Avoid skew in Roundrobin repartition #18880

Dandandan · 2025-11-22T10:01:26Z

Which issue does this PR close?

Closes Roundrobin repartition skews to left-side partitions #18883

Rationale for this change

This makes roundrobin repartition more fairly distributed.
The benchmarks probably don't reflect this as much (maybe on very high core counts?), as the partitioning already mostly happens at the source side.

What changes are included in this PR?

Set start partition based on input partition.

Are these changes tested?

Existing tests

Are there any user-facing changes?

Dandandan · 2025-11-22T10:04:57Z

datafusion/core/tests/physical_optimizer/partition_statistics.rs

        }
        assert_eq!(partition_row_counts.len(), 3);
-        assert_eq!(partition_row_counts[0], 2);
+        assert_eq!(partition_row_counts[0], 1);


This shows the improvement - all output partitions get at least 1 batch, instead of skewing them to the left side.

Dandandan · 2025-11-23T07:24:26Z

Couldn't show perf difference on my 10 core machine.

alamb

Makes sense to me -- thank you @Dandandan

I have scheduled a benchmark run just to make sure there isn't something we missed but I don't think so

alamb · 2025-11-23T14:58:04Z

🤖 ./gh_compare_branch.sh Benchmark Script Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing improve_round_robin (7923e9c) to e6d1773 diff using: tpch_mem clickbench_partitioned clickbench_extended
Results will be posted here when complete

alamb · 2025-11-23T15:45:22Z

🤖: Benchmark completed

Details

Comparing HEAD and improve_round_robin
--------------------
Benchmark clickbench_extended.json
--------------------
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query        ┃        HEAD ┃ improve_round_robin ┃    Change ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 0     │  2595.38 ms │          2597.17 ms │ no change │
│ QQuery 1     │  1177.94 ms │          1190.90 ms │ no change │
│ QQuery 2     │  2380.03 ms │          2409.04 ms │ no change │
│ QQuery 3     │  1123.45 ms │          1169.65 ms │ no change │
│ QQuery 4     │  2306.66 ms │          2299.56 ms │ no change │
│ QQuery 5     │ 28310.15 ms │         28487.39 ms │ no change │
│ QQuery 6     │  4053.54 ms │          4070.51 ms │ no change │
│ QQuery 7     │  3539.32 ms │          3484.79 ms │ no change │
└──────────────┴─────────────┴─────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                  ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                  │ 45486.47ms │
│ Total Time (improve_round_robin)   │ 45709.01ms │
│ Average Time (HEAD)                │  5685.81ms │
│ Average Time (improve_round_robin) │  5713.63ms │
│ Queries Faster                     │          0 │
│ Queries Slower                     │          0 │
│ Queries with No Change             │          8 │
│ Queries with Failure               │          0 │
└────────────────────────────────────┴────────────┘
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query        ┃        HEAD ┃ improve_round_robin ┃        Change ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0     │     2.15 ms │             2.38 ms │  1.11x slower │
│ QQuery 1     │    49.73 ms │            56.40 ms │  1.13x slower │
│ QQuery 2     │   135.28 ms │           152.26 ms │  1.13x slower │
│ QQuery 3     │   165.47 ms │           180.46 ms │  1.09x slower │
│ QQuery 4     │  1134.59 ms │          1197.59 ms │  1.06x slower │
│ QQuery 5     │  1515.78 ms │          1575.32 ms │     no change │
│ QQuery 6     │     2.13 ms │             2.13 ms │     no change │
│ QQuery 7     │    56.23 ms │            56.15 ms │     no change │
│ QQuery 8     │  1495.27 ms │          1514.66 ms │     no change │
│ QQuery 9     │  1924.03 ms │          1984.95 ms │     no change │
│ QQuery 10    │   374.62 ms │           379.12 ms │     no change │
│ QQuery 11    │   426.78 ms │           432.36 ms │     no change │
│ QQuery 12    │  1451.16 ms │          1479.07 ms │     no change │
│ QQuery 13    │  2172.22 ms │          2188.10 ms │     no change │
│ QQuery 14    │  1310.14 ms │          1335.93 ms │     no change │
│ QQuery 15    │  1261.43 ms │          1293.28 ms │     no change │
│ QQuery 16    │  2684.79 ms │          2746.00 ms │     no change │
│ QQuery 17    │  2646.52 ms │          2709.54 ms │     no change │
│ QQuery 18    │  5450.75 ms │          5190.07 ms │     no change │
│ QQuery 19    │   128.17 ms │           131.84 ms │     no change │
│ QQuery 20    │  2019.99 ms │          1986.07 ms │     no change │
│ QQuery 21    │  2384.41 ms │          2308.55 ms │     no change │
│ QQuery 22    │  4026.18 ms │          3892.83 ms │     no change │
│ QQuery 23    │ 13686.85 ms │         12851.26 ms │ +1.07x faster │
│ QQuery 24    │   213.69 ms │           220.83 ms │     no change │
│ QQuery 25    │   475.22 ms │           477.64 ms │     no change │
│ QQuery 26    │   211.72 ms │           229.80 ms │  1.09x slower │
│ QQuery 27    │  2890.26 ms │          2821.92 ms │     no change │
│ QQuery 28    │ 24093.16 ms │         23316.79 ms │     no change │
│ QQuery 29    │  1012.48 ms │           968.54 ms │     no change │
│ QQuery 30    │  1372.89 ms │          1365.68 ms │     no change │
│ QQuery 31    │  1430.46 ms │          1395.63 ms │     no change │
│ QQuery 32    │  4937.49 ms │          4567.13 ms │ +1.08x faster │
│ QQuery 33    │  6032.51 ms │          5668.22 ms │ +1.06x faster │
│ QQuery 34    │  6052.95 ms │          6020.43 ms │     no change │
│ QQuery 35    │  1966.38 ms │          1919.65 ms │     no change │
│ QQuery 36    │   126.48 ms │           118.61 ms │ +1.07x faster │
│ QQuery 37    │    53.75 ms │            53.95 ms │     no change │
│ QQuery 38    │   122.80 ms │           120.61 ms │     no change │
│ QQuery 39    │   200.01 ms │           200.19 ms │     no change │
│ QQuery 40    │    41.49 ms │            43.51 ms │     no change │
│ QQuery 41    │    39.54 ms │            41.39 ms │     no change │
│ QQuery 42    │    32.83 ms │            33.60 ms │     no change │
└──────────────┴─────────────┴─────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                  ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                  │ 97810.75ms │
│ Total Time (improve_round_robin)   │ 95230.45ms │
│ Average Time (HEAD)                │  2274.67ms │
│ Average Time (improve_round_robin) │  2214.66ms │
│ Queries Faster                     │          4 │
│ Queries Slower                     │          6 │
│ Queries with No Change             │         33 │
│ Queries with Failure               │          0 │
└────────────────────────────────────┴────────────┘
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query        ┃      HEAD ┃ improve_round_robin ┃        Change ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1     │ 130.05 ms │           132.03 ms │     no change │
│ QQuery 2     │  27.07 ms │            28.60 ms │  1.06x slower │
│ QQuery 3     │  34.31 ms │            39.21 ms │  1.14x slower │
│ QQuery 4     │  29.36 ms │            29.37 ms │     no change │
│ QQuery 5     │  88.72 ms │            87.85 ms │     no change │
│ QQuery 6     │  19.61 ms │            19.71 ms │     no change │
│ QQuery 7     │ 220.58 ms │           225.71 ms │     no change │
│ QQuery 8     │  34.36 ms │            35.66 ms │     no change │
│ QQuery 9     │ 102.35 ms │           103.43 ms │     no change │
│ QQuery 10    │  66.06 ms │            65.16 ms │     no change │
│ QQuery 11    │  18.34 ms │            17.60 ms │     no change │
│ QQuery 12    │  52.17 ms │            51.29 ms │     no change │
│ QQuery 13    │  47.91 ms │            47.14 ms │     no change │
│ QQuery 14    │  14.02 ms │            14.20 ms │     no change │
│ QQuery 15    │  26.16 ms │            24.45 ms │ +1.07x faster │
│ QQuery 16    │  25.21 ms │            25.57 ms │     no change │
│ QQuery 17    │ 150.56 ms │           149.85 ms │     no change │
│ QQuery 18    │ 278.19 ms │           282.53 ms │     no change │
│ QQuery 19    │  37.49 ms │            37.54 ms │     no change │
│ QQuery 20    │  50.17 ms │            49.66 ms │     no change │
│ QQuery 21    │ 321.74 ms │           328.07 ms │     no change │
│ QQuery 22    │  17.75 ms │            18.11 ms │     no change │
└──────────────┴───────────┴─────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                  ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                  │ 1792.17ms │
│ Total Time (improve_round_robin)   │ 1812.71ms │
│ Average Time (HEAD)                │   81.46ms │
│ Average Time (improve_round_robin) │   82.40ms │
│ Queries Faster                     │         1 │
│ Queries Slower                     │         2 │
│ Queries with No Change             │        19 │
│ Queries with Failure               │         0 │
└────────────────────────────────────┴───────────┘

Dandandan · 2025-11-23T20:01:15Z

🤖: Benchmark completed

Details

Comparing HEAD and improve_round_robin
--------------------
Benchmark clickbench_extended.json
--------------------
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query        ┃        HEAD ┃ improve_round_robin ┃    Change ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 0     │  2595.38 ms │          2597.17 ms │ no change │
│ QQuery 1     │  1177.94 ms │          1190.90 ms │ no change │
│ QQuery 2     │  2380.03 ms │          2409.04 ms │ no change │
│ QQuery 3     │  1123.45 ms │          1169.65 ms │ no change │
│ QQuery 4     │  2306.66 ms │          2299.56 ms │ no change │
│ QQuery 5     │ 28310.15 ms │         28487.39 ms │ no change │
│ QQuery 6     │  4053.54 ms │          4070.51 ms │ no change │
│ QQuery 7     │  3539.32 ms │          3484.79 ms │ no change │
└──────────────┴─────────────┴─────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                  ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                  │ 45486.47ms │
│ Total Time (improve_round_robin)   │ 45709.01ms │
│ Average Time (HEAD)                │  5685.81ms │
│ Average Time (improve_round_robin) │  5713.63ms │
│ Queries Faster                     │          0 │
│ Queries Slower                     │          0 │
│ Queries with No Change             │          8 │
│ Queries with Failure               │          0 │
└────────────────────────────────────┴────────────┘
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query        ┃        HEAD ┃ improve_round_robin ┃        Change ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0     │     2.15 ms │             2.38 ms │  1.11x slower │
│ QQuery 1     │    49.73 ms │            56.40 ms │  1.13x slower │
│ QQuery 2     │   135.28 ms │           152.26 ms │  1.13x slower │
│ QQuery 3     │   165.47 ms │           180.46 ms │  1.09x slower │
│ QQuery 4     │  1134.59 ms │          1197.59 ms │  1.06x slower │
│ QQuery 5     │  1515.78 ms │          1575.32 ms │     no change │
│ QQuery 6     │     2.13 ms │             2.13 ms │     no change │
│ QQuery 7     │    56.23 ms │            56.15 ms │     no change │
│ QQuery 8     │  1495.27 ms │          1514.66 ms │     no change │
│ QQuery 9     │  1924.03 ms │          1984.95 ms │     no change │
│ QQuery 10    │   374.62 ms │           379.12 ms │     no change │
│ QQuery 11    │   426.78 ms │           432.36 ms │     no change │
│ QQuery 12    │  1451.16 ms │          1479.07 ms │     no change │
│ QQuery 13    │  2172.22 ms │          2188.10 ms │     no change │
│ QQuery 14    │  1310.14 ms │          1335.93 ms │     no change │
│ QQuery 15    │  1261.43 ms │          1293.28 ms │     no change │
│ QQuery 16    │  2684.79 ms │          2746.00 ms │     no change │
│ QQuery 17    │  2646.52 ms │          2709.54 ms │     no change │
│ QQuery 18    │  5450.75 ms │          5190.07 ms │     no change │
│ QQuery 19    │   128.17 ms │           131.84 ms │     no change │
│ QQuery 20    │  2019.99 ms │          1986.07 ms │     no change │
│ QQuery 21    │  2384.41 ms │          2308.55 ms │     no change │
│ QQuery 22    │  4026.18 ms │          3892.83 ms │     no change │
│ QQuery 23    │ 13686.85 ms │         12851.26 ms │ +1.07x faster │
│ QQuery 24    │   213.69 ms │           220.83 ms │     no change │
│ QQuery 25    │   475.22 ms │           477.64 ms │     no change │
│ QQuery 26    │   211.72 ms │           229.80 ms │  1.09x slower │
│ QQuery 27    │  2890.26 ms │          2821.92 ms │     no change │
│ QQuery 28    │ 24093.16 ms │         23316.79 ms │     no change │
│ QQuery 29    │  1012.48 ms │           968.54 ms │     no change │
│ QQuery 30    │  1372.89 ms │          1365.68 ms │     no change │
│ QQuery 31    │  1430.46 ms │          1395.63 ms │     no change │
│ QQuery 32    │  4937.49 ms │          4567.13 ms │ +1.08x faster │
│ QQuery 33    │  6032.51 ms │          5668.22 ms │ +1.06x faster │
│ QQuery 34    │  6052.95 ms │          6020.43 ms │     no change │
│ QQuery 35    │  1966.38 ms │          1919.65 ms │     no change │
│ QQuery 36    │   126.48 ms │           118.61 ms │ +1.07x faster │
│ QQuery 37    │    53.75 ms │            53.95 ms │     no change │
│ QQuery 38    │   122.80 ms │           120.61 ms │     no change │
│ QQuery 39    │   200.01 ms │           200.19 ms │     no change │
│ QQuery 40    │    41.49 ms │            43.51 ms │     no change │
│ QQuery 41    │    39.54 ms │            41.39 ms │     no change │
│ QQuery 42    │    32.83 ms │            33.60 ms │     no change │
└──────────────┴─────────────┴─────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                  ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                  │ 97810.75ms │
│ Total Time (improve_round_robin)   │ 95230.45ms │
│ Average Time (HEAD)                │  2274.67ms │
│ Average Time (improve_round_robin) │  2214.66ms │
│ Queries Faster                     │          4 │
│ Queries Slower                     │          6 │
│ Queries with No Change             │         33 │
│ Queries with Failure               │          0 │
└────────────────────────────────────┴────────────┘
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query        ┃      HEAD ┃ improve_round_robin ┃        Change ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1     │ 130.05 ms │           132.03 ms │     no change │
│ QQuery 2     │  27.07 ms │            28.60 ms │  1.06x slower │
│ QQuery 3     │  34.31 ms │            39.21 ms │  1.14x slower │
│ QQuery 4     │  29.36 ms │            29.37 ms │     no change │
│ QQuery 5     │  88.72 ms │            87.85 ms │     no change │
│ QQuery 6     │  19.61 ms │            19.71 ms │     no change │
│ QQuery 7     │ 220.58 ms │           225.71 ms │     no change │
│ QQuery 8     │  34.36 ms │            35.66 ms │     no change │
│ QQuery 9     │ 102.35 ms │           103.43 ms │     no change │
│ QQuery 10    │  66.06 ms │            65.16 ms │     no change │
│ QQuery 11    │  18.34 ms │            17.60 ms │     no change │
│ QQuery 12    │  52.17 ms │            51.29 ms │     no change │
│ QQuery 13    │  47.91 ms │            47.14 ms │     no change │
│ QQuery 14    │  14.02 ms │            14.20 ms │     no change │
│ QQuery 15    │  26.16 ms │            24.45 ms │ +1.07x faster │
│ QQuery 16    │  25.21 ms │            25.57 ms │     no change │
│ QQuery 17    │ 150.56 ms │           149.85 ms │     no change │
│ QQuery 18    │ 278.19 ms │           282.53 ms │     no change │
│ QQuery 19    │  37.49 ms │            37.54 ms │     no change │
│ QQuery 20    │  50.17 ms │            49.66 ms │     no change │
│ QQuery 21    │ 321.74 ms │           328.07 ms │     no change │
│ QQuery 22    │  17.75 ms │            18.11 ms │     no change │
└──────────────┴───────────┴─────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                  ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                  │ 1792.17ms │
│ Total Time (improve_round_robin)   │ 1812.71ms │
│ Average Time (HEAD)                │   81.46ms │
│ Average Time (improve_round_robin) │   82.40ms │
│ Queries Faster                     │         1 │
│ Queries Slower                     │         2 │
│ Queries with No Change             │        19 │
│ Queries with Failure               │         0 │
└────────────────────────────────────┴───────────┘

Looks like mostly noise.

milenkovicm · 2026-01-02T12:35:37Z

Sorry I'm a bit late with my comment. I've stumbled upon this change updating ballista. Its a bit confusing change from usage perspective, there are two parameters which are used only in round robin case, would it make sense splitting try_new method in try_new_hash and try_new_round_robin?

alamb · 2026-01-05T21:20:00Z

makes sense to me

milenkovicm · 2026-01-06T09:40:50Z

created #19664

…ructors (#19668) ### Which issue does this PR close? Closes #19664 --- ### Rationale for this change After #18880, `BatchPartitioner::try_new` gained additional parameters that are only relevant for round-robin repartitioning. This made the constructor API confusing, as hash repartitioning received parameters it does not use. Splitting the constructor improves clarity and avoids passing round-robin–specific parameters to hash partitioning. --- ### What changes are included in this PR? - Introduce `BatchPartitioner::try_new_hash` - Introduce `BatchPartitioner::try_new_round_robin` - Refactor callers to use the specialized constructors - Retain `BatchPartitioner::try_new` as a delegator for backward compatibility This is a pure refactor; behavior is unchanged. --- ### Are these changes tested? Yes. Existing tests cover this code path. All builds pass locally. --- ### Are there any user-facing changes? No. This change is internal only and does not affect user-facing behavior or APIs. --------- Co-authored-by: Your Name <[email protected]>

…ructors (apache#19668) ### Which issue does this PR close? Closes apache#19664 --- ### Rationale for this change After apache#18880, `BatchPartitioner::try_new` gained additional parameters that are only relevant for round-robin repartitioning. This made the constructor API confusing, as hash repartitioning received parameters it does not use. Splitting the constructor improves clarity and avoids passing round-robin–specific parameters to hash partitioning. --- ### What changes are included in this PR? - Introduce `BatchPartitioner::try_new_hash` - Introduce `BatchPartitioner::try_new_round_robin` - Refactor callers to use the specialized constructors - Retain `BatchPartitioner::try_new` as a delegator for backward compatibility This is a pure refactor; behavior is unchanged. --- ### Are these changes tested? Yes. Existing tests cover this code path. All builds pass locally. --- ### Are there any user-facing changes? No. This change is internal only and does not affect user-facing behavior or APIs. --------- Co-authored-by: Your Name <[email protected]>

Avoid repartition skew

fb56dfe

github-actions bot added core Core DataFusion crate physical-plan Changes to the physical-plan crate labels Nov 22, 2025

comment

6165887

Dandandan commented Nov 22, 2025

View reviewed changes

Dandandan added 2 commits November 22, 2025 11:08

Simplify

0cc5ba2

Simplify

7923e9c

Dandandan changed the title ~~Avoid repartition skew~~ Avoid skew in Roundrobin repartition Nov 22, 2025

Dandandan force-pushed the improve_round_robin branch from 026513e to 7923e9c Compare November 22, 2025 18:59

alamb approved these changes Nov 23, 2025

View reviewed changes

Dandandan added this pull request to the merge queue Nov 23, 2025

Merged via the queue into apache:main with commit c2ba087 Nov 23, 2025
75 checks passed

milenkovicm mentioned this pull request Jan 6, 2026

Split BatchPartitioner::try_new(..) into BatchPartitioner::new_hash and BatchPartitioner::new_round_robin #19664

Closed

mohit7705 mentioned this pull request Jan 6, 2026

feat: split BatchPartitioner::try_new into hash and round-robin constructors #19668

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Avoid skew in Roundrobin repartition #18880

Avoid skew in Roundrobin repartition #18880

Dandandan commented Nov 22, 2025 •

edited

Loading

Uh oh!

Dandandan Nov 22, 2025 •

edited

Loading

Uh oh!

Dandandan commented Nov 23, 2025

Uh oh!

alamb left a comment

Uh oh!

alamb commented Nov 23, 2025

Uh oh!

alamb commented Nov 23, 2025

Uh oh!

Dandandan commented Nov 23, 2025

Uh oh!

Uh oh!

milenkovicm commented Jan 2, 2026

Uh oh!

alamb commented Jan 5, 2026

Uh oh!

milenkovicm commented Jan 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Avoid skew in Roundrobin repartition #18880

Avoid skew in Roundrobin repartition #18880

Conversation

Dandandan commented Nov 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Which issue does this PR close?

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

Uh oh!

Dandandan Nov 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Dandandan commented Nov 23, 2025

Uh oh!

alamb left a comment

Choose a reason for hiding this comment

Uh oh!

alamb commented Nov 23, 2025

Uh oh!

alamb commented Nov 23, 2025

Uh oh!

Dandandan commented Nov 23, 2025

Uh oh!

Uh oh!

milenkovicm commented Jan 2, 2026

Uh oh!

alamb commented Jan 5, 2026

Uh oh!

milenkovicm commented Jan 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Dandandan commented Nov 22, 2025 •

edited

Loading

Dandandan Nov 22, 2025 •

edited

Loading