[
https://issues.apache.org/jira/browse/IGNITE-26193?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Aleksandr Polovtsev updated IGNITE-26193:
-----------------------------------------
Description:
When analyzing a JFR from a write-heavy workload, I noticed the following
problem: a lot of {{TxPriority[]}} arrays are being allocated through
{{TxPriority.values()}} calls, because it's used inside
{{{}TxIdPriorityComparator{}}}. This can be easily fixed by using a cached
implementation.
Before the fix:
!Screenshot 2025-08-12 at 20.51.18.png|width=985,height=694!
was:
When analyzing a JFR from a write-heavy workload, I noticed the following
problem: a lot of `TxPriority[]` arrays are being allocated through
`TxPriority.values()` calls, because it's used inside `TxIdPriorityComparator`.
This can be easily fixed by using a cached implementation.
Before the fix:
!Screenshot 2025-08-12 at 20.51.18.png|width=985,height=694!
> Excessive TxPriority[] array allocations
> ----------------------------------------
>
> Key: IGNITE-26193
> URL: https://issues.apache.org/jira/browse/IGNITE-26193
> Project: Ignite
> Issue Type: Improvement
> Reporter: Aleksandr Polovtsev
> Assignee: Aleksandr Polovtsev
> Priority: Major
> Labels: ignite-3
> Attachments: Screenshot 2025-08-12 at 20.51.18.png
>
>
> When analyzing a JFR from a write-heavy workload, I noticed the following
> problem: a lot of {{TxPriority[]}} arrays are being allocated through
> {{TxPriority.values()}} calls, because it's used inside
> {{{}TxIdPriorityComparator{}}}. This can be easily fixed by using a cached
> implementation.
> Before the fix:
> !Screenshot 2025-08-12 at 20.51.18.png|width=985,height=694!
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
