chore(query): refine hash join bitmap and support fast path for datablock take

[Dousir9]

I hereby agree to the terms of the CLA available at: https://databend.rs/dev/policies/cla/

Summary

After jorgecarleitao/arrow2#1574, If a Bitmap is all true or all false, Bitmap.slice() has almost no overhead, we can benefit a lot from it, for example, we can keep an all true bitmap true_validity in hash join ProbeState, when we need to wrap a Column to a NullableColumn, we can just slice the true_validity to avoid creating a new bitmap, it can also save a lot of memory(all bitmaps is refer to the true_validity), besides, we can introduce a fast path in take.rs and take_chunks.rs to avoid iterating column to generate a new bitmap when a bitmap is all true or all false.

• Closes #issue

---

This change is 

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
databend	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 12, 2023 2:07am

[github-actions]

Docker Image for PR

• tag: pr-13213-1ee5742

note: this image tag is only available for internal use,
please check the internal doc for more details.

[github-actions]

ClickBench Report

• hits: https://benchmark.databend.rs/clickbench/pr/13213/6483712052/hits.html
• tpch: https://benchmark.databend.rs/clickbench/pr/13213/6483712052/tpch.html

[BohuTANG]

Dev / linux / sqllogic_cluster_tpch:

[Diff] (-expected|+actual)
-   HashJoin: INNER (rows: 25224.93)
+   HashJoin: INNER (rows: 25247.99)
    ├── Build
    │   └── Scan: default.tpch.customer (read rows: 15000)
    └── Probe
-       └── HashJoin: INNER (rows: 25224.93)
+       └── HashJoin: INNER (rows: 25247.99)
            ├── Build
            │   └── Scan: default.tpch.orders (read rows: 150000)
            └── Probe
                └── HashJoin: INNER (rows: 120114.40)
                    ├── Build
                    │   └── HashJoin: INNER (rows: 200.00)
                    │       ├── Build
                    │       │   └── HashJoin: INNER (rows: 5.00)
                    │       │       ├── Build
                    │       │       │   └── Scan: default.tpch.region (read rows: 5)
                    │       │       └── Probe
                    │       │           └── Scan: default.tpch.nation (read rows: 25)
                    │       └── Probe
                    │           └── Scan: default.tpch.supplier (read rows: 1000)
                    └── Probe
                        └── Scan: default.tpch.lineitem (read rows: 600572)
at tests/sqllogictests/suites/tpch/queries.test:1325

[BohuTANG]

There is a same issue here in another PR:
https://github.com/datafuselabs/databend/actions/runs/6483645024/job/17606440850?pr=13213#step:4:165

[Dousir9]

There is a same issue here in another PR: https://github.com/datafuselabs/databend/actions/runs/6483645024/job/17606440850?pr=13213#step:4:165

This issue has been addressed by #13212.