Re: [PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-06-06 Thread via GitHub
2010YOUY01 commented on PR #16192: URL: https://github.com/apache/datafusion/pull/16192#issuecomment-2951468269 > @2010YOUY01 Hi, I’ve been struggling a bit with tracking peak memory in SPM step, and I was wondering if I could ask for some help. > > ### 1. Can we add the memory for co

Re: [PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-06-06 Thread via GitHub
ding-young commented on PR #16192: URL: https://github.com/apache/datafusion/pull/16192#issuecomment-2949499201 @2010YOUY01 Thanks for your help! I’m currently working on a different issue (spill file compression option) meanwhile. Feel free to ping me if you'd like me to clarify any of the

Re: [PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-06-06 Thread via GitHub
2010YOUY01 commented on PR #16192: URL: https://github.com/apache/datafusion/pull/16192#issuecomment-2948663700 I added some background docs https://github.com/apache/datafusion/pull/16289, but gotta head out now — I’ll get back to the `ExternalSorter` part and address your questions in the

Re: [PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-06-03 Thread via GitHub
2010YOUY01 commented on PR #16192: URL: https://github.com/apache/datafusion/pull/16192#issuecomment-2938019298 @ding-young I also think the code to manage `reservation` + `merge_reservation` is tricky. I'll try to answer your questions by adding more doc about memory reservation management

Re: [PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-06-03 Thread via GitHub
ding-young commented on PR #16192: URL: https://github.com/apache/datafusion/pull/16192#issuecomment-2936483760 @2010YOUY01 Hi, I’ve been struggling a bit with tracking peak memory in SPM step, and I was wondering if I could ask for some help. ### 1. Can we add the memory for conv

Re: [PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-05-27 Thread via GitHub
2010YOUY01 commented on code in PR #16192: URL: https://github.com/apache/datafusion/pull/16192#discussion_r2110846999 ## datafusion/physical-plan/src/sorts/sort.rs: ## @@ -658,6 +664,8 @@ impl ExternalSorter { self.reservation .try_resize(get_reser

[PR] Track peak_mem_used in ExternalSorter [datafusion]

2025-05-26 Thread via GitHub
ding-young opened a new pull request, #16192: URL: https://github.com/apache/datafusion/pull/16192 ## Which issue does this PR close? - Related to #16042 ## Questions - There are other paths that does not build `ExternalSorter` when `execute()` is called in `SortEx