[apache#1267] improvement(client): throw the detailed stacktrace when…

… exceptions happened (apache#1411)

### What changes were proposed in this pull request?

Save the previous exception in advance to prevent it from being lost during the next retry.

### Why are the changes needed?

This is the follow up pr of  [apache#1344](apache#1344)

### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

Existing UTs.

client-spark/spark3/src/main/java/org/apache/spark/shuffle/DelegationRssShuffleManager.java

@@ -164,10 +164,7 @@ private boolean tryAccessCluster() {
         return canAccess;
       } catch (Throwable e) {
         LOG.warn(
-            "Fail to access cluster {} using {} for {}",
-            coordinatorClient.getDesc(),
-            accessId,
-            e.getMessage());
+            "Fail to access cluster {} using {} for ", coordinatorClient.getDesc(), accessId, e);
       }
     }
 

common/src/main/java/org/apache/uniffle/common/util/RetryUtils.java

@@ -82,8 +82,18 @@ public static <T> T retryWithCondition(
       } catch (Throwable t) {
         retry++;
         if (isRetryFunc.apply(t) && retry < retryTimes) {
-          LOG.info("Retry due to Throwable, " + t.getClass().getName() + " " + t.getMessage());
-          LOG.info("Waiting " + intervalMs + " milliseconds before next connection attempt.");
+          if (LOG.isDebugEnabled()) {
+            LOG.error("Retry due to Throwable ", t);
+          } else {
+            LOG.error(
+                "Retry due to Throwable {}. Use DEBUG level to see the full stack: {}",
+                t.getClass().getName(),
+                t.getMessage());
+          }
+          LOG.error(
+              "Will retry {} more time(s) after waiting {} milliseconds.",
+              retryTimes - retry,
+              intervalMs);
           Thread.sleep(intervalMs);
           if (callBack != null) {
             callBack.execute();

internal-client/src/main/java/org/apache/uniffle/client/impl/grpc/ShuffleServerGrpcClient.java

@@ -464,7 +464,7 @@ public RssSendShuffleDataResponse sendShuffleData(RssSendShuffleDataRequest requ
             maxRetryAttempts,
             t -> !(t instanceof OutOfMemoryError));
       } catch (Throwable throwable) {
-        LOG.warn(throwable.getMessage());
+        LOG.warn("Failed to send shuffle data due to ", throwable);
         isSuccessful = false;
         break;
       }

internal-client/src/main/java/org/apache/uniffle/client/impl/grpc/ShuffleServerGrpcNettyClient.java

@@ -154,7 +154,7 @@ public RssSendShuffleDataResponse sendShuffleData(RssSendShuffleDataRequest requ
             maxRetryAttempts,
             t -> !(t instanceof OutOfMemoryError));
       } catch (Throwable throwable) {
-        LOG.warn(throwable.getMessage());
+        LOG.warn("Failed to send shuffle data due to ", throwable);
         isSuccessful = false;
         break;
       }