ignite-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Vladimir Ozerov (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (IGNITE-5579) Make sure identical binary metadata updates from the same node do not happen twice
Date Mon, 10 Jul 2017 07:26:00 GMT

     [ https://issues.apache.org/jira/browse/IGNITE-5579?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Vladimir Ozerov updated IGNITE-5579:
------------------------------------
    Fix Version/s:     (was: 2.1)
                   2.2

> Make sure identical binary metadata updates from the same node do not happen twice
> ----------------------------------------------------------------------------------
>
>                 Key: IGNITE-5579
>                 URL: https://issues.apache.org/jira/browse/IGNITE-5579
>             Project: Ignite
>          Issue Type: Improvement
>          Components: cache
>    Affects Versions: 1.7
>            Reporter: Alexey Goncharuk
>             Fix For: 2.2
>
>
> It is possible that multiple user threads attempt identical binary metadata update concurrently.
In this case, a node will just increase contention on the cache key, but once the lock is
acquired there will be nothing changed. On large topologies, this may lead to nodes waiting
for the metadata update for hours (!).
> We should work out a way to identify identical metadata updates and allow only one thread
to proceed.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

Mime
View raw message