You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@ignite.apache.org by "Denis Chudov (Jira)" <ji...@apache.org> on 2023/08/17 07:54:00 UTC

[jira] [Updated] (IGNITE-20195) Long fsync of Raft log storage

     [ https://issues.apache.org/jira/browse/IGNITE-20195?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Denis Chudov updated IGNITE-20195:
----------------------------------
    Description: 
Under intensive transactional load (see test [1]) the duration of fsync of Raft log storage [2] can exceed 1 second on local test runs. To reproduce it, you should turn on fsync on raft configuration mock.

[1] ItTxDistributedTestThreeNodesThreeReplicas#testBalance

[2] RocksDbSharedLogStorage#commitWriteBatch

  was:
Under intensive transactional load (see test [1]) the duration of fsync of Raft log storage [2] can exceed 1 second on local test runs.

[1] ItTxDistributedTestThreeNodesThreeReplicas#testBalance

[2] RocksDbSharedLogStorage#commitWriteBatch


> Long fsync of Raft log storage
> ------------------------------
>
>                 Key: IGNITE-20195
>                 URL: https://issues.apache.org/jira/browse/IGNITE-20195
>             Project: Ignite
>          Issue Type: Bug
>            Reporter: Denis Chudov
>            Priority: Major
>              Labels: ignite-3
>
> Under intensive transactional load (see test [1]) the duration of fsync of Raft log storage [2] can exceed 1 second on local test runs. To reproduce it, you should turn on fsync on raft configuration mock.
> [1] ItTxDistributedTestThreeNodesThreeReplicas#testBalance
> [2] RocksDbSharedLogStorage#commitWriteBatch



--
This message was sent by Atlassian Jira
(v8.20.10#820010)