Feature/jdbc log s3 upload #85
There are no files selected for viewing
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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 | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|
@@ -2,6 +2,7 @@ | |||||||||||||||
|
|
||||||||||||||||
| import com.fasterxml.jackson.annotation.JsonCreator; | ||||||||||||||||
| import com.fasterxml.jackson.annotation.JsonValue; | ||||||||||||||||
| import java.io.File; | ||||||||||||||||
| import java.io.IOException; | ||||||||||||||||
| import java.sql.SQLException; | ||||||||||||||||
| import java.sql.Types; | ||||||||||||||||
|
|
@@ -15,6 +16,7 @@ | |||||||||||||||
| import org.embulk.config.ConfigSource; | ||||||||||||||||
| import org.embulk.config.TaskSource; | ||||||||||||||||
| import org.embulk.output.jdbc.*; | ||||||||||||||||
| import org.embulk.output.s3.JdbcLogUploader; | ||||||||||||||||
| import org.embulk.output.snowflake.PrivateKeyReader; | ||||||||||||||||
| import org.embulk.output.snowflake.SnowflakeCopyBatchInsert; | ||||||||||||||||
| import org.embulk.output.snowflake.SnowflakeOutputConnection; | ||||||||||||||||
|
|
@@ -91,6 +93,30 @@ public interface SnowflakePluginTask extends PluginTask { | |||||||||||||||
| @ConfigDefault("\"none\"") | ||||||||||||||||
| public MatchByColumnName getMatchByColumnName(); | ||||||||||||||||
|
|
||||||||||||||||
| @Config("upload_jdbc_log_to_s3") | ||||||||||||||||
| @ConfigDefault("false") | ||||||||||||||||
| public boolean getUploadJdbcLogToS3(); | ||||||||||||||||
|
|
||||||||||||||||
| @Config("s3_bucket") | ||||||||||||||||
| @ConfigDefault("null") | ||||||||||||||||
| public Optional<String> getS3Bucket(); | ||||||||||||||||
|
|
||||||||||||||||
| @Config("s3_prefix") | ||||||||||||||||
| @ConfigDefault("null") | ||||||||||||||||
| public Optional<String> getS3Prefix(); | ||||||||||||||||
|
|
||||||||||||||||
| @Config("s3_region") | ||||||||||||||||
| @ConfigDefault("null") | ||||||||||||||||
| public Optional<String> getS3Region(); | ||||||||||||||||
|
|
||||||||||||||||
| @Config("s3_access_key_id") | ||||||||||||||||
| @ConfigDefault("null") | ||||||||||||||||
| public Optional<String> getS3AccessKeyId(); | ||||||||||||||||
|
|
||||||||||||||||
| @Config("s3_secret_access_key") | ||||||||||||||||
| @ConfigDefault("null") | ||||||||||||||||
| public Optional<String> getS3SecretAccessKey(); | ||||||||||||||||
|
|
||||||||||||||||
| public void setCopyIntoTableColumnNames(String[] columnNames); | ||||||||||||||||
|
|
||||||||||||||||
| public String[] getCopyIntoTableColumnNames(); | ||||||||||||||||
|
|
@@ -139,6 +165,9 @@ public static MatchByColumnName fromString(String value) { | |||||||||||||||
| private static final int MASTER_TOKEN_INVALID_GS_CODE = 390115; | ||||||||||||||||
| private static final int ID_TOKEN_INVALID_LOGIN_REQUEST_GS_CODE = 390195; | ||||||||||||||||
|
|
||||||||||||||||
| private static final String ENCOUNTERED_COMMUNICATION_ERROR_MESSAGE = | ||||||||||||||||
| "JDBC driver encountered communication error"; | ||||||||||||||||
|
|
||||||||||||||||
| @Override | ||||||||||||||||
| protected Class<? extends PluginTask> getTaskClass() { | ||||||||||||||||
| return SnowflakePluginTask.class; | ||||||||||||||||
|
|
@@ -198,6 +227,10 @@ protected JdbcOutputConnector getConnector(PluginTask task, boolean retryableMet | |||||||||||||||
| props.setProperty("CLIENT_METADATA_REQUEST_USE_CONNECTION_CTX", "true"); | ||||||||||||||||
| props.setProperty("MULTI_STATEMENT_COUNT", "0"); | ||||||||||||||||
|
|
||||||||||||||||
| if (t.getUploadJdbcLogToS3()) { | ||||||||||||||||
| props.setProperty("tracing", "ALL"); | ||||||||||||||||
| } | ||||||||||||||||
|
|
||||||||||||||||
| props.putAll(t.getOptions()); | ||||||||||||||||
|
|
||||||||||||||||
| logConnectionProperties(url, props); | ||||||||||||||||
|
|
@@ -217,11 +250,53 @@ public ConfigDiff transaction( | |||||||||||||||
| try { | ||||||||||||||||
| snowflakeCon = (SnowflakeOutputConnection) getConnector(task, true).connect(true); | ||||||||||||||||
| snowflakeCon.runCreateStage(stageIdentifier); | ||||||||||||||||
|
|
||||||||||||||||
| configDiff = super.transaction(config, schema, taskCount, control); | ||||||||||||||||
| if (t.getDeleteStage()) { | ||||||||||||||||
| runDropStageWithRecovery(snowflakeCon, stageIdentifier, task); | ||||||||||||||||
| } | ||||||||||||||||
| } catch (Exception e) { | ||||||||||||||||
| if (e instanceof SQLException) { | ||||||||||||||||
| String message = e.getMessage(); | ||||||||||||||||
| if (message != null | ||||||||||||||||
| && message.contains(ENCOUNTERED_COMMUNICATION_ERROR_MESSAGE) | ||||||||||||||||
|
Comment on lines
+259
to
+262
There was a problem hiding this comment. [nitpick] Relying on message text can be brittle; consider checking the SQL error code or vendor-specific code instead of string matching to detect communication errors more reliably.
Suggested change
|
||||||||||||||||
| && t.getUploadJdbcLogToS3() == true) { | ||||||||||||||||
|
Contributor
There was a problem hiding this comment.
|
||||||||||||||||
| final Optional<String> s3Bucket = t.getS3Bucket(); | ||||||||||||||||
| final Optional<String> s3Prefix = t.getS3Prefix(); | ||||||||||||||||
| final Optional<String> s3Region = t.getS3Region(); | ||||||||||||||||
| final Optional<String> s3AccessKeyId = t.getS3AccessKeyId(); | ||||||||||||||||
| final Optional<String> s3SecretAccessKey = t.getS3SecretAccessKey(); | ||||||||||||||||
| if (!s3Bucket.isPresent() || !s3Region.isPresent()) { | ||||||||||||||||
| logger.warn("s3_bucket, and s3_region must be set when upload_jdbc_log_to_s3 is true"); | ||||||||||||||||
kentoyoshida marked this conversation as resolved.
Show resolved
Hide resolved
|
||||||||||||||||
| } else if (s3AccessKeyId.isPresent() != s3SecretAccessKey.isPresent()) { | ||||||||||||||||
| logger.warn( | ||||||||||||||||
| "Both s3_access_key_id and s3_secret_access_key must be set together or omitted."); | ||||||||||||||||
| } else { | ||||||||||||||||
| try (JdbcLogUploader jdbcLogUploader = | ||||||||||||||||
| new JdbcLogUploader( | ||||||||||||||||
| s3Bucket.get(), | ||||||||||||||||
| s3Prefix.orElse(""), | ||||||||||||||||
| s3Region.get(), | ||||||||||||||||
| s3AccessKeyId.orElse(null), | ||||||||||||||||
| s3SecretAccessKey.orElse(null))) { | ||||||||||||||||
| String tmpDir = System.getProperty("java.io.tmpdir", "/tmp"); | ||||||||||||||||
| File logDir = new File(tmpDir); | ||||||||||||||||
| File[] logFiles = logDir.listFiles((dir, name) -> name.startsWith("snowflake_jdbc")); | ||||||||||||||||
| if (logFiles != null && logFiles.length > 0) { | ||||||||||||||||
| Optional<File> latest = | ||||||||||||||||
| Arrays.stream(logFiles).max(Comparator.comparingLong(File::lastModified)); | ||||||||||||||||
| if (latest.isPresent()) { | ||||||||||||||||
| jdbcLogUploader.uploadIfExists(latest.get()); | ||||||||||||||||
| } | ||||||||||||||||
| } else { | ||||||||||||||||
| logger.warn("No snowflake_jdbc*.log file found in {} for upload", tmpDir); | ||||||||||||||||
| } | ||||||||||||||||
| } catch (Exception uploadException) { | ||||||||||||||||
| logger.warn("Failed to upload JDBC log to S3: {}", uploadException.getMessage()); | ||||||||||||||||
| } | ||||||||||||||||
| } | ||||||||||||||||
| } | ||||||||||||||||
| } | ||||||||||||||||
| if (t.getDeleteStage() && t.getDeleteStageOnError()) { | ||||||||||||||||
| try { | ||||||||||||||||
| runDropStageWithRecovery(snowflakeCon, stageIdentifier, task); | ||||||||||||||||
|
|
||||||||||||||||
This file contains hidden or 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 |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| package org.embulk.output.s3; | ||
|
|
||
| import java.io.File; | ||
| import java.time.LocalDateTime; | ||
| import java.time.format.DateTimeFormatter; | ||
| import org.slf4j.Logger; | ||
| import org.slf4j.LoggerFactory; | ||
| import software.amazon.awssdk.auth.credentials.AwsBasicCredentials; | ||
| import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider; | ||
| import software.amazon.awssdk.auth.credentials.StaticCredentialsProvider; | ||
| import software.amazon.awssdk.core.sync.RequestBody; | ||
| import software.amazon.awssdk.regions.Region; | ||
| import software.amazon.awssdk.services.s3.S3Client; | ||
| import software.amazon.awssdk.services.s3.model.PutObjectRequest; | ||
|
|
||
| public class JdbcLogUploader implements AutoCloseable { | ||
| private final Logger logger = LoggerFactory.getLogger(JdbcLogUploader.class); | ||
|
|
||
| private final S3Client s3Client; | ||
| private final String bucket; | ||
| private final String prefix; | ||
| private final Region region; | ||
|
|
||
| public JdbcLogUploader( | ||
| String bucket, String prefix, String region, String accessKeyId, String secretAccessKey) { | ||
| this.bucket = bucket; | ||
| this.prefix = prefix; | ||
| this.region = Region.of(region); | ||
|
|
||
| if (accessKeyId != null && secretAccessKey != null) { | ||
| // Use explicit credentials | ||
| AwsBasicCredentials awsCreds = AwsBasicCredentials.create(accessKeyId, secretAccessKey); | ||
| this.s3Client = | ||
| S3Client.builder() | ||
| .region(this.region) | ||
| .credentialsProvider(StaticCredentialsProvider.create(awsCreds)) | ||
| .build(); | ||
| } else { | ||
| // Use default credentials provider (IAM role, environment variables, etc.) | ||
| this.s3Client = | ||
| S3Client.builder() | ||
| .region(this.region) | ||
| .credentialsProvider(DefaultCredentialsProvider.create()) | ||
| .build(); | ||
| } | ||
| } | ||
|
|
||
| public void uploadIfExists(File file) { | ||
| if (!file.exists()) { | ||
| logger.warn("File not found: {}", file.getAbsolutePath()); | ||
| return; | ||
| } | ||
|
|
||
| // Add timestamp to filename | ||
| String timestamp = LocalDateTime.now().format(DateTimeFormatter.ofPattern("yyyyMMdd_HHmmss")); | ||
| String originalFileName = file.getName(); | ||
| String fileNameWithTimestamp; | ||
|
|
||
| // Insert timestamp before file extension | ||
| int lastDotIndex = originalFileName.lastIndexOf('.'); | ||
| if (lastDotIndex > 0) { | ||
| String nameWithoutExt = originalFileName.substring(0, lastDotIndex); | ||
| String extension = originalFileName.substring(lastDotIndex); | ||
| fileNameWithTimestamp = nameWithoutExt + "_" + timestamp + extension; | ||
| } else { | ||
| fileNameWithTimestamp = originalFileName + "_" + timestamp; | ||
| } | ||
|
|
||
| String key = prefix.isEmpty() ? fileNameWithTimestamp : prefix + "/" + fileNameWithTimestamp; | ||
| try { | ||
| PutObjectRequest putObjectRequest = | ||
| PutObjectRequest.builder().bucket(bucket).key(key).build(); | ||
|
|
||
| s3Client.putObject(putObjectRequest, RequestBody.fromFile(file)); | ||
| logger.info("Uploaded {}", file.getAbsolutePath()); | ||
| } catch (Exception e) { | ||
| logger.error("Failed to upload {}", file.getAbsolutePath(), e); | ||
| } | ||
| } | ||
|
|
||
| @Override | ||
| public void close() { | ||
| if (s3Client != null) { | ||
| s3Client.close(); | ||
| } | ||
| } | ||
| } |
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.
ref: https://github.com/embulk/embulk-output-s3
(nits)
s3_prefixcould bes3_path_prefixlike embulk-output-s3