da88994
Merge branch 'master' into portflap
dgsudharsan Mar 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions orchagent/port.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,7 @@ class Port
uint32_t m_nat_zone_id = 0;
uint32_t m_vnid = VNID_NONE;
uint32_t m_fdb_count = 0;
uint64_t m_flap_count = 0;
uint32_t m_up_member_count = 0;
uint32_t m_maximum_headroom = 0;
std::set<uint32_t> m_adv_speeds;
Expand Down
48 changes: 46 additions & 2 deletions orchagent/portsorch.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3107,6 +3107,30 @@ bool PortsOrch::removeVlanHostIntf(Port vl)
return true;
}

void PortsOrch::updateDbPortFlapCount(Port& port, sai_port_oper_status_t pstatus)
{
SWSS_LOG_ENTER();

++port.m_flap_count;
prgeor marked this conversation as resolved.
Show resolved Hide resolved
vector<FieldValueTuple> tuples;
FieldValueTuple tuple("flap_count", std::to_string(port.m_flap_count));
tuples.push_back(tuple);

auto now = std::chrono::system_clock::now();
std::time_t now_c = std::chrono::system_clock::to_time_t(now);
if (pstatus == SAI_PORT_OPER_STATUS_DOWN)
{
FieldValueTuple tuple("last_down_time", std::ctime(&now_c));
tuples.push_back(tuple);
}
else if (pstatus == SAI_PORT_OPER_STATUS_UP)
{
FieldValueTuple tuple("last_up_time", std::ctime(&now_c));
tuples.push_back(tuple);
}
m_portTable->set(port.m_alias, tuples);
}

void PortsOrch::updateDbPortOperStatus(const Port& port, sai_port_oper_status_t status) const
{
SWSS_LOG_ENTER();
Expand Down Expand Up @@ -5315,7 +5339,7 @@ bool PortsOrch::initializePort(Port &port)
/* Check warm start states */
vector<FieldValueTuple> tuples;
bool exist = m_portTable->get(port.m_alias, tuples);
string operStatus;
string operStatus, flapCount = "0";
if (exist)
{
for (auto i : tuples)
Expand All @@ -5324,9 +5348,14 @@ bool PortsOrch::initializePort(Port &port)
{
operStatus = fvValue(i);
}

if (fvField(i) == "flap_count")
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this to handle reconciliation during warm/fast reboot?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@dgsudharsan yes

{
flapCount = fvValue(i);
}
}
}
SWSS_LOG_DEBUG("initializePort %s with oper %s", port.m_alias.c_str(), operStatus.c_str());
SWSS_LOG_INFO("Port %s with oper %s flap_count=%s", port.m_alias.c_str(), operStatus.c_str(), flapCount.c_str());

/**
* Create database port oper status as DOWN if attr missing
Expand All @@ -5347,6 +5376,20 @@ bool PortsOrch::initializePort(Port &port)
port.m_oper_status = SAI_PORT_OPER_STATUS_DOWN;
}

// initalize port flap count
if (!flapCount.empty())
{
try
{
port.m_flap_count = stoull(flapCount);
m_portTable->hset(port.m_alias, "flap_count", flapCount);
}
catch (const std::exception &e)
{
SWSS_LOG_ERROR("Failed to get port (%s) flap_count: %s", port.m_alias.c_str(), e.what());
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is going to throw an unwanted error during WB from old versions which doesn't have this field in DB. Please change to DEBUG as this is not a real error scenario

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@prsunny if the value is not there in the DB, flapCount default value = "0" (see line 5317 above)

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@prgeor if we hit the exception, is it ok to still put the value to the DB?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@nazariig fixed

}
}

/* initialize port admin status */
if (!getPortAdminStatus(port.m_port_id, port.m_admin_state_up))
{
Expand Down Expand Up @@ -7580,6 +7623,7 @@ void PortsOrch::updatePortOperStatus(Port &port, sai_port_oper_status_t status)
if (port.m_type == Port::PHY)
{
updateDbPortOperStatus(port, status);
updateDbPortFlapCount(port, status);
updateGearboxPortOperStatus(port);

/* Refresh the port states and reschedule the poller tasks */
Expand Down
1 change: 1 addition & 0 deletions orchagent/portsorch.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,6 +147,7 @@ class PortsOrch : public Orch, public Subject

bool setHostIntfsOperStatus(const Port& port, bool up) const;
void updateDbPortOperStatus(const Port& port, sai_port_oper_status_t status) const;
void updateDbPortFlapCount(Port& port, sai_port_oper_status_t pstatus);

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@prgeor please remove extra line

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@nazariig removed

bool createVlanHostIntf(Port& vl, string hostif_name);
bool removeVlanHostIntf(Port vl);
Expand Down
68 changes: 68 additions & 0 deletions tests/mock_tests/portsorch_ut.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -499,6 +499,73 @@ namespace portsorch_test
}

};

/*
* Test port flap count
*/
TEST_F(PortsOrchTest, PortFlapCount)
{
Table portTable = Table(m_app_db.get(), APP_PORT_TABLE_NAME);

// Get SAI default ports to populate DB
auto ports = ut_helper::getInitialSaiPorts();

// Populate port table with SAI ports
for (const auto &it : ports)
{
portTable.set(it.first, it.second);
}

// Set PortConfigDone, PortInitDone
portTable.set("PortConfigDone", { { "count", to_string(ports.size()) } });
portTable.set("PortInitDone", { { "lanes", "0" } });

// refill consumer
gPortsOrch->addExistingData(&portTable);
// Apply configuration : create ports
static_cast<Orch *>(gPortsOrch)->doTask();

// Get first port, expect the oper status is not UP
Port port;
gPortsOrch->getPort("Ethernet0", port);
ASSERT_TRUE(port.m_oper_status != SAI_PORT_OPER_STATUS_UP);
ASSERT_TRUE(port.m_flap_count == 0);

auto exec = static_cast<Notifier *>(gPortsOrch->getExecutor("PORT_STATUS_NOTIFICATIONS"));
auto consumer = exec->getNotificationConsumer();

// mock a redis reply for notification, it notifies that Ehernet0 is going to up
for (uint32_t count=0; count < 5; count++) {
sai_port_oper_status_t oper_status = (count % 2 == 0) ? SAI_PORT_OPER_STATUS_UP : SAI_PORT_OPER_STATUS_DOWN;
mockReply = (redisReply *)calloc(sizeof(redisReply), 1);
mockReply->type = REDIS_REPLY_ARRAY;
mockReply->elements = 3; // REDIS_PUBLISH_MESSAGE_ELEMNTS
mockReply->element = (redisReply **)calloc(sizeof(redisReply *), mockReply->elements);
mockReply->element[2] = (redisReply *)calloc(sizeof(redisReply), 1);
mockReply->element[2]->type = REDIS_REPLY_STRING;
sai_port_oper_status_notification_t port_oper_status;
port_oper_status.port_state = oper_status;
port_oper_status.port_id = port.m_port_id;
std::string data = sai_serialize_port_oper_status_ntf(1, &port_oper_status);
std::vector<FieldValueTuple> notifyValues;
FieldValueTuple opdata("port_state_change", data);
notifyValues.push_back(opdata);
std::string msg = swss::JSon::buildJson(notifyValues);
mockReply->element[2]->str = (char*)calloc(1, msg.length() + 1);
memcpy(mockReply->element[2]->str, msg.c_str(), msg.length());

// trigger the notification
consumer->readData();
gPortsOrch->doTask(*consumer);
mockReply = nullptr;

gPortsOrch->getPort("Ethernet0", port);
ASSERT_TRUE(port.m_oper_status == oper_status);
ASSERT_TRUE(port.m_flap_count == count+1);
}

cleanupPorts(gPortsOrch);
}

TEST_F(PortsOrchTest, PortBulkCreateRemove)
{
Expand Down Expand Up @@ -1956,6 +2023,7 @@ namespace portsorch_test

gPortsOrch->getPort("Ethernet0", port);
ASSERT_TRUE(port.m_oper_status == SAI_PORT_OPER_STATUS_UP);
ASSERT_TRUE(port.m_flap_count == 1);

std::vector<FieldValueTuple> values;
portTable.get("Ethernet0", values);
Expand Down
2 changes: 1 addition & 1 deletion tests/test_warm_reboot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1090,7 +1090,7 @@ def test_swss_port_state_syncup(self, dvs, testlog):
orchStateCount += 1;

# Only WARM_RESTART_TABLE|orchagent state=reconciled operation may exist after port oper status change.
assert orchStateCount == 1
assert orchStateCount == 2

#clean up arp
dvs.runcmd("arp -d 10.0.0.1")
Expand Down
Loading