[Opt](cloud) Add segment prefetcher

[bobhan1]

What problem does this PR solve?

Cold run test result

• Environment: 1 FE + 2 BE(aliyun, ecs.i4g.16xlarge, 2.7 GHz Intel® Xeon® Scalable (Ice Lake) processors with high-performance local NVMe SSDs)
  • Network baseline bandwidth 32 Gbit/s
• Duplicate table, 16 buckets, 6178831001 rows, data size is 396.837 GB
• Cold run means query without any doris page, OS page cache or local disk file cache, all data will be fetched from S3.
• Query: select count(user_id) from test_dup3 where env_id % 10 = 0 and user_id%10=0 and time % 10 =0 and event_id % 10 = 0 and length(domain) % 10 = 0 and length(path) % 10 = 0 and length(query)%10=0;
  • For this query, each BE will download 114GB data to local disk file cache from S3
  • 8 instance * 48 scanner = 384 scanner on each BE, and scanner thread pool size is set to 48

	no prefetch	prefetch_block_size=2
query time	2min47sec	39sec273ms
network bandwidth (on one BE)

based on #59476

Check List (For Author)

• Test

  • Regression test
  • Unit Test
  • Manual test (add detailed scripts or steps below)
  • No need to test or manual test. Explain why:
    • This is a refactor/code format and no logic has been changed.
    • Previous test can cover this change.
    • No code files have been changed.
    • Other reason

• Behavior changed:

  • No.
  • Yes.

• Does this need documentation?

  • No.
  • Yes.

Check List (For Reviewer who merge this PR)

• Confirm the release note
• Confirm test cases
• Confirm document
• Add branch pick label

[Thearas]

Thank you for your contribution to Apache Doris.
Don't know what should be done next? See How to process your PR.

Please clearly describe your PR:

1. What problem was fixed (it's best to include specific error reporting information). How it was fixed.
2. Which behaviors were modified. What was the previous behavior, what is it now, why was it modified, and what possible impacts might there be.
3. What features were added. Why was this function added?
4. Which code was refactored and why was this part of the code refactored?
5. Which functions were optimized and what is the difference before and after the optimization?

[bobhan1]

run buildall

[hello-stephen]

Cloud UT Coverage Report

Increment line coverage 🎉

Increment coverage report
Complete coverage report

Category	Coverage
Function Coverage	79.53% (1779/2237)
Line Coverage	64.72% (31481/48643)
Region Coverage	65.38% (15655/23943)
Branch Coverage	55.99% (8318/14856)

[dataroaring]

run buildall

[doris-robot]

Cloud UT Coverage Report

Increment line coverage 🎉

Increment coverage report
Complete coverage report

Category	Coverage
Function Coverage	79.53% (1779/2237)
Line Coverage	64.74% (31490/48643)
Region Coverage	65.41% (15660/23943)
Branch Coverage	56.00% (8320/14856)

[doris-robot]

BE UT Coverage Report

Increment line coverage 27.93% (205/734) 🎉

Increment coverage report
Complete coverage report

Category	Coverage
Function Coverage	53.03% (18997/35820)
Line Coverage	39.07% (175906/450188)
Region Coverage	33.62% (136271/405311)
Branch Coverage	34.58% (58772/169962)