Skip to content

Fix Orchagent crashes from port down cnt conversion out of range. #3889

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

Merged
merged 6 commits into from
Oct 2, 2025
+43 −43
Merged

Fix Orchagent crashes from port down cnt conversion out of range. #3889

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
908cfa0
Fix Orchagent crashes from port down cnt conversion out of range.
jfeng-arista Sep 17, 2025
63fbedc
Merge branch 'master' into master-port-down-cnt-conversion-fix
jfeng-arista Sep 23, 2025
f3cffaa
Merge branch 'master' into master-port-down-cnt-conversion-fix
jfeng-arista Sep 24, 2025
3bb9ed4
Merge branch 'master' into master-port-down-cnt-conversion-fix
jfeng-arista Sep 25, 2025
ba99d4e
Merge branch 'master' into master-port-down-cnt-conversion-fix
jfeng-arista Sep 29, 2025
608821f
Merge branch 'master' into master-port-down-cnt-conversion-fix
jfeng-arista Oct 1, 2025
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
84 changes: 42 additions & 42 deletions orchagent/fabricportsorch.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -426,12 +426,12 @@ void FabricPortsOrch::updateFabricDebugCounters()
}
now = time_now.tv_sec;

int fecIsolatedPolls = FEC_ISOLATE_POLLS; // monPollThreshIsolation
int fecUnisolatePolls = FEC_UNISOLATE_POLLS; // monPollThreshRecovery
int isolationPollsCfg = ISOLATION_POLLS_CFG; // monPollThreshIsolation
int recoveryPollsCfg = RECOVERY_POLLS_CFG; // monPollThreshRecovery
int errorRateCrcCellsCfg = ERROR_RATE_CRC_CELLS_CFG; // monErrThreshCrcCells
int errorRateRxCellsCfg = ERROR_RATE_RX_CELLS_CFG; // monErrThreshRxCells
uint64_t fecIsolatedPolls = FEC_ISOLATE_POLLS; // monPollThreshIsolation
uint64_t fecUnisolatePolls = FEC_UNISOLATE_POLLS; // monPollThreshRecovery
uint64_t isolationPollsCfg = ISOLATION_POLLS_CFG; // monPollThreshIsolation
uint64_t recoveryPollsCfg = RECOVERY_POLLS_CFG; // monPollThreshRecovery
uint64_t errorRateCrcCellsCfg = ERROR_RATE_CRC_CELLS_CFG; // monErrThreshCrcCells
uint64_t errorRateRxCellsCfg = ERROR_RATE_RX_CELLS_CFG; // monErrThreshRxCells
string applConstKey = FABRIC_MONITOR_DATA;
std::vector<FieldValueTuple> constValues;
SWSS_LOG_INFO("updateFabricDebugCounters");
Expand Down Expand Up @@ -547,13 +547,13 @@ void FabricPortsOrch::updateFabricDebugCounters()
//
// cfgIsolated CONFIG_ISOLATED

int consecutivePollsWithErrors = 0;
int consecutivePollsWithNoErrors = 0;
int consecutivePollsWithFecErrs = 0;
int consecutivePollsWithNoFecErrs = 0;
uint64_t consecutivePollsWithErrors = 0;
uint64_t consecutivePollsWithNoErrors = 0;
uint64_t consecutivePollsWithFecErrs = 0;
uint64_t consecutivePollsWithNoFecErrs = 0;

int skipCrcErrorsOnLinkupCount = 0;
int skipFecErrorsOnLinkupCount = 0;
uint64_t skipCrcErrorsOnLinkupCount = 0;
uint64_t skipFecErrorsOnLinkupCount = 0;
uint64_t prevRxCells = 0;
uint64_t prevCrcErrors = 0;
uint64_t prevCodeErrors = 0;
Expand All @@ -569,8 +569,8 @@ void FabricPortsOrch::updateFabricDebugCounters()

// link status
string lnkStatus = "down";
int lnkDownCnt = 0;
int preLnkDwnCnt = 0;
uint64_t lnkDownCnt = 0;
uint64_t preLnkDwnCnt = 0;

// for testing
string testState = "product";
Expand Down Expand Up @@ -624,57 +624,57 @@ void FabricPortsOrch::updateFabricDebugCounters()
}
if (fvField(val) == "PORT_DOWN_COUNT")
{
lnkDownCnt = to_uint<uint8_t>(valuePt);
lnkDownCnt = std::stoull(valuePt);
continue;
}
if (fvField(val) == "PORT_DOWN_COUNT_handled")
{
preLnkDwnCnt = to_uint<uint8_t>(valuePt);
preLnkDwnCnt = std::stoull(valuePt);
continue;
}
if (fvField(val) == "POLL_WITH_ERRORS")
{
consecutivePollsWithErrors = to_uint<uint8_t>(valuePt);
consecutivePollsWithErrors = std::stoull(valuePt);
continue;
}
if (fvField(val) == "POLL_WITH_NO_ERRORS")
{
consecutivePollsWithNoErrors = to_uint<uint8_t>(valuePt);
consecutivePollsWithNoErrors = std::stoull(valuePt);
continue;
}
if (fvField(val) == "POLL_WITH_FEC_ERRORS")
{
consecutivePollsWithFecErrs = to_uint<uint8_t>(valuePt);
consecutivePollsWithFecErrs = std::stoull(valuePt);
continue;
}
if (fvField(val) == "POLL_WITH_NOFEC_ERRORS")
{
consecutivePollsWithNoFecErrs = to_uint<uint8_t>(valuePt);
consecutivePollsWithNoFecErrs = std::stoull(valuePt);
continue;
}
if (fvField(val) == "SKIP_CRC_ERR_ON_LNKUP_CNT")
{
skipCrcErrorsOnLinkupCount = to_uint<uint8_t>(valuePt);
skipCrcErrorsOnLinkupCount = std::stoull(valuePt);
continue;
}
if (fvField(val) == "SKIP_FEC_ERR_ON_LNKUP_CNT")
{
skipFecErrorsOnLinkupCount = to_uint<uint8_t>(valuePt);
skipFecErrorsOnLinkupCount = std::stoull(valuePt);
continue;
}
if (fvField(val) == "RX_CELLS")
{
prevRxCells = to_uint<uint64_t>(valuePt);
prevRxCells = std::stoull(valuePt);
continue;
}
if (fvField(val) == "CRC_ERRORS")
{
prevCrcErrors = to_uint<uint64_t>(valuePt);
prevCrcErrors = std::stoull(valuePt);
continue;
}
if (fvField(val) == "CODE_ERRORS")
{
prevCodeErrors = to_uint<uint64_t>(valuePt);
prevCodeErrors = std::stoull(valuePt);
continue;
}
if (fvField(val) == "AUTO_ISOLATED")
Expand All @@ -691,12 +691,12 @@ void FabricPortsOrch::updateFabricDebugCounters()
}
if (fvField(val) == "TEST_CRC_ERRORS")
{
testCrcErrors = to_uint<uint64_t>(valuePt);
testCrcErrors = std::stoull(valuePt);
continue;
}
if (fvField(val) == "TEST_CODE_ERRORS")
{
testCodeErrors = to_uint<uint64_t>(valuePt);
testCodeErrors = std::stoull(valuePt);
continue;
}
if (fvField(val) == "TEST")
Expand All @@ -721,7 +721,7 @@ void FabricPortsOrch::updateFabricDebugCounters()
// if MANUAL_ISOLATED:
// autoIsolated = 0
//
SWSS_LOG_INFO("Port %d lnk down cnt %d handled: %d", lane, lnkDownCnt, preLnkDwnCnt);
SWSS_LOG_INFO("Port %d lnk down cnt %lld handled: %lld", lane, (long long)lnkDownCnt, (long long)preLnkDwnCnt);
if (lnkDownCnt != preLnkDwnCnt)
{

Expand All @@ -744,7 +744,7 @@ void FabricPortsOrch::updateFabricDebugCounters()
// Now should be the event monitoring on an up link

// checking crc errors
int maxSkipCrcCnt = MAX_SKIP_CRCERR_ON_LNKUP_POLLS;
uint64_t maxSkipCrcCnt = MAX_SKIP_CRCERR_ON_LNKUP_POLLS;
if (testState == "TEST"){
maxSkipCrcCnt = 2;
}
Expand Down Expand Up @@ -790,12 +790,12 @@ void FabricPortsOrch::updateFabricDebugCounters()
}
}
SWSS_LOG_INFO("port %s diffCrcCells %lld", key.c_str(), (long long)diffCrcCells);
SWSS_LOG_INFO("consecutivePollsWithCRCErrs %d consecutivePollsWithNoCRCErrs %d",
consecutivePollsWithErrors, consecutivePollsWithNoErrors);
SWSS_LOG_INFO("consecutivePollsWithCRCErrs %lld consecutivePollsWithNoCRCErrs %lld",
(long long)consecutivePollsWithErrors, (long long)consecutivePollsWithNoErrors);
}

// checking FEC errors
int maxSkipFecCnt = MAX_SKIP_FECERR_ON_LNKUP_POLLS;
uint64_t maxSkipFecCnt = MAX_SKIP_FECERR_ON_LNKUP_POLLS;
if (testState == "TEST"){
maxSkipFecCnt = 2;
}
Expand Down Expand Up @@ -837,9 +837,9 @@ void FabricPortsOrch::updateFabricDebugCounters()
consecutivePollsWithFecErrs = 0;
}
}
SWSS_LOG_INFO("consecutivePollsWithFecErrs %d consecutivePollsWithNoFecErrs %d",
consecutivePollsWithFecErrs,consecutivePollsWithNoFecErrs);
SWSS_LOG_INFO("fecUnisolatePolls %d", fecUnisolatePolls);
SWSS_LOG_INFO("consecutivePollsWithFecErrs %lld consecutivePollsWithNoFecErrs %lld",
(long long)consecutivePollsWithFecErrs, (long long)consecutivePollsWithNoFecErrs);
SWSS_LOG_INFO("fecUnisolatePolls %lld", (long long)fecUnisolatePolls);
}

// take care serdes link shut state setting
Expand All @@ -848,10 +848,10 @@ void FabricPortsOrch::updateFabricDebugCounters()
// debug information
SWSS_LOG_INFO("port %s status up autoIsolated %d",
key.c_str(), autoIsolated);
SWSS_LOG_INFO("consecutivePollsWithErrors %d consecutivePollsWithFecErrs %d",
consecutivePollsWithErrors, consecutivePollsWithFecErrs);
SWSS_LOG_INFO("consecutivePollsWithNoErrors %d consecutivePollsWithNoFecErrs %d",
consecutivePollsWithNoErrors, consecutivePollsWithNoFecErrs);
SWSS_LOG_INFO("consecutivePollsWithErrors %lld consecutivePollsWithFecErrs %lld",
(long long)consecutivePollsWithErrors, (long long)consecutivePollsWithFecErrs);
SWSS_LOG_INFO("consecutivePollsWithNoErrors %lld consecutivePollsWithNoFecErrs %lld",
(long long)consecutivePollsWithNoErrors, (long long)consecutivePollsWithNoFecErrs);
if (autoIsolated == 0 && (consecutivePollsWithErrors >= isolationPollsCfg
|| consecutivePollsWithFecErrs >= fecIsolatedPolls))
{
Expand Down Expand Up @@ -941,7 +941,7 @@ void FabricPortsOrch::updateStateDbTable(
const std::unique_ptr<Table>& stateTable,
const std::string& key,
const std::string& field,
int value)
uint64_t value)
{
// Convert the integer value to a string
std::string valueStr = std::to_string(value);
Expand All @@ -950,8 +950,8 @@ void FabricPortsOrch::updateStateDbTable(
stateTable->hset(key, field, valueStr.c_str());

// Log the update
SWSS_LOG_INFO("%s updates %s to %s %d",
key.c_str(), field.c_str(), valueStr.c_str(), value);
SWSS_LOG_INFO("%s updates %s to %s %lld",
key.c_str(), field.c_str(), valueStr.c_str(), (long long)value);
}

// Isolate/Unisolate a fabric link
Expand Down
2 changes: 1 addition & 1 deletion orchagent/fabricportsorch.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ class FabricPortsOrch : public Orch, public Subject
const unique_ptr<Table>& stateTable,
const string& key,
const string& field,
int value);
uint64_t value);
void isolateFabricLink(int lane, bool isolate);

void doTask() override;
Expand Down
Loading