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.
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
Retry disconnects and expired sessions when reading system.zookeeper #59388
Merged
Merged
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
023b8cb
Retry disconnects and expired sessions
davenger 82c06ca
Use ZooKeeperRetriesControl
davenger c348c4e
Move ZooKeeperRetries.h to Common
davenger 5947e5b
Use retry settings and fault injection
davenger 7c1e318
Test retries
davenger 6e82dc8
Use fixed seed in test
davenger File filter
Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
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 |
---|---|---|
|
@@ -424,9 +424,35 @@ void ReadFromSystemZooKeeper::applyFilters() | |
paths = extractPath(getFilterNodes().nodes, context, context->getSettingsRef().allow_unrestricted_reads_from_keeper); | ||
} | ||
|
||
/// Executes a request to Keeper and retries it in case of expired sessions and disconnects | ||
template <typename Result, typename Operation> | ||
static Result runWithReconnects(Operation && operation, ContextPtr context, QueryStatusPtr query_status) | ||
{ | ||
constexpr int max_retries = 20; /// Limit retries by some reasonable number to avoid infinite loops | ||
for (int attempt = 0; ; ++attempt) | ||
{ | ||
if (query_status) | ||
query_status->checkTimeLimit(); | ||
|
||
zkutil::ZooKeeperPtr keeper = context->getZooKeeper(); | ||
|
||
try | ||
{ | ||
return operation(keeper); | ||
} | ||
catch (const Coordination::Exception & e) | ||
{ | ||
if (!Coordination::isHardwareError(e.code) || | ||
attempt >= max_retries || | ||
e.code == Coordination::Error::ZOPERATIONTIMEOUT) | ||
throw; | ||
} | ||
} | ||
} | ||
|
||
void ReadFromSystemZooKeeper::fillData(MutableColumns & res_columns) | ||
{ | ||
zkutil::ZooKeeperPtr zookeeper = context->getZooKeeper(); | ||
QueryStatusPtr query_status = context->getProcessListElement(); | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Let's use the whole pack:
|
||
|
||
if (paths.empty()) | ||
throw Exception(ErrorCodes::BAD_ARGUMENTS, | ||
|
@@ -448,6 +474,9 @@ void ReadFromSystemZooKeeper::fillData(MutableColumns & res_columns) | |
std::unordered_set<String> added; | ||
while (!paths.empty()) | ||
{ | ||
if (query_status) | ||
query_status->checkTimeLimit(); | ||
|
||
list_tasks.clear(); | ||
std::vector<String> paths_to_list; | ||
while (!paths.empty() && static_cast<Int64>(list_tasks.size()) < max_inflight_requests) | ||
|
@@ -470,7 +499,9 @@ void ReadFromSystemZooKeeper::fillData(MutableColumns & res_columns) | |
paths_to_list.emplace_back(task.path_corrected); | ||
list_tasks.emplace_back(std::move(task)); | ||
} | ||
auto list_responses = zookeeper->tryGetChildren(paths_to_list); | ||
auto list_responses = runWithReconnects<zkutil::ZooKeeper::MultiTryGetChildrenResponse>( | ||
[&paths_to_list](zkutil::ZooKeeperPtr zookeeper) { return zookeeper->tryGetChildren(paths_to_list); }, | ||
context, query_status); | ||
|
||
struct GetTask | ||
{ | ||
|
@@ -514,7 +545,9 @@ void ReadFromSystemZooKeeper::fillData(MutableColumns & res_columns) | |
} | ||
} | ||
|
||
auto get_responses = zookeeper->tryGet(paths_to_get); | ||
auto get_responses = runWithReconnects<zkutil::ZooKeeper::MultiTryGetResponse>( | ||
[&paths_to_get](zkutil::ZooKeeperPtr zookeeper) { return zookeeper->tryGet(paths_to_get); }, | ||
context, query_status); | ||
|
||
for (size_t i = 0, size = get_tasks.size(); i < size; ++i) | ||
{ | ||
|
Oops, something went wrong.
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.
Why isn't this using
ZooKeeperRetriesControl
? It's better to adapt that if we need to rather than re-implement retriesThere 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.
Ok
Do you think we should move ZooKeeperRetriesControl from Storages/MergeTree to Common?
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.
Absolutely. Ideally we should be using
ZooKeeperRetriesControl
+ZooKeeperWithFaultInjectionPtr
everywhere so we handle both injections and retries.