>
>
> [image: image.png]
>
> from your posting, the result is amazing. glad to know hive on mr3 has
> that nice performance.
>
Hive on MR3 is similar to Hive-LLAP in performance, so we can interpret the
above result as Hive being much faster than SparkSQL. For executing
concurrent queries, the per
I spent some time over the past couple of years making micro optimizations
within Avro, Parquet, ORC.
Curious to know if there's a way for you all to get timings at different
levels of the stack to compare and not just look at the top-line numbers. A
further breakdown could also help identify area
[image: image.png]
from your posting, the result is amazing. glad to know hive on mr3 has that
nice performance.
regards.
On Sat, Jan 7, 2023 at 11:29 PM Sungwoo Park wrote:
> In fact, Hive 3 has been much faster than Spark for a long time. For
> complex queries, Hive 3 is much faster than Pr
Thanks for this insight guys.
On your point below and I quote:
... "It's even as fast as Spark by using the default mr engine"
OK as we are all experimentalists, are we stating that the classic
MapReduce computation can outdo Spark's in-memory computation. I would be
curious to know this.
Than
In fact, Hive 3 has been much faster than Spark for a long time. For
complex queries, Hive 3 is much faster than Presto (or Trino) as well. The
reality is different from common beliefs on Hive, Spark, and Presto. If
interested, see the result of performance comparison using the TPC-DS
benchmark.
P
