saxenapranav commented on code in PR #6699:
URL: https://github.com/apache/hadoop/pull/6699#discussion_r1579180763
##########
hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsInputStream.java:
##########
@@ -376,32 +439,48 @@ private int readLastBlock(final byte[] b, final int off,
final int len)
// data need to be copied to user buffer from index bCursor,
// AbfsInutStream buffer is going to contain data from last block start. In
// that case bCursor will be set to fCursor - lastBlockStart
- long lastBlockStart = max(0, contentLength - footerReadSize);
+ if (!fileStatusInformationPresent.get()) {
+ long lastBlockStart = max(0, (fCursor + len) - footerReadSize);
+ bCursor = (int) (fCursor - lastBlockStart);
+ return optimisedRead(b, off, len, lastBlockStart, min(fCursor + len,
footerReadSize), true);
+ }
+ long lastBlockStart = max(0, getContentLength() - footerReadSize);
bCursor = (int) (fCursor - lastBlockStart);
// 0 if contentlength is < buffersize
- long actualLenToRead = min(footerReadSize, contentLength);
- return optimisedRead(b, off, len, lastBlockStart, actualLenToRead);
+ long actualLenToRead = min(footerReadSize, getContentLength());
+ return optimisedRead(b, off, len, lastBlockStart, actualLenToRead, false);
}
private int optimisedRead(final byte[] b, final int off, final int len,
- final long readFrom, final long actualLen) throws IOException {
+ final long readFrom, final long actualLen,
+ final boolean isReadWithoutContentLengthInformation) throws IOException {
fCursor = readFrom;
int totalBytesRead = 0;
int lastBytesRead = 0;
try {
buffer = new byte[bufferSize];
+ boolean fileStatusInformationPresentBeforeRead =
fileStatusInformationPresent.get();
for (int i = 0;
- i < MAX_OPTIMIZED_READ_ATTEMPTS && fCursor < contentLength; i++) {
+ i < MAX_OPTIMIZED_READ_ATTEMPTS &&
(!fileStatusInformationPresent.get()
+ || fCursor < getContentLength()); i++) {
lastBytesRead = readInternal(fCursor, buffer, limit,
(int) actualLen - limit, true);
if (lastBytesRead > 0) {
totalBytesRead += lastBytesRead;
+ boolean shouldBreak = !fileStatusInformationPresentBeforeRead
+ && totalBytesRead == (int) actualLen;
limit += lastBytesRead;
fCursor += lastBytesRead;
fCursorAfterLastRead = fCursor;
+ if (shouldBreak) {
+ break;
+ }
}
}
} catch (IOException e) {
+ if (isNonRetriableOptimizedReadException(e)) {
+ throw e;
Review Comment:
adding:
```
/*
* FileNotFoundException in AbfsInputStream read can happen only in
case of
* lazy optimization enabled. In such case, the contentLength is not
known
* before opening the inputStream, and the first read can give a
* FileNotFoundException, and if this exception is raised, it has to
be
* thrown back to the application and make a readOneBlock call.
*/
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org
