[jira] [Commented] (IGNITE-7368) IgniteCache.getAll() throws high volume of GridDhtInvalidPartitionException if on-heap is enabled

["Andrey Kornev (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/IGNITE-7368?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16319420#comment-16319420 ] 

Andrey Kornev commented on IGNITE-7368:
---------------------------------------

In terms of the fix, the code in {{org.apache.ignite.internal.processors.cache.distributed.dht.atomic.GridDhtAtomicCache#getAllAsync0()}} could be improved to reduce the amount of data that needs to fetched from remote nodes. All it has to do is at the top split the input key list into two: one with local (primary and if enabled backup) keys and the other one with non-local (remote) keys. Next, fire off an async fetch of the remote keys, while in parallel start retrieving the local keys.

> IgniteCache.getAll() throws high volume of GridDhtInvalidPartitionException if on-heap is enabled
> -------------------------------------------------------------------------------------------------
>
>                 Key: IGNITE-7368
>                 URL: https://issues.apache.org/jira/browse/IGNITE-7368
>             Project: Ignite
>          Issue Type: Bug
>          Components: cache
>    Affects Versions: 2.3
>            Reporter: Andrey Kornev
>         Attachments: Screen Shot 2018-01-09 at 3.37.53 PM.png
>
>
> With on-heap option enabled, {{IgniteCache.getAll()}} throws a GridDhtInvalidPartitionException if the input set of keys contains at least one non-local key (a key for which the node executing {{getAll}} is not the primary). In general case, the input set always contains such keys which, given sufficiently high request rate, results in thousands of exceptions thrown per second. Attached is a screenshot of a JFR recording showing the exceptions and their stack traces.



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