This is an automated email from the ASF dual-hosted git repository.
yiguolei pushed a commit to branch branch-2.1
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/branch-2.1 by this push:
new 79f6b647d57 [FIX] should check fe host standing when coordinator is
not found. (#37772)
79f6b647d57 is described below
commit 79f6b647d575744af2649c147457d9ad86d1f28b
Author: zhiqiang <seuhezhiqi...@163.com>
AuthorDate: Mon Jul 15 12:27:31 2024 +0800
[FIX] should check fe host standing when coordinator is not found. (#37772)
fix https://github.com/apache/doris/pull/37707
---
be/src/runtime/fragment_mgr.cpp | 68 ++++++++++++++++++++---------------------
1 file changed, 33 insertions(+), 35 deletions(-)
diff --git a/be/src/runtime/fragment_mgr.cpp b/be/src/runtime/fragment_mgr.cpp
index c2f16e1d05a..6846782dd8e 100644
--- a/be/src/runtime/fragment_mgr.cpp
+++ b/be/src/runtime/fragment_mgr.cpp
@@ -1178,46 +1178,44 @@ void FragmentMgr::cancel_worker() {
auto itr = running_fes.find(query_context->coord_addr);
if (itr != running_fes.end()) {
- if (query_context->get_fe_process_uuid() ==
itr->second.info.process_uuid ||
+ if (q.second->get_fe_process_uuid() ==
itr->second.info.process_uuid ||
itr->second.info.process_uuid == 0) {
continue;
} else {
- // In some rear cases, the rpc port of follower is
not updated in time,
- // then the port of this follower will be zero,
but acutally it is still running,
- // and be has already received the query from
follower.
- // So we need to check if host is in running_fes.
- bool fe_host_is_standing = std::any_of(
- running_fes.begin(), running_fes.end(),
- [query_context](const auto& fe) {
- return fe.first.hostname ==
-
query_context->coord_addr.hostname &&
- fe.first.port == 0;
- });
- if (fe_host_is_standing) {
- LOG_WARNING(
- "Coordinator {}:{} is not found, but
its host is still "
- "running with an unstable brpc port,
not going to cancel "
- "it.",
- query_context->coord_addr.hostname,
- query_context->coord_addr.port,
- print_id(query_context->query_id()));
- continue;
- } else {
- LOG_WARNING(
- "Could not find target coordinator
{}:{} of query {}, "
- "going to "
- "cancel it.",
- query_context->coord_addr.hostname,
- query_context->coord_addr.port,
- print_id(query_context->query_id()));
- }
+ LOG_WARNING("Coordinator of query {} restarted,
going to cancel it.",
+ print_id(q.second->query_id()));
}
} else {
- LOG_WARNING(
- "Could not find target coordinator {}:{} of
query {}, going to "
- "cancel it.",
- query_context->coord_addr.hostname,
query_context->coord_addr.port,
- print_id(query_context->query_id()));
+ // In some rear cases, the rpc port of follower is not
updated in time,
+ // then the port of this follower will be zero, but
acutally it is still running,
+ // and be has already received the query from follower.
+ // So we need to check if host is in running_fes.
+ bool fe_host_is_standing =
+ std::any_of(running_fes.begin(),
running_fes.end(),
+ [query_context](const auto& fe) {
+ return fe.first.hostname ==
+
query_context->coord_addr.hostname &&
+ fe.first.port == 0;
+ });
+
+ if (fe_host_is_standing) {
+ LOG_WARNING(
+ "Coordinator {}:{} is not found, but its
host is still "
+ "running with an unstable rpc port, not
going to cancel "
+ "it.",
+ query_context->coord_addr.hostname,
+ query_context->coord_addr.port,
+ print_id(query_context->query_id()));
+ continue;
+ } else {
+ LOG_WARNING(
+ "Could not find target coordinator {}:{}
of query {}, "
+ "going to "
+ "cancel it.",
+ query_context->coord_addr.hostname,
+ query_context->coord_addr.port,
+ print_id(query_context->query_id()));
+ }
}
// Coorninator of this query has already dead.
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
