[teamd]: Clean teamd process if LAG creation fails #2888
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -307,6 +307,8 @@ void TeamMgr::doLagTask(Consumer &consumer) | |
| { | ||
| if (addLag(alias, min_links, fallback, fast_rate) == task_need_retry) | ||
| { | ||
| // If LAG creation fails, we need to clean up any potentially orphaned teamd processes | ||
| removeLag(alias); | ||
| it++; | ||
| continue; | ||
| } | ||
|
|
@@ -654,10 +656,46 @@ bool TeamMgr::removeLag(const string &alias) | |
|
|
||
| stringstream cmd; | ||
| string res; | ||
| pid_t pid; | ||
|
|
||
| cmd << TEAMD_CMD << " -k -t " << shellquote(alias); | ||
| EXEC_WITH_ERROR_THROW(cmd.str(), res); | ||
|
|
||
| try | ||
| { | ||
| std::stringstream cmd; | ||
| cmd << "cat " << shellquote("/var/run/teamd/" + alias + ".pid"); | ||
| EXEC_WITH_ERROR_THROW(cmd.str(), res); | ||
| } | ||
| catch (const std::exception &e) | ||
| { | ||
| SWSS_LOG_NOTICE("Failed to remove non-existent port channel %s pid...", alias.c_str()); | ||
| return false; | ||
| } | ||
|
Comment on lines
+661
to
+671
There was a problem hiding this comment. Thinking about this a bit more, IMO this is internal implementation details of There was a problem hiding this comment. Teammgrd already reads this file in There was a problem hiding this comment.
|
||
|
|
||
| try | ||
| { | ||
| pid = static_cast<pid_t>(std::stoul(res, nullptr, 10)); | ||
| SWSS_LOG_INFO("Read port channel %s pid %d", alias.c_str(), pid); | ||
| } | ||
| catch (const std::exception &e) | ||
| { | ||
| SWSS_LOG_ERROR("Failed to read port channel %s pid: %s", alias.c_str(), e.what()); | ||
| return false; | ||
| } | ||
|
|
||
| try | ||
| { | ||
| std::stringstream cmd; | ||
| cmd << "kill -TERM " << pid; | ||
| EXEC_WITH_ERROR_THROW(cmd.str(), res); | ||
| } | ||
| catch (const std::exception &e) | ||
| { | ||
| SWSS_LOG_ERROR("Failed to send SIGTERM to port channel %s pid %d: %s", alias.c_str(), pid, e.what()); | ||
| return false; | ||
| } | ||
|
|
||
|
There was a problem hiding this comment. Do we need to do this? It should be part of the There was a problem hiding this comment. Yes, since |
||
| SWSS_LOG_NOTICE("Stop port channel %s", alias.c_str()); | ||
|
|
||
| return true; | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,74 @@ | ||
| #include "gtest/gtest.h" | ||
| #include "../mock_table.h" | ||
| #include "teammgr.h" | ||
|
|
||
| extern int (*callback)(const std::string &cmd, std::string &stdout); | ||
| extern std::vector<std::string> mockCallArgs; | ||
|
|
||
| int cb(const std::string &cmd, std::string &stdout) | ||
| { | ||
| mockCallArgs.push_back(cmd); | ||
| if (cmd.find("/usr/bin/teamd -r -t PortChannel1") != std::string::npos) | ||
| { | ||
| return 1; | ||
| } | ||
| else if (cmd.find("cat /var/run/teamd/PortChannel1.pid") != std::string::npos) | ||
| { | ||
| stdout = "1234"; | ||
| return 0; | ||
| } | ||
| return 0; | ||
| } | ||
|
|
||
| namespace teammgr_ut | ||
| { | ||
| struct TeamMgrTest : public ::testing::Test | ||
| { | ||
| std::shared_ptr<swss::DBConnector> m_config_db; | ||
| std::shared_ptr<swss::DBConnector> m_app_db; | ||
| std::shared_ptr<swss::DBConnector> m_state_db; | ||
| std::vector<TableConnector> cfg_lag_tables; | ||
|
|
||
| virtual void SetUp() override | ||
| { | ||
| testing_db::reset(); | ||
| m_config_db = std::make_shared<swss::DBConnector>("CONFIG_DB", 0); | ||
| m_app_db = std::make_shared<swss::DBConnector>("APPL_DB", 0); | ||
| m_state_db = std::make_shared<swss::DBConnector>("STATE_DB", 0); | ||
|
|
||
| m_config_db.get()->hset("DEVICE_METADATA|localhost", "mac", "01:23:45:67:89:ab"); | ||
|
|
||
| TableConnector conf_lag_table(m_config_db.get(), CFG_LAG_TABLE_NAME); | ||
| TableConnector conf_lag_member_table(m_config_db.get(), CFG_LAG_MEMBER_TABLE_NAME); | ||
| TableConnector state_port_table(m_state_db.get(), STATE_PORT_TABLE_NAME); | ||
|
|
||
| std::vector<TableConnector> tables = { | ||
| conf_lag_table, | ||
| conf_lag_member_table, | ||
| state_port_table | ||
| }; | ||
|
|
||
| cfg_lag_tables = tables; | ||
| mockCallArgs.clear(); | ||
| callback = cb; | ||
| } | ||
| }; | ||
|
|
||
| TEST_F(TeamMgrTest, testProcessKilledAfterAddLagFailure) | ||
| { | ||
| swss::TeamMgr teammgr(m_config_db.get(), m_app_db.get(), m_state_db.get(), cfg_lag_tables); | ||
| swss::Table cfg_lag_table = swss::Table(m_config_db.get(), CFG_LAG_TABLE_NAME); | ||
| cfg_lag_table.set("PortChannel1", { { "admin_status", "up" }, | ||
| { "mtu", "9100" }, | ||
| { "lacp_key", "auto" }, | ||
| { "min_links", "2" } }); | ||
| teammgr.addExistingData(&cfg_lag_table); | ||
| int kill_cmd_called = 0; | ||
| for (auto cmd : mockCallArgs){ | ||
| if (cmd.find("kill -TERM 1234") != std::string::npos){ | ||
| kill_cmd_called++; | ||
| } | ||
| } | ||
| ASSERT_EQ(kill_cmd_called, 1); | ||
| } | ||
| } |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This could be causing issues. IIUC if the process actually wasn't running, then
teamd -k -t PortChannel.1would fail. So in the case whereaddLag()fails, but noteamd ...running, thenteamd -k -t PortChannel.would fail, as a result an exception will be thrown, could you check?