clickhouse-native 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d3e2cb4cbe829d9afd7e30e0ac29ea828020896c93634852b4baef007348d3b0
-  data.tar.gz: e5f13079f4de6e64e545f49736a8da6832de954dfe82f1a4d105dd1228680887
+  metadata.gz: 984a63d34de19388f777cfe71ecd0a844d22f0b67b89e9fddfe07c5c0ac1cc05
+  data.tar.gz: 78f829e40f715aef0264e1419cb9b06b97faab1ac38f33329c5da6ada1dd251b
 SHA512:
-  metadata.gz: 9998240b8ca84a4d28ad1fb956c0bf92e1893d4a9ce024fa443eefaa01efb35b657b55d8c2ce92718fd9224a5167fe0201a955f7147ab7499560a331906e2567
-  data.tar.gz: d097a39e1fa03b051a30fe1fb273a928b7e2e555e05945d32b22a9dd9dc1deaf280193b80ecae146d7d442d513bbfb6e638ba4b63589f5a58171ce4b25ba5b87
+  metadata.gz: c579da78d2185108712c92e902217c2e508655533c2e78efc7e36ae358a826f809f41d884684b8fcb0e1b36749bc80be5f23b76c85ebf081423adb615d73928b
+  data.tar.gz: 93259646a6f150ed271202e3eaca075e0d1cf8d707aed5ac2ac9b530061de47cf1a65082289718857b367dd5b8d764c73cf270c34d080018ce8caac540d8bab6

data/ext/clickhouse_native/client.cpp

@@ -17,11 +17,13 @@
 #include <clickhouse/exceptions.h>
 #include <clickhouse/types/types.h>
 
+#include <chrono>
 #include <cstdint>
 #include <exception>
 #include <memory>
 #include <string>
 #include <system_error>
+#include <utility>
 #include <vector>
 
 using namespace clickhouse;
@@ -666,6 +668,11 @@ static void append_value(const ColumnRef& col, VALUE value) {
 
 struct CHClient {
     std::unique_ptr<Client> client;
+    // Session settings applied to *every* query as per-query settings, rather
+    // than a one-time session `SET`. Per-query settings ride each query packet,
+    // so they survive a transparent ping_before_query reconnect (a fresh socket
+    // would otherwise lose a session-level SET and fall back to server defaults).
+    std::vector<std::pair<std::string, std::string>> default_settings;
 };
 
 static void ch_client_free(void* p) {
@@ -707,6 +714,18 @@ static uint16_t kwarg_uint16(VALUE kwargs, const char* key, uint16_t fallback) {
     return static_cast<uint16_t>(NUM2UINT(v));
 }
 
+static bool kwarg_bool(VALUE kwargs, const char* key, bool fallback) {
+    VALUE v = rb_hash_lookup2(kwargs, ID2SYM(rb_intern(key)), Qundef);
+    if (v == Qundef) return fallback;
+    return RTEST(v);
+}
+
+static unsigned int kwarg_uint(VALUE kwargs, const char* key, unsigned int fallback) {
+    VALUE v = rb_hash_lookup2(kwargs, ID2SYM(rb_intern(key)), Qundef);
+    if (v == Qundef || NIL_P(v)) return fallback;
+    return NUM2UINT(v);
+}
+
 static CompressionMethod kwarg_compression(VALUE kwargs) {
     VALUE v = rb_hash_lookup2(kwargs, ID2SYM(rb_intern("compression")), Qundef);
     if (v == Qundef || NIL_P(v)) return CompressionMethod::None;
@@ -742,6 +761,16 @@ static int apply_settings_cb(VALUE key, VALUE val, VALUE arg) {
     return ST_CONTINUE;
 }
 
+// Collect a `settings:` Hash into a client's default_settings vector at
+// construction. Values are stringified the same way per-query settings are.
+static int collect_setting_cb(VALUE key, VALUE val, VALUE arg) {
+    auto* vec = reinterpret_cast<std::vector<std::pair<std::string, std::string>>*>(arg);
+    VALUE k = SYMBOL_P(key) ? rb_sym2str(key) : key;
+    StringValue(k);
+    vec->emplace_back(std::string(RSTRING_PTR(k), RSTRING_LEN(k)), stringify_setting_value(val));
+    return ST_CONTINUE;
+}
+
 // Read a `settings:` Hash out of the parsed kwargs and stamp each entry
 // onto `q` as a per-query setting. No-op if kwargs is nil or settings is
 // missing/empty. Raises TypeError if settings is not a Hash.
@@ -765,6 +794,16 @@ static void apply_read_settings(Query& q, VALUE kwargs) {
     apply_settings(q, kwargs);
 }
 
+// Stamp the client's construction-time `settings:` onto `q`. Marked important
+// (flag 1) so an unknown setting name errors — matching the old session `SET`,
+// which failed loudly instead of silently ignoring a typo'd setting. Applied
+// before per-call settings so an explicit `settings:` on the call still wins.
+static void apply_default_settings(Query& q, CHClient* c) {
+    for (const auto& kv : c->default_settings) {
+        q.SetSetting(kv.first, QuerySettingsField{kv.second, 1});
+    }
+}
+
 // Client.new(host:, port:, database:, user:, password:)
 static VALUE ch_client_initialize(int argc, VALUE* argv, VALUE self) {
     VALUE kwargs = Qnil;
@@ -778,12 +817,35 @@ static VALUE ch_client_initialize(int argc, VALUE* argv, VALUE self) {
     std::string password = kwarg_str(kwargs, "password", "");
     CompressionMethod compression = kwarg_compression(kwargs);
 
+    // Connection-resilience defaults. Long-lived pooled connections get
+    // silently closed by the server (idle_connection_timeout) or an LB, so
+    // the next use of a checked-out client would otherwise hit recv()==0 and
+    // raise ConnectionError("closed: ..."). ping_before_query makes the driver
+    // ping first and transparently reconnect on a dead socket; tcp_keepalive
+    // keeps idle sockets healthy at the OS level. retry_timeout is the backoff
+    // before each reconnect attempt — kept low (1s) since a pooled reconnect
+    // to a live server should be quick and we don't want to stall queries.
+    bool ping_before_query = kwarg_bool(kwargs, "ping_before_query", true);
+    bool tcp_keepalive = kwarg_bool(kwargs, "tcp_keepalive", true);
+    unsigned int retry_timeout = kwarg_uint(kwargs, "retry_timeout", 1);
+
     CHClient* c = as_client(self);
+
+    VALUE settings = rb_hash_lookup2(kwargs, ID2SYM(rb_intern("settings")), Qnil);
+    if (!NIL_P(settings)) {
+        Check_Type(settings, T_HASH);
+        rb_hash_foreach(settings, collect_setting_cb,
+                        reinterpret_cast<VALUE>(&c->default_settings));
+    }
+
     try {
         ClientOptions opts;
         opts.SetHost(host).SetPort(port)
             .SetDefaultDatabase(database).SetUser(user).SetPassword(password)
-            .SetCompressionMethod(compression);
+            .SetCompressionMethod(compression)
+            .SetPingBeforeQuery(ping_before_query)
+            .TcpKeepAlive(tcp_keepalive)
+            .SetRetryTimeout(std::chrono::seconds(retry_timeout));
         c->client = std::make_unique<Client>(opts);
     } catch (const std::exception& e) {
         raise_mapped_ex(e);
@@ -792,6 +854,9 @@ static VALUE ch_client_initialize(int argc, VALUE* argv, VALUE self) {
     rb_ivar_set(self, rb_intern("@host"), rb_utf8_str_new(host.data(), host.size()));
     rb_ivar_set(self, rb_intern("@port"), UINT2NUM(port));
     rb_ivar_set(self, rb_intern("@database"), rb_utf8_str_new(database.data(), database.size()));
+    rb_ivar_set(self, rb_intern("@ping_before_query"), ping_before_query ? Qtrue : Qfalse);
+    rb_ivar_set(self, rb_intern("@tcp_keepalive"), tcp_keepalive ? Qtrue : Qfalse);
+    rb_ivar_set(self, rb_intern("@retry_timeout"), UINT2NUM(retry_timeout));
 
     VALUE logger = rb_hash_lookup2(kwargs, ID2SYM(rb_intern("logger")), Qnil);
     rb_ivar_set(self, rb_intern("@logger"), logger);
@@ -835,6 +900,7 @@ static VALUE ch_client_execute(int argc, VALUE* argv, VALUE self) {
     if (!c->client) rb_raise(err_connection, "clickhouse-native: client is closed");
 
     Query q(std::string(RSTRING_PTR(rb_sql), RSTRING_LEN(rb_sql)));
+    apply_default_settings(q, c);
     apply_settings(q, kwargs);
 
     ExecuteNoGVL args{c->client.get(), &q, nullptr};
@@ -866,6 +932,7 @@ static VALUE ch_client_query(int argc, VALUE* argv, VALUE self) {
     try {
         std::vector<ID> col_ids;
         Query q(std::string(RSTRING_PTR(rb_sql), RSTRING_LEN(rb_sql)));
+        apply_default_settings(q, c);
         apply_read_settings(q, kwargs);
         q.OnData([&](const Block& block) {
             size_t ncols = block.GetColumnCount();
@@ -911,6 +978,7 @@ static VALUE ch_client_query_value(int argc, VALUE* argv, VALUE self) {
         VALUE out = Qnil;
         bool seen = false;
         Query q(std::string(RSTRING_PTR(rb_sql), RSTRING_LEN(rb_sql)));
+        apply_default_settings(q, c);
         apply_read_settings(q, kwargs);
         q.OnData([&](const Block& block) {
             if (seen) return;
@@ -936,6 +1004,7 @@ struct InsertNoGVL {
     Client* client;
     const std::string* table;
     const Block* block;
+    const std::vector<std::pair<std::string, std::string>>* settings;
     std::exception_ptr err;
 };
 }  // namespace
@@ -943,7 +1012,7 @@ struct InsertNoGVL {
 static void* insert_no_gvl(void* data) {
     auto* a = static_cast<InsertNoGVL*>(data);
     try {
-        a->client->Insert(*a->table, *a->block);
+        a->client->Insert(*a->table, *a->block, *a->settings);
     } catch (...) {
         a->err = std::current_exception();
     }
@@ -1009,7 +1078,7 @@ static VALUE ch_client_insert_block(VALUE self, VALUE rb_table, VALUE rb_columns
             block.AppendColumn(names[i], cols[i]);
         }
 
-        InsertNoGVL args{c->client.get(), &table, &block, nullptr};
+        InsertNoGVL args{c->client.get(), &table, &block, &c->default_settings, nullptr};
         rb_thread_call_without_gvl(insert_no_gvl, &args, insert_unblock, &args);
         if (args.err) {
             try { c->client->ResetConnection(); } catch (...) {}
@@ -1110,6 +1179,7 @@ static VALUE ch_client_query_each(int argc, VALUE* argv, VALUE self) {
 
     QueryEachState state{rb_block_proc(), {}, 0, false};
     Query q(std::string(RSTRING_PTR(rb_sql), RSTRING_LEN(rb_sql)));
+    apply_default_settings(q, c);
     apply_read_settings(q, kwargs);
     q.OnDataCancelable([&state](const Block& block) -> bool {
         if (state.aborted) return false;

data/ext/clickhouse_native/patches/0002-carry-settings-into-insert.patch

@@ -0,0 +1,82 @@
+diff --git a/clickhouse/client.cpp b/clickhouse/client.cpp
+index 34a733d..c9732f4 100644
+--- a/clickhouse/client.cpp
++++ b/clickhouse/client.cpp
+@@ -211,7 +211,8 @@ public:
+ 
+     bool IsSelecting() const { return state_ == State::Selecting; }
+ 
+-    void Insert(const std::string& table_name, const std::string& query_id, const Block& block);
++    void Insert(const std::string& table_name, const std::string& query_id, const Block& block,
++                const std::vector<std::pair<std::string, std::string>>& settings = {});
+ 
+     Block BeginInsert(Query query);
+ 
+@@ -485,7 +486,8 @@ std::string NameToQueryString(const std::string &input)
+     return output;
+ }
+ 
+-void Client::Impl::Insert(const std::string& table_name, const std::string& query_id, const Block& block) {
++void Client::Impl::Insert(const std::string& table_name, const std::string& query_id, const Block& block,
++                          const std::vector<std::pair<std::string, std::string>>& settings) {
+     if (state_ == State::Inserting) {
+         throw ValidationError("cannot execute query while inserting, use SendInsertData instead");
+     }
+@@ -511,6 +513,9 @@ void Client::Impl::Insert(const std::string& table_name, const std::string& quer
+     }
+ 
+     Query query("INSERT INTO " + table_name + " ( " + fields_section.str() + " ) VALUES", query_id);
++    for (const auto& kv : settings) {
++        query.SetSetting(kv.first, QuerySettingsField{kv.second, 1});
++    }
+     SendQuery(query);
+ 
+     // Wait for a data packet and return
+@@ -1365,12 +1370,14 @@ bool Client::IsSelecting() const
+     return impl_->IsSelecting();
+ }
+ 
+-void Client::Insert(const std::string& table_name, const Block& block) {
+-    impl_->Insert(table_name, Query::default_query_id, block);
++void Client::Insert(const std::string& table_name, const Block& block,
++                    const std::vector<std::pair<std::string, std::string>>& settings) {
++    impl_->Insert(table_name, Query::default_query_id, block, settings);
+ }
+ 
+-void Client::Insert(const std::string& table_name, const std::string& query_id, const Block& block) {
+-    impl_->Insert(table_name, query_id, block);
++void Client::Insert(const std::string& table_name, const std::string& query_id, const Block& block,
++                    const std::vector<std::pair<std::string, std::string>>& settings) {
++    impl_->Insert(table_name, query_id, block, settings);
+ }
+ 
+ Block Client::BeginInsert(const std::string& query) {
+diff --git a/clickhouse/client.h b/clickhouse/client.h
+index a55fd74..6c6ff53 100644
+--- a/clickhouse/client.h
++++ b/clickhouse/client.h
+@@ -23,6 +23,8 @@
+ #include "columns/bool.h"
+ 
+ #include <chrono>
++#include <utility>
++#include <vector>
+ #include <cstdint>
+ #include <memory>
+ #include <ostream>
+@@ -298,8 +300,13 @@ public:
+     bool IsSelecting() const;
+ 
+     /// Intends for insert block of data into a table \p table_name.
+-    void Insert(const std::string& table_name, const Block& block);
+-    void Insert(const std::string& table_name, const std::string& query_id, const Block& block);
++    /// \p settings are applied to the generated INSERT query as per-query
++    /// settings (patched-in for clickhouse-native: lets a pooled client carry
++    /// its session settings into inserts without a session-level SET).
++    void Insert(const std::string& table_name, const Block& block,
++                const std::vector<std::pair<std::string, std::string>>& settings = {});
++    void Insert(const std::string& table_name, const std::string& query_id, const Block& block,
++                const std::vector<std::pair<std::string, std::string>>& settings = {});
+ 
+     /// Start an \p INSERT statement, insert batches of data, then finish the insert.
+     Block BeginInsert(const std::string& query);

data/lib/clickhouse_native/client.rb

@@ -2,7 +2,7 @@
 
 module ClickhouseNative
   class Client
-    attr_reader :host, :port, :database
+    attr_reader :host, :port, :database, :ping_before_query, :tcp_keepalive, :retry_timeout
 
     def describe_table(table, db_name: nil)
       fq = db_name ? "#{db_name}.#{table}" : table

data/lib/clickhouse_native/pool.rb

@@ -8,16 +8,17 @@ module ClickhouseNative
 
     def initialize(host:, port:, database: "default", user: "default", password: "",
                    compression: :none, logger: nil, settings: {},
-                   pool_size: 5, pool_timeout: 5)
+                   pool_size: 5, pool_timeout: 5,
+                   ping_before_query: true, tcp_keepalive: true, retry_timeout: 1)
       @host = host
       @port = port
       @database = database
-      client_kwargs = { host:, port:, database:, user:, password:, compression:, logger: }
-      @set_sql = settings_sql(settings)
+      client_kwargs = {
+        host:, port:, database:, user:, password:, compression:, logger:, settings:,
+        ping_before_query:, tcp_keepalive:, retry_timeout:
+      }
       @pool = ConnectionPool.new(size: pool_size, timeout: pool_timeout) do
-        client = Client.new(**client_kwargs)
-        client.execute(@set_sql) if @set_sql
-        client
+        Client.new(**client_kwargs)
       end
     end
 
@@ -25,18 +26,24 @@ module ClickhouseNative
     # path leaves the socket in an unknown state. The C++ binding issues
     # ResetConnection, but a subsequent send can still surface buffered
     # protocol errors from the prior aborted operation — those get
-    # attributed to whatever SQL we tried next (e.g. the SET reapplying
-    # session settings), producing misleading log lines and re-raises in
-    # unrelated code. A fresh socket + handshake is cheap relative to
-    # debugging that.
+    # attributed to whatever SQL we tried next, producing misleading log
+    # lines and re-raises in unrelated code. A fresh socket + handshake is
+    # cheap relative to debugging that.
     #
     # ConnectionError gets one automatic retry: pooled connections that
     # have been idle long enough for the server / an LB to FIN them
-    # surface as "closed" on the very next recv (errno 0, message
-    # "closed: Success"). Discarding and re-checking out lands a fresh
-    # socket and the operation succeeds. The retry only triggers when
-    # the dead-connection error fired before any data was sent, so
-    # write operations don't risk double-execution from this path.
+    # surface as "closed" on the very next recv (errno is whatever stale
+    # value was left in the thread — "closed: Success", "closed: Operation
+    # now in progress", etc. all mean the same recv()==0). Discarding and
+    # re-checking out lands a fresh socket and the operation succeeds. The
+    # retry only triggers when the dead-connection error fired before any
+    # data was sent, so write operations don't risk double-execution.
+    #
+    # This is the backstop: with ping_before_query on (the default) the
+    # driver already pings and transparently reconnects a dead socket
+    # before running the query, so most stale connections never surface as
+    # a ConnectionError here at all. This retry still covers the residual
+    # race (socket dies between the ping and the query).
     def with
       attempts = 0
       begin
@@ -84,21 +91,5 @@ module ClickhouseNative
     def describe_table(table, db_name: nil)
       with { |c| c.describe_table(table, db_name:) }
     end
-
-    private
-
-    # Render a `SET key1 = val1, key2 = val2` statement once at pool setup
-    # so every checked-out connection starts with the same session
-    # settings. Matches how the HTTP driver injected global_params per
-    # request. Values: Integer / Float render bare; anything else is
-    # quoted as a SQL string literal.
-    def settings_sql(settings)
-      return nil if settings.nil? || settings.empty?
-      parts = settings.map do |k, v|
-        literal = v.is_a?(Numeric) ? v.to_s : "'#{v.to_s.gsub("'", "''")}'"
-        "#{k} = #{literal}"
-      end
-      "SET #{parts.join(', ')}"
-    end
   end
 end

data/lib/clickhouse_native/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ClickhouseNative
-  VERSION = "0.10.0"
+  VERSION = "0.11.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: clickhouse-native
 version: !ruby/object:Gem::Version
-  version: 0.10.0
+  version: 0.11.0
 platform: ruby
 authors:
 - Yuri Smirnov
@@ -35,6 +35,7 @@ files:
 - ext/clickhouse_native/client.cpp
 - ext/clickhouse_native/extconf.rb
 - ext/clickhouse_native/patches/0001-preserve-declared-column-type.patch
+- ext/clickhouse_native/patches/0002-carry-settings-into-insert.patch
 - ext/clickhouse_native/vendor/clickhouse-cpp/.clang-format
 - ext/clickhouse_native/vendor/clickhouse-cpp/.git
 - ext/clickhouse_native/vendor/clickhouse-cpp/.gitattributes
@@ -323,7 +324,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.10
+rubygems_version: 4.0.16
 specification_version: 4
 summary: ClickHouse Ruby driver over the native TCP protocol
 test_files: []