Skip to content

Fixed database status in multi-region mode when primary DC fails #12071

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fixed database status in multi-region mode when primary DC fails #12071

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
24 changes: 18 additions & 6 deletions fdbcli/StatusCommand.actor.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -694,11 +694,9 @@ void printStatus(StatusObjectReader statusObj,

if (dataLoss == -1) {
ASSERT_WE_THINK(availLoss == -1);
outputString += format(
"\n\n Warning: the database may have data loss and availability loss. Please restart "
"following tlog interfaces, otherwise storage servers may never be able to catch "
"up.\n");
StatusObjectReader logs;
std::string epochData;
int32_t minFaultTolerance = 0;
if (statusObjCluster.has("logs")) {
for (StatusObjectReader logEpoch : statusObjCluster.last().get_array()) {
bool possiblyLosingData;
Expand All @@ -709,10 +707,13 @@ void printStatus(StatusObjectReader statusObj,
// Current epoch doesn't have an end version.
int64_t epoch, beginVersion, endVersion = invalidVersion;
bool current;
int32_t faultTolerance;
logEpoch.get("epoch", epoch);
logEpoch.get("begin_version", beginVersion);
logEpoch.get("end_version", endVersion);
logEpoch.get("current", current);
logEpoch.get("remote_log_fault_tolerance", faultTolerance);
minFaultTolerance = std::min(minFaultTolerance, faultTolerance);
std::string missing_log_interfaces;
if (logEpoch.has("log_interfaces")) {
for (StatusObjectReader logInterface : logEpoch.last().get_array()) {
Expand All @@ -721,11 +722,14 @@ void printStatus(StatusObjectReader statusObj,
if (logInterface.get("healthy", healthy) && !healthy) {
logInterface.get("id", id);
logInterface.get("address", address);
missing_log_interfaces += format("%s,%s ", id.c_str(), address.c_str());
missing_log_interfaces +=
format("%s,%s ",
id.c_str(),
address.empty() ? "unknown" : address.c_str());
}
}
}
outputString += format(
epochData += format(
" %s log epoch: %lld begin: %lld end: %s, missing "
"log interfaces(id,address): %s\n",
current ? "Current" : "Old",
Expand All @@ -735,6 +739,14 @@ void printStatus(StatusObjectReader statusObj,
missing_log_interfaces.c_str());
}
}
outputString += format("\n\n ");
if (minFaultTolerance < 0) {
outputString += format("Warning: the database may have data loss and availability loss. ");
}
outputString += format(
"Please restart "
"following tlog interfaces, otherwise storage servers may never be able to catch "
"up.\n") + epochData;
}
}
}
Expand Down