Jay Narale
Jay Narale
Even if we use arrow, after the reads and before the writes we still might need to convert it to presto page format when we would exchange the table scan...
Thats awesome! you will need the reader as well. I was trying to look into this as a velox-beginner task for myself but I will leave it to the experts!
Actually the **PAGEFILE** may not be most optimal since TableScan operator has the data in **velox RowVectorPtr** and not in Presto **page** format unlike java. So using something which is...
@aditi-pandit I added some scaffolding in arrow ipc reader and writer (just named it pagefile in my velox pr) just to learn https://github.com/facebookincubator/velox/pull/11258/files#diff-831ec175fb2fa915fc432de875dc2205576589c1b1a87e9405189a6f88ccec58. The IPC file reader is working for...
Trying to brainstorm some ideas on how to do a cost based implementation Currently, the logicalCteOptimizer is situated high within the planning hierarchy, a level where historical statistics cannot be...
Nice! But can this increase S3 operation cost if the buffer size is too small?
Sounds good, but for temporary tables it might make more sense to have a bigger buffer size which is anyways configurable i guess.
cc: @kaikalur
Not working for me too
Please update the commit message with a little bit more description like **Remove Duplicate definition of kCounterMemoryCacheTotalTinyPaddingBytes metric**. Guidelines - [link](https://github.com/prestodb/presto/blob/2216cc61b6afcd8298b3f95b0138cc47f128214e/CONTRIBUTING.md#commit-message-style)