Release for azure-cosmos 4.30.1 and adding reason to rntbd channel health check failures

eng/jacoco-test-coverage/pom.xml

@@ -178,12 +178,12 @@
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos-encryption</artifactId>
-      <version>1.3.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos-encryption;current} -->
+      <version>1.2.1</version> <!-- {x-version-update;com.azure:azure-cosmos-encryption;current} -->
     </dependency>
     <dependency>
       <groupId>com.azure</groupId>

eng/versioning/version_client.txt

@@ -81,13 +81,13 @@ com.azure:azure-core-serializer-json-gson;1.1.15;1.2.0-beta.1
 com.azure:azure-core-serializer-json-jackson;1.2.16;1.3.0-beta.1
 com.azure:azure-core-test;1.8.0;1.9.0-beta.1
 com.azure:azure-core-tracing-opentelemetry;1.0.0-beta.23;1.0.0-beta.24
-com.azure:azure-cosmos;4.30.0;4.31.0-beta.1
+com.azure:azure-cosmos;4.30.0;4.30.1
 com.azure:azure-cosmos-benchmark;4.0.1-beta.1;4.0.1-beta.1
 com.azure:azure-cosmos-dotnet-benchmark;4.0.1-beta.1;4.0.1-beta.1
 com.azure.cosmos.spark:azure-cosmos-spark_3_2-12;1.0.0-beta.1;1.0.0-beta.1
-com.azure.cosmos.spark:azure-cosmos-spark_3-1_2-12;4.10.0;4.11.0-beta.1
-com.azure.cosmos.spark:azure-cosmos-spark_3-2_2-12;4.10.0;4.11.0-beta.1
-com.azure:azure-cosmos-encryption;1.2.0;1.3.0-beta.1
+com.azure.cosmos.spark:azure-cosmos-spark_3-1_2-12;4.10.0;4.10.1
+com.azure.cosmos.spark:azure-cosmos-spark_3-2_2-12;4.10.0;4.10.1
+com.azure:azure-cosmos-encryption;1.2.0;1.2.1
 com.azure:azure-data-appconfiguration;1.3.3;1.4.0-beta.1
 com.azure:azure-data-appconfiguration-perf;1.0.0-beta.1;1.0.0-beta.1
 com.azure:azure-data-schemaregistry;1.2.0;1.3.0-beta.1

sdk/cosmos/azure-cosmos-benchmark/pom.xml

@@ -51,13 +51,13 @@ Licensed under the MIT License.
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
 
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos-encryption</artifactId>
-      <version>1.3.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos-encryption;current} -->
+      <version>1.2.1</version> <!-- {x-version-update;com.azure:azure-cosmos-encryption;current} -->
     </dependency>
 
     <dependency>

sdk/cosmos/azure-cosmos-dotnet-benchmark/pom.xml

@@ -50,7 +50,7 @@ Licensed under the MIT License.
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
 
     <dependency>

sdk/cosmos/azure-cosmos-encryption/CHANGELOG.md

@@ -1,14 +1,8 @@
 ## Release History
 
-### 1.3.0-beta.1 (Unreleased)
-
-#### Features Added
-
-#### Breaking Changes
-
-#### Bugs Fixed
-
+### 1.2.1 (2022-06-01)
 #### Other Changes
+* Updated `azure-cosmos` to version `4.30.1`.
 
 ### 1.2.0 (2022-05-20)
 #### Other Changes

sdk/cosmos/azure-cosmos-encryption/README.md

@@ -12,7 +12,7 @@ The Azure Cosmos Encryption Plugin is used for encrypting data with a user-provi
 <dependency>
   <groupId>com.azure</groupId>
   <artifactId>azure-cosmos-encryption</artifactId>
-  <version>1.2.0</version>
+  <version>1.2.1</version>
 </dependency>
 ```
 [//]: # ({x-version-update-end})

sdk/cosmos/azure-cosmos-encryption/pom.xml

@@ -13,7 +13,7 @@ Licensed under the MIT License.
 
   <groupId>com.azure</groupId>
   <artifactId>azure-cosmos-encryption</artifactId>
-  <version>1.3.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos-encryption;current} -->
+  <version>1.2.1</version> <!-- {x-version-update;com.azure:azure-cosmos-encryption;current} -->
   <name>Encryption Plugin for Azure Cosmos DB SDK</name>
   <description>This Package contains Encryption Plugin for Microsoft Azure Cosmos SDK</description>
   <packaging>jar</packaging>
@@ -56,7 +56,7 @@ Licensed under the MIT License.
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
 
     <dependency>

sdk/cosmos/azure-cosmos-spark_3-1_2-12/CHANGELOG.md

@@ -1,19 +1,15 @@
 ## Release History
 
-### 4.11.0-beta.1 (Unreleased)
+### 4.10.1 (2022-06-01)
 
 #### Features Added
 * Added ability to disable endpoint rediscovery when using custom domain names in combination with private endpoints from a custom (on-premise) Spark environment (neither Databricks nor Synapse). - See [PR 29027](https://github.com/Azure/azure-sdk-for-java/pull/29027)
 * Added a config option `spark.cosmos.serialization.dateTimeConversionMode` to allow changing date/time conversion to fall back to converting `java.sql.Date` and `java.sql.Tiemstamp` into Epoch Milliseconds like in the Cosmos DB Connector for Spark 2.4 - See [PR 29081](https://github.com/Azure/azure-sdk-for-java/pull/29081)
 
-#### Breaking Changes
-
 #### Bugs Fixed
 * Fixed possible perf issue when Split results in 410 when trying to get latest LSN in Spark partitioner that could result in reprocessing change feed events (causing "hot partition2") - See [PR 29152](https://github.com/Azure/azure-sdk-for-java/pull/29152)
 * Fixed a bug resulting in ChangeFeed requests using the account's default consistency model instead of falling back to eventual if `spark.cosmos.read.forceEventualConsistency` is `true` (the default config). - See [PR 29152](https://github.com/Azure/azure-sdk-for-java/pull/29152)
 
-#### Other Changes
-
 ### 4.10.0 (2022-05-20)
 #### Features Added
 * Added the ability to change the target throughput control (`spark.cosmos.throughputControl.targetThroughputThreshold` or `spark.cosmos.throughputControl.targetThroughput`) when throughput control is enabled without having to also change the throughput control group name (`spark.cosmos.throughputControl.name`). - See [PR 28969](https://github.com/Azure/azure-sdk-for-java/pull/28969)

sdk/cosmos/azure-cosmos-spark_3-1_2-12/pom.xml

@@ -11,7 +11,7 @@
   </parent>
   <groupId>com.azure.cosmos.spark</groupId>
   <artifactId>azure-cosmos-spark_3-1_2-12</artifactId>
-  <version>4.11.0-beta.1</version> <!-- {x-version-update;com.azure.cosmos.spark:azure-cosmos-spark_3-1_2-12;current} -->
+  <version>4.10.1</version> <!-- {x-version-update;com.azure.cosmos.spark:azure-cosmos-spark_3-1_2-12;current} -->
   <packaging>jar</packaging>
   <url>https://github.com/Azure/azure-sdk-for-java/tree/main/sdk/cosmos/azure-cosmos-spark_3-1_2-12</url>
   <name>OLTP Spark 3.1 Connector for Azure Cosmos DB SQL API</name>
@@ -106,7 +106,7 @@
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
     <dependency>
       <groupId>com.fasterxml.jackson.core</groupId>

sdk/cosmos/azure-cosmos-spark_3-2_2-12/CHANGELOG.md

@@ -1,19 +1,15 @@
 ## Release History
 
-### 4.11.0-beta.1 (Unreleased)
+### 4.10.1 (2022-06-01)
 
 #### Features Added
 * Added ability to disable endpoint rediscovery when using custom domain names in combination with private endpoints from a custom (on-premise) Spark environment (neither Databricks nor Synapse). - See [PR 29027](https://github.com/Azure/azure-sdk-for-java/pull/29027)
 * Added a config option `spark.cosmos.serialization.dateTimeConversionMode` to allow changing date/time conversion to fall back to converting `java.sql.Date` and `java.sql.Tiemstamp` into Epoch Milliseconds like in the Cosmos DB Connector for Spark 2.4 - See [PR 29081](https://github.com/Azure/azure-sdk-for-java/pull/29081)
 
-#### Breaking Changes
-
 #### Bugs Fixed
 * Fixed possible perf issue when Split results in 410 when trying to get latest LSN in Spark partitioner that could result in reprocessing change feed events (causing "hot partition2") - See [PR 29152](https://github.com/Azure/azure-sdk-for-java/pull/29152)
 * Fixed a bug resulting in ChangeFeed requests using the account's default consistency model instead of falling back to eventual if `spark.cosmos.read.forceEventualConsistency` is `true` (the default config). - See [PR 29152](https://github.com/Azure/azure-sdk-for-java/pull/29152)
 
-#### Other Changes
-
 ### 4.10.0 (2022-05-20)
 #### Features Added
 * Added the ability to change the target throughput control (`spark.cosmos.throughputControl.targetThroughputThreshold` or `spark.cosmos.throughputControl.targetThroughput`) when throughput control is enabled without having to also change the throughput control group name (`spark.cosmos.throughputControl.name`). - See [PR 28969](https://github.com/Azure/azure-sdk-for-java/pull/28969)

sdk/cosmos/azure-cosmos-spark_3-2_2-12/pom.xml

@@ -11,7 +11,7 @@
   </parent>
   <groupId>com.azure.cosmos.spark</groupId>
   <artifactId>azure-cosmos-spark_3-2_2-12</artifactId>
-  <version>4.11.0-beta.1</version> <!-- {x-version-update;com.azure.cosmos.spark:azure-cosmos-spark_3-2_2-12;current} -->
+  <version>4.10.1</version> <!-- {x-version-update;com.azure.cosmos.spark:azure-cosmos-spark_3-2_2-12;current} -->
   <packaging>jar</packaging>
   <url>https://github.com/Azure/azure-sdk-for-java/tree/main/sdk/cosmos/azure-cosmos-spark_3-2_2-12</url>
   <name>OLTP Spark 3.2 Connector for Azure Cosmos DB SQL API</name>
@@ -108,7 +108,7 @@
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
     <dependency>
       <groupId>com.fasterxml.jackson.core</groupId>

sdk/cosmos/azure-cosmos-spark_3_2-12/pom.xml

@@ -63,7 +63,7 @@
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-cosmos</artifactId>
-      <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+      <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
     </dependency>
     <dependency>
       <groupId>org.scala-lang.modules</groupId>

sdk/cosmos/azure-cosmos/CHANGELOG.md

@@ -1,15 +1,11 @@
 ## Release History
 
-### 4.31.0-beta.1 (Unreleased)
-
-#### Features Added
-
-#### Breaking Changes
-
-#### Bugs Fixed
+### 4.30.1 (2022-06-01)
 
 #### Other Changes
-* Making CosmosPatchOperations thread-safe. Usually there is no reason to modify a CosmosPatchOperations instance concurrently form multiple threads - but making it thread-safe acts as protection in case this is done anyway - See [PR 29143](https://github.com/Azure/azure-sdk-for-java/pull/29143)
+* Made CosmosPatchOperations thread-safe. Usually there is no reason to modify a CosmosPatchOperations instance concurrently form multiple threads - but making it thread-safe acts as protection in case this is done anyway - See [PR 29143](https://github.com/Azure/azure-sdk-for-java/pull/29143)
+* Added system property to allow overriding proxy setting for client telemetry endpoint. - See [PR 29022](https://github.com/Azure/azure-sdk-for-java/pull/29022)
+* Added additional information about the reason on Rntbd channel health check failures. - See [PR 29022](https://github.com/Azure/azure-sdk-for-java/pull/29022)
 
 ### 4.30.0 (2022-05-20)
 #### Bugs Fixed

sdk/cosmos/azure-cosmos/README.md

@@ -45,7 +45,7 @@ add the direct dependency to your project as follows.
 <dependency>
   <groupId>com.azure</groupId>
   <artifactId>azure-cosmos</artifactId>
-  <version>4.30.0</version>
+  <version>4.30.1</version>
 </dependency>
 ```
 [//]: # ({x-version-update-end})

sdk/cosmos/azure-cosmos/pom.xml

@@ -13,7 +13,7 @@ Licensed under the MIT License.
 
   <groupId>com.azure</groupId>
   <artifactId>azure-cosmos</artifactId>
-  <version>4.31.0-beta.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
+  <version>4.30.1</version> <!-- {x-version-update;com.azure:azure-cosmos;current} -->
   <name>Microsoft Azure SDK for SQL API of Azure Cosmos DB Service</name>
   <description>This Package contains Microsoft Azure Cosmos SDK (with Reactive Extension Reactor support) for Azure Cosmos DB SQL API</description>
   <packaging>jar</packaging>

sdk/cosmos/azure-cosmos/src/main/java/com/azure/cosmos/implementation/directconnectivity/rntbd/RntbdClientChannelHealthChecker.java

@@ -12,6 +12,7 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import java.text.MessageFormat;
 import java.util.Optional;
 import java.util.concurrent.atomic.AtomicLongFieldUpdater;
 
@@ -126,7 +127,6 @@ public long writeDelayLimitInNanos() {
      * @return A future with a result of {@code true} if the channel is healthy, or {@code false} otherwise.
      */
     public Future<Boolean> isHealthy(final Channel channel) {
-
         checkNotNull(channel, "expected non-null channel");
 
         final RntbdRequestManager requestManager = channel.pipeline().get(RntbdRequestManager.class);
@@ -181,7 +181,7 @@ public Future<Boolean> isHealthy(final Channel channel) {
             final int pendingRequestCount = requestManager.pendingRequestCount();
 
             logger.warn("{} health check failed due to nonresponding read: {lastChannelWrite: {}, lastChannelRead: {}, "
-                + "readDelay: {}, readDelayLimit: {}, rntbdContext: {}, pendingRequestCount: {}}", channel,
+                    + "readDelay: {}, readDelayLimit: {}, rntbdContext: {}, pendingRequestCount: {}}", channel,
                 timestamps.lastChannelWriteNanoTime(), timestamps.lastChannelReadNanoTime(), readDelay,
                 this.readDelayLimitInNanos, rntbdContext, pendingRequestCount);
 
@@ -206,6 +206,122 @@ public Future<Boolean> isHealthy(final Channel channel) {
         return promise;
     }
 
+    /**
+     * Determines whether a specified channel is healthy.
+     *
+     * @param channel A channel whose health is to be checked.
+     * @return A future with a result of {@code true} if the channel is healthy, or {@code false} otherwise.
+     */
+    public Future<String> isHealthyWithFailureReason(final Channel channel) {
+
+        checkNotNull(channel, "expected non-null channel");
+
+        final RntbdRequestManager requestManager = channel.pipeline().get(RntbdRequestManager.class);
+        final Promise<String> promise = channel.eventLoop().newPromise();
+
+        if (requestManager == null) {
+            reportIssueUnless(logger, !channel.isActive(), channel, "active with no request manager");
+            return promise.setSuccess("active with no request manager");
+        }
+
+        final Timestamps timestamps = requestManager.snapshotTimestamps();
+        final long currentTime = System.nanoTime();
+
+        if (currentTime - timestamps.lastChannelReadNanoTime() < recentReadWindowInNanos) {
+            // because we recently received data
+            return promise.setSuccess(RntbdConstants.RntbdHealthCheckResults.SuccessValue);
+        }
+
+        // Black hole detection, part 1:
+        // Treat the channel as unhealthy if the gap between the last attempted write and the last successful write
+        // grew beyond acceptable limits, unless a write was attempted recently. This is a sign of a nonresponding write.
+
+        final long writeDelayInNanos =
+            timestamps.lastChannelWriteAttemptNanoTime() - timestamps.lastChannelWriteNanoTime();
+
+        final long writeHangDurationInNanos =
+            currentTime - timestamps.lastChannelWriteAttemptNanoTime();
+
+        if (writeDelayInNanos > this.writeDelayLimitInNanos && writeHangDurationInNanos > writeHangGracePeriodInNanos) {
+
+            final Optional<RntbdContext> rntbdContext = requestManager.rntbdContext();
+            final int pendingRequestCount = requestManager.pendingRequestCount();
+
+            logger.warn("{} health check failed due to nonresponding write: {lastChannelWriteAttemptNanoTime: {}, " +
+                    "lastChannelWriteNanoTime: {}, writeDelayInNanos: {}, writeDelayLimitInNanos: {}, " +
+                    "rntbdContext: {}, pendingRequestCount: {}}",
+                channel, timestamps.lastChannelWriteAttemptNanoTime(), timestamps.lastChannelWriteNanoTime(),
+                writeDelayInNanos, this.writeDelayLimitInNanos, rntbdContext, pendingRequestCount);
+
+            String msg = MessageFormat.format(
+                "{0} health check failed due to nonresponding write: (lastChannelWriteAttemptNanoTime: {1}, " +
+                    "lastChannelWriteNanoTime: {2}, writeDelayInNanos: {3}, writeDelayLimitInNanos: {4}, " +
+                    "rntbdContext: {5}, pendingRequestCount: {6})",
+                channel, timestamps.lastChannelWriteAttemptNanoTime(), timestamps.lastChannelWriteNanoTime(),
+                writeDelayInNanos, this.writeDelayLimitInNanos, rntbdContext, pendingRequestCount
+            );
+
+            return promise.setSuccess(msg);
+        }
+
+        // Black hole detection, part 2:
+        // Treat the connection as unhealthy if the gap between the last successful write and the last successful read
+        // grew beyond acceptable limits, unless a write succeeded recently. This is a sign of a nonresponding read.
+
+        final long readDelay = timestamps.lastChannelWriteNanoTime() - timestamps.lastChannelReadNanoTime();
+        final long readHangDuration = currentTime - timestamps.lastChannelWriteNanoTime();
+
+        if (readDelay > this.readDelayLimitInNanos && readHangDuration > readHangGracePeriodInNanos) {
+
+            final Optional<RntbdContext> rntbdContext = requestManager.rntbdContext();
+            final int pendingRequestCount = requestManager.pendingRequestCount();
+
+            logger.warn("{} health check failed due to nonresponding read: {lastChannelWrite: {}, lastChannelRead: {}, "
+                + "readDelay: {}, readDelayLimit: {}, rntbdContext: {}, pendingRequestCount: {}}", channel,
+                timestamps.lastChannelWriteNanoTime(), timestamps.lastChannelReadNanoTime(), readDelay,
+                this.readDelayLimitInNanos, rntbdContext, pendingRequestCount);
+
+            String msg = MessageFormat.format(
+                "{0} health check failed due to nonresponding read: (lastChannelWrite: {1}, lastChannelRead: {2}, "
+                    + "readDelay: {3}, readDelayLimit: {4}, rntbdContext: {5}, pendingRequestCount: {6})", channel,
+                timestamps.lastChannelWriteNanoTime(), timestamps.lastChannelReadNanoTime(), readDelay,
+                this.readDelayLimitInNanos, rntbdContext, pendingRequestCount
+            );
+
+            return promise.setSuccess(msg);
+        }
+
+        if (this.idleConnectionTimeoutInNanos > 0L) {
+            if (currentTime - timestamps.lastChannelReadNanoTime() > this.idleConnectionTimeoutInNanos) {
+                String msg = MessageFormat.format(
+                    "{0} health check failed due to idle connection timeout: (lastChannelWrite: {1}, lastChannelRead: {2}, "
+                        + "idleConnectionTimeout: {3}, currentTime: {4}", channel,
+                    timestamps.lastChannelWriteNanoTime(), timestamps.lastChannelReadNanoTime(),
+                    idleConnectionTimeoutInNanos, currentTime
+                );
+                return promise.setSuccess(msg);
+            }
+        }
+
+        channel.writeAndFlush(RntbdHealthCheckRequest.MESSAGE).addListener(completed -> {
+            if (completed.isSuccess()) {
+                promise.setSuccess(RntbdConstants.RntbdHealthCheckResults.SuccessValue);
+            } else {
+                logger.warn("{} health check request failed due to:", channel, completed.cause());
+
+                String msg = MessageFormat.format(
+                    "{0} health check request failed due to: {1}",
+                    channel,
+                    completed.cause().toString()
+                );
+
+                promise.setSuccess(msg);
+            }
+        });
+
+        return promise;
+    }
+
     @Override
     public String toString() {
         return RntbdObjectMapper.toString(this);

sdk/cosmos/azure-cosmos/src/main/java/com/azure/cosmos/implementation/directconnectivity/rntbd/RntbdConstants.java

@@ -22,6 +22,10 @@ public final class RntbdConstants {
     private RntbdConstants() {
     }
 
+    public static class RntbdHealthCheckResults {
+        public static final String SuccessValue = "Success";
+    }
+
     public enum RntbdConsistencyLevel {
 
         Strong((byte) 0x00),