hi!
In hbase 0.90.2, HFile$Reader readBlock do this:
synchronized (blockIndex.blockKeys[block]) {
blockLoads++;
// Check cache for block. If found return.
if (cache != null) {
ByteBuffer cachedBuf = cache.getBlock(name + block, cacheBlock);
if (cachedBuf != null) {
// Return a distinct 'shallow copy' of the block,
// so pos doesnt get messed by the scanner
cacheHits++;
return cachedBuf.duplicate();
}
// Carry on, please load.
}
// load from file
// put to cache
}
Why check cache code snippets be wrote in synchronized? I think we
can also do the check cache for block code outside the synchronized,so
we can improve performance.
--
=============================
| BlueDavy |
| http://www.bluedavy.com |
=============================
