Zhang Li
Zhang Li
**Describe the bug** currently, each requester can allocate at most `(pool_size - tracker_total) / num_requesters` memory. if an execution plan is skewed there will be a lot of memory wasted...
error recovery is important for practical parser, is there any plan that plex will support it? for example, when we are failed to parse a statement, we skip remaining tokens...
**Is your feature request related to a problem or challenge? Please describe what you are trying to do.** currently, blaze hangs on TPC-DS q40 case (1TB) because of a severely...
is there any plan to support deoplete under neovim?
**Is your feature request related to a problem? Please describe.** [apache-celeborn](https://celeborn.apache.org/) is widely used as an RSS (remote shuffle service) for spark. currently blaze has supported an internal RSS implementation...
**Is your feature request related to a problem? Please describe.** currently this is not supported in v2.0.6. we have to broadcast the original small table data to executor and build...
**Is your feature request related to a problem? Please describe.** spark uses SortMergeJoin for symmetric large data by default and ShuffledHashJoin is optional. can we implement a native ShuffledHashJoin for...
**Is your feature request related to a problem? Please describe.** arrow-rs is supporting new `StringViewArray` type (https://github.com/apache/arrow-rs/issues/5374), which is likely to achieve better performance by reducing large memcpys. **Describe the...
# Which issue does this PR close? Closes #260 . # Rationale for this change # What changes are included in this PR? # Are there any user-facing changes?