Skip to content
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

Add queryID in userAgent for spark delta sharing queries in branch 0.7 #482

Merged
merged 2 commits into from
Apr 23, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ import java.nio.charset.StandardCharsets.UTF_8
import java.sql.Timestamp
import java.time.LocalDateTime
import java.time.format.DateTimeFormatter.ISO_DATE_TIME
import java.util.UUID

import scala.collection.JavaConverters._
import scala.collection.mutable.{ArrayBuffer, ListBuffer}
Expand Down Expand Up @@ -104,9 +105,12 @@ private[spark] class DeltaSharingRestClient(
sslTrustAll: Boolean = false,
forStreaming: Boolean = false
) extends DeltaSharingClient with Logging {
import DeltaSharingRestClient._

@volatile private var created = false

private var queryId: Option[String] = None

private lazy val client = {
val clientBuilder: HttpClientBuilder = if (sslTrustAll) {
val sslBuilder = new SSLContextBuilder()
Expand Down Expand Up @@ -480,6 +484,8 @@ private[spark] class DeltaSharingRestClient(
allowNoContent: Boolean = false,
fetchAsOneString: Boolean = false
): (Option[Long], Seq[String]) = {
// Reset queryId before calling RetryUtils, and before prepareHeaders.
queryId = Some(UUID.randomUUID().toString().split('-').head)
RetryUtils.runWithExponentialBackoff(numRetries, maxRetryDuration) {
val profile = profileProvider.getProfile
val response = client.execute(
Expand Down Expand Up @@ -550,7 +556,11 @@ private[spark] class DeltaSharingRestClient(
} else {
"Delta-Sharing-Spark"
}
s"$sparkAgent/$VERSION" + DeltaSharingRestClient.USER_AGENT
s"$sparkAgent/$VERSION" + s" $sparkVersionString" + s" $getQueryIdString" + USER_AGENT
}

private def getQueryIdString: String = {
s"QueryId-${queryId.getOrElse("not_set")}"
}

def close(): Unit = {
Expand All @@ -571,7 +581,6 @@ private[spark] object DeltaSharingRestClient extends Logging {

lazy val USER_AGENT = {
try {
s" $sparkVersionString" +
s" Hadoop/${VersionInfo.getVersion()}" +
s" ${spaceFreeProperty("os.name")}/${spaceFreeProperty("os.version")}" +
s" ${spaceFreeProperty("java.vm.name")}/${spaceFreeProperty("java.vm.version")}" +
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -184,6 +184,7 @@ case class DeltaSharingSource(
if (lastGetVersionTimestamp == -1 ||
(currentTimeMillis - lastGetVersionTimestamp) >= QUERY_TABLE_VERSION_INTERVAL_MILLIS) {
val serverVersion = deltaLog.client.getTableVersion(deltaLog.table)
logInfo(s"Got table version $serverVersion from Delta Sharing Server.")
if (serverVersion < 0) {
throw new IllegalStateException(s"Delta Sharing Server returning negative table version:" +
s"$serverVersion.")
Expand Down Expand Up @@ -1135,7 +1136,10 @@ case class DeltaSharingSource(
}
Some(v)
} else if (options.startingTimestamp.isDefined) {
Some(deltaLog.client.getTableVersion(deltaLog.table, options.startingTimestamp))
val version = deltaLog.client.getTableVersion(deltaLog.table, options.startingTimestamp)
logInfo(s"Got table version $version for timestamp ${options.startingTimestamp} " +
s"from Delta Sharing Server.")
Some(version)
} else {
None
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -41,12 +41,17 @@ class DeltaSharingRestClientSuite extends DeltaSharingIntegrationTest {
val httpRequest = new HttpGet("random_url")

val client = new DeltaSharingRestClient(testProfileProvider, forStreaming = false)
var h = client.prepareHeaders(httpRequest).getFirstHeader(HttpHeaders.USER_AGENT)
assert(!h.getValue.contains(DeltaSharingRestClient.SPARK_STRUCTURED_STREAMING))
var h = client.prepareHeaders(httpRequest).getFirstHeader(HttpHeaders.USER_AGENT).getValue
assert(!h.contains(DeltaSharingRestClient.SPARK_STRUCTURED_STREAMING))
assert(h.contains("Delta-Sharing-Spark"))
assert(h.contains(" QueryId-"))
assert(h.contains(" Hadoop/"))
assert(h.contains(" Linux/"))
assert(h.contains(" java/"))

val streamingClient = new DeltaSharingRestClient(testProfileProvider, forStreaming = true)
h = streamingClient.prepareHeaders(httpRequest).getFirstHeader(HttpHeaders.USER_AGENT)
assert(h.getValue.contains(DeltaSharingRestClient.SPARK_STRUCTURED_STREAMING))
h = streamingClient.prepareHeaders(httpRequest).getFirstHeader(HttpHeaders.USER_AGENT).getValue
assert(h.contains(DeltaSharingRestClient.SPARK_STRUCTURED_STREAMING))
}

integrationTest("listAllTables") {
Expand Down