perf: Change HDD read params default values

[dmga44]

This change targets tuning the chunkserver read scheme default behavior
into providing better performance in a general basis:
MAX_BLOCKS_PER_HDD_READ_JOB = 8 -> 16
MAX_PARALLEL_HDD_READ_JOBS_PER_CS_ENTRY = 16 -> 1

Signed-off-by: Dave [email protected]

[gemini-code-assist]

Summary of Changes

Hello @dmga44, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces performance tuning adjustments to the chunkserver's HDD read scheme. By modifying two key default parameters, the aim is to optimize read operations for better general performance. The changes involve increasing the amount of data processed per read job while simultaneously reducing the degree of parallelism for read jobs per client connection, reflecting a strategic shift in how disk reads are managed to improve overall efficiency.

Highlights

• Increased Read Job Block Size: The default value for MAX_BLOCKS_PER_HDD_READ_JOB has been increased from 8 to 16. This change allows the chunkserver to read more data in a single operation, potentially reducing the overhead of multiple smaller read requests.
• Reduced Parallel Read Jobs: The default value for MAX_PARALLEL_HDD_READ_JOBS_PER_CS_ENTRY has been significantly reduced from 16 to 1. This adjustment limits the number of concurrent read jobs processed per client connection, which might help in managing disk I/O contention or optimizing sequential access patterns.
• Consistent Configuration Updates: These default parameter changes are consistently applied across the chunkserver's configuration documentation (doc/sfschunkserver.cfg.5.adoc), C++ constant definitions (src/chunkserver/network_worker_thread.h), and default option mappings (src/admin/dump_config_command.cc and src/data/sfschunkserver.cfg.in).

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the default values for HDD read parameters to improve performance. Specifically, MAX_BLOCKS_PER_HDD_READ_JOB is increased from 8 to 16, and MAX_PARALLEL_HDD_READ_JOBS_PER_CS_ENTRY is decreased from 16 to 1. The changes are applied consistently across the codebase, including documentation and configuration files.

My main concern, detailed in a specific comment, is the potential for performance regression in certain workloads due to the reduction in parallelism for read jobs. While this may benefit sequential reads on HDDs, it could negatively impact other scenarios. More details on the performance analysis would be beneficial.

[Copilot]

Pull Request Overview

Performance tuning changes to optimize HDD read parameters in the chunkserver configuration by adjusting default values for better general performance.

• Increased maximum blocks per HDD read job from 8 to 16 to enable larger single read operations
• Decreased maximum parallel HDD read jobs per client connection from 16 to 1 to reduce contention
• Updated configuration documentation to reflect the new default values

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
src/data/sfschunkserver.cfg.in	Updated configuration template with new default values and comments
src/chunkserver/network_worker_thread.h	Modified constant definitions for HDD read job parameters
src/admin/dump_config_command.cc	Updated default configuration map with new parameter values
doc/sfschunkserver.cfg.5.adoc	Updated documentation to reflect new default values

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}