feat(query): restore prefetch for spilled sort blocks

[forsaken628]

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

Summary

• Restore prefetch for spilled sort blocks.
• Dynamically adjusts num_merge based on current memory usage.

Tests

• Unit Test
• Logic Test
• Benchmark Test
• No Test - Explain why

Type of change

• Bug Fix (non-breaking change which fixes an issue)
• New Feature (non-breaking change which adds functionality)
• Breaking Change (fix or feature that could cause existing functionality not to work as expected)
• Documentation Update
• Refactoring
• Performance Improvement
• Other (please describe):

---

This change is 

[github-actions]

Docker Image for PR

• tag: pr-19409-44d95f9-1770973358

note: this image tag is only available for internal use.

[forsaken628]

benchmark

DataSet: tpch sf100
SQL: select * from orders order by o_totalprice desc ignore_result;
version:
default: v1.2.881-nightly-1cc88fbd2d
pr-19409: v1.2.881-nightly-44d95f9ded

settings	warehouse	warehouse_size	query_duration_s	sort_cpu_s	sort_io_s	scan_cpu_s	scan_io_s	spill_write_mib	spill_write_cnt	spill_write_s	spill_read_mib	spill_read_cnt	spill_read_s
	default	Small	8.992	82.069	0.000	28.664	120.315	0.00	0	0.000	0.00	0	0.000
	pr-19409	Small	8.411	79.013	0.000	27.590	110.592	0.00	0	0.000	0.00	0	0.000
8GB memory,max_threads=16	default	Small	129.949	191.875	435.848	24.951	129.753	8727.22	2576	271.944	8727.22	2576	245.662
8GB memory,max_threads=16	pr-19409	Small	103.968	171.155	458.787	23.912	118.767	9240.97	2592	271.162	9240.97	2592	252.046
8GB memory,max_threads=16,prefetch	pr-19409	Small	94.509	172.547	278.685	25.427	149.108	9024.19	2618	273.412	9024.19	2618	268.342
8GB memory,max_threads=8	default	Small	147.596	172.960	425.807	21.144	117.693	7626.20	2338	232.318	7626.20	2338	264.497
8GB memory,max_threads=8	pr-19409	Small	123.879	152.505	399.620	21.295	105.338	7499.10	2297	225.891	7499.10	2297	226.442
8GB memory,max_threads=8,prefetch	pr-19409	Small	91.926	155.238	205.868	21.607	112.598	7517.94	2304	227.549	7517.94	2304	254.188
8GB memory,max_threads=4	default	Small	213.574	168.825	416.782	20.946	104.166	7433.13	2281	227.004	7433.13	2281	258.523
8GB memory,max_threads=4	pr-19409	Small	197.512	150.545	415.796	20.503	105.156	7539.75	2317	233.391	7539.75	2317	235.309
8GB memory,max_threads=4,prefetch	pr-19409	Small	133.019	154.509	214.640	20.888	107.092	7523.69	2315	238.795	7523.69	2315	261.771

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 8ed2c0f5c2

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".