Integrated: 8327042: G1: Parallelism used for redirty logged cards needs better control.

[Ivan Walulya]

On Thu, 22 Feb 2024 13:02:13 GMT, Ivan Walulya <iwalulya at openjdk.org> wrote:

> Please review this change that provides better scaling of the `RedirtyLoggedCardsTask` with high number of worker threads. In the current implementation, the threads  contend for access to the Log Buffers through a single BufferNode resulting in a bottleneck as we increase the threads. The cost per card is pretty low, thus the work distribution overhead dominates the task. 
> 
> The new approach preserves the BufferNodeList states from G1ParScanThreadState, which effectively act as fingers (short cuts) into the list of buffers within `G1RedirtyCardsQueueSet`. We use these  BufferNodeList states to distribute BufferNodes for "redirtying" to the worker threads. By creating multiple points of access to the buffers, this method significantly reduces synchronization overheads and eliminates the bottleneck.
> 
> I have attached results from the Big Ram Tester microbenchmark on a server that spins up 163 worker threads for the `RedirtyLoggedCardsTask`
> 
> ![prepare_mixed](https://github.com/openjdk/jdk/assets/69453999/7120aa59-9b84-4e32-ac58-129ff31bb668)
> ![normal](https://github.com/openjdk/jdk/assets/69453999/7aafb72e-8f18-410d-9f1b-0c0adcd78b03)
> ![mixed](https://github.com/openjdk/jdk/assets/69453999/8a115d9c-56d3-4654-931e-1fa84987915d)
> ![concurrent_start](https://github.com/openjdk/jdk/assets/69453999/783d8804-b7b8-42a7-976c-4c217636157b)
> 
> 
> Testing: Tier 1-3

This pull request has now been integrated.

Changeset: b69d1b51
Author:    Ivan Walulya <iwalulya at openjdk.org>
URL:       https://git.openjdk.org/jdk/commit/b69d1b51c77ceda2fae3402418f4afcae2a735a8
Stats:     55 lines in 5 files changed: 28 ins; 7 del; 20 mod

8327042: G1: Parallelism used for redirty logged cards needs better control.

Co-authored-by: Thomas Schatzl <tschatzl at openjdk.org>
Reviewed-by: tschatzl, ayang

-------------

PR: https://git.openjdk.org/jdk/pull/17963