From 65c3ead62f511645d47f5539e6d24aa762d4894f Mon Sep 17 00:00:00 2001
From: chrislu <chris.lu@gmail.com>
Date: Sun, 23 Nov 2025 13:28:38 -0800
Subject: [PATCH] debug: enhance logging to capture footer writes and getPos
 calls

Added targeted logging to answer the key question:
"Are the missing 78 bytes the Parquet footer that never got written?"

Changes:
1. Log ALL writes after call 220 (likely footer-related)
   - Previous: only logged writes >= 20 bytes
   - Now: also log small writes near end marked [FOOTER?]

2. Enhanced getPos() logging with writeCalls context
   - Shows relationship between getPos() and actual writes
   - Helps identify if Parquet calculates size before writing footer

This will reveal:
A) What the last ~14 write calls contain (footer structure)
B) If getPos() is called before/during footer writes
C) If there's a mismatch between calculated size and actual writes

Expected pattern if footer is missing:
- Large writes up to ~600 bytes (data pages)
- Small writes for metadata
- getPos() called to calculate footer offset
- Footer writes (78 bytes) that either:
  * Never happen (bug in Parquet)
  * Get lost in FSDataOutputStream
  * Are written but lost in flush

Next run will show the exact write sequence!
---
 .../seaweedfs/client/SeaweedOutputStream.java | 23 +++++++++++++------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/other/java/client/src/main/java/seaweedfs/client/SeaweedOutputStream.java b/other/java/client/src/main/java/seaweedfs/client/SeaweedOutputStream.java
index ed7f1d1d8..54a15bfba 100644
--- a/other/java/client/src/main/java/seaweedfs/client/SeaweedOutputStream.java
+++ b/other/java/client/src/main/java/seaweedfs/client/SeaweedOutputStream.java
@@ -99,8 +99,10 @@ public class SeaweedOutputStream extends OutputStream {
      */
     public synchronized long getPos() {
         long currentPos = position + buffer.position();
-        LOG.info("[DEBUG-2024] 📍 getPos() called: flushedPosition={} bufferPosition={} returning={} path={}",
-                position, buffer.position(), currentPos, path);
+        if (path.contains("parquet")) {
+            LOG.info("[DEBUG-2024] 📍 getPos() called: flushedPosition={} bufferPosition={} returning={} totalBytesWritten={} writeCalls={}", 
+                    position, buffer.position(), currentPos, totalBytesWritten, writeCallCount);
+        }
         return currentPos;
     }
 
@@ -168,11 +170,18 @@ public class SeaweedOutputStream extends OutputStream {
 
         totalBytesWritten += length;
         writeCallCount++;
-        // Only log significant writes to avoid flooding logs with byte-by-byte writes
-        if (path.contains("parquet") && length >= 20) {
-            LOG.info("[DEBUG-2024] ✍️ write({} bytes): totalSoFar={} writeCalls={} position={} bufferPos={}, file={}",
-                    length, totalBytesWritten, writeCallCount, position, buffer.position(),
-                    path.substring(path.lastIndexOf('/') + 1));
+        // Log significant writes AND writes near the end (potential footer)
+        if (path.contains("parquet")) {
+            if (length >= 20) {
+                LOG.info("[DEBUG-2024] ✍️ write({} bytes): totalSoFar={} writeCalls={} position={} bufferPos={}, file={}",
+                        length, totalBytesWritten, writeCallCount, position, buffer.position(),
+                        path.substring(path.lastIndexOf('/') + 1));
+            } else if (writeCallCount >= 220) {
+                // Log all small writes after call 220 (likely footer writes)
+                LOG.info("[DEBUG-2024] ✍️ write({} bytes): totalSoFar={} writeCalls={} position={} bufferPos={} [FOOTER?], file={}",
+                        length, totalBytesWritten, writeCallCount, position, buffer.position(),
+                        path.substring(path.lastIndexOf('/') + 1));
+            }
         }
 
         // System.out.println(path + " write [" + (outputIndex + off) + "," +