Mailing-List: contact issues-help@ignite.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@ignite.apache.org
Date: Thu, 13 Apr 2017 15:04:41 +0000 (UTC)
From: "Ivan Rakov (JIRA)" <jira@apache.org>
To: issues@ignite.apache.org
Message-ID: <JIRA.13063816.1492095351000.276425.1492095881665@Atlassian.JIRA>
In-Reply-To: <JIRA.13063816.1492095351000@Atlassian.JIRA>
References: <JIRA.13063816.1492095351000@Atlassian.JIRA> <JIRA.13063816.1492095351805@jira-lw-us.apache.org>
Subject: [jira] [Updated] (IGNITE-4959) Possible slight memory leak in free
 list
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Thu, 13 Apr 2017 15:04:48 -0000


     [ https://issues.apache.org/jira/browse/IGNITE-4959?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Ivan Rakov updated IGNITE-4959:
-------------------------------
    Description: 
To reproduce, run PageEvictionMultinodeTest (any eviction mode), set ENTRIES to Integer.MAX_VALUE.
Observations:
1) After a few minutes of test running, number of allocated pages looks like a constant (a bit more than eviciton threshold, 90% by default). This is expected behaviour with enabled page eviction.
2) More precise measurement shows that there's slow linear growth of allocated pages number, literally 10-20 pages per minute.
3) Number of pages with type T_PAGE_LIST_NODE grows, number of all other pages remains constant.
4) Though, total number of data pages in free list remains constant (with minor fluctuations).
We have to find out whether this process has a saturation point, after which pages number stops growing. Otherwise, it's a memory leak and should be fixed.

  was:
To reproduce, run PageEvictionMultinodeTest (any eviction mode), set ENTRIES to Integer.MAX_VALUE.
Observations:
1) After a few minutes of test running, number of allocated pages looks like a constant (a bit more than eviciton threshold, 90% by default). This is expected behaviour with enabled page eviction.
2) More precise measurement shows that there's slow linear growth of allocated pages number, literally 10-20 pages per minute.
3) Number of pages with type T_PAGE_LIST_NODE grows, number of all other pages remains constant.
4) Though, total number of pages in free list remains constant (with minor fluctuations).
We have to find out whether this process has a saturation point, after which pages number stops growing. Otherwise, it's a memory leak and should be fixed.


> Possible slight memory leak in free list
> ----------------------------------------
>
>                 Key: IGNITE-4959
>                 URL: https://issues.apache.org/jira/browse/IGNITE-4959
>             Project: Ignite
>          Issue Type: Improvement
>          Components: cache
>    Affects Versions: 2.0
>            Reporter: Ivan Rakov
>            Assignee: Alexey Goncharuk
>
> To reproduce, run PageEvictionMultinodeTest (any eviction mode), set ENTRIES to Integer.MAX_VALUE.
> Observations:
> 1) After a few minutes of test running, number of allocated pages looks like a constant (a bit more than eviciton threshold, 90% by default). This is expected behaviour with enabled page eviction.
> 2) More precise measurement shows that there's slow linear growth of allocated pages number, literally 10-20 pages per minute.
> 3) Number of pages with type T_PAGE_LIST_NODE grows, number of all other pages remains constant.
> 4) Though, total number of data pages in free list remains constant (with minor fluctuations).
> We have to find out whether this process has a saturation point, after which pages number stops growing. Otherwise, it's a memory leak and should be fixed.


--
This message was sent by Atlassian JIRA
(v6.3.15#6346)