cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Peter Kovgan (JIRA)" <j...@apache.org>
Subject [jira] [Comment Edited] (CASSANDRA-10937) OOM on multiple nodes during test of insert load
Date Sun, 27 Dec 2015 06:11:49 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-10937?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072053#comment-15072053
] 

Peter Kovgan edited comment on CASSANDRA-10937 at 12/27/15 6:10 AM:
--------------------------------------------------------------------

Unfortunatelly retest with lesser load did not help.
Now average CPU usage on all nodes was 60-70%.(when test started, not sure about entire test)
There are still some nodes down.
GC is very long (30-40 sec) before OOM occurs.

I send logs and heap shapshot attachment (test3.rar)

First (2015-12-24 20:51:58) OOM occured on node 69 (logs attached in test3.rar) 
Then (2015-12-25 03:20:28) hints ate all the disk space on node 65 and node shutdown
Then (2015-12-25 13:10:20) the node 67 gone with OOM





--  Address      Load       Tokens       Owns    Host ID                               Rack
UN  10.20.42.68  285.06 GB  256          ?       6ce9d0bf-9569-4f4a-9769-c96f76a1c87f  rack1
DN  10.20.42.69  119.4 GB   256          ?       8452fbfb-c692-403e-9c43-83493ab39201  rack1
UN  10.20.42.64  317.97 GB  256          ?       b09eb63c-0d24-4373-8379-85d0616f488e  rack1
DN  10.20.42.65  197.49 GB  256          ?       61a1561a-15a4-412b-b831-b47a6e5902a9  rack1
UN  10.20.42.66  276.96 GB  256          ?       22a3f2d8-39ea-4aa9-9b38-be8e850823f4  rack1
DN  10.20.42.67  243.97 GB  256          ?       05672e1a-581a-45b1-92fe-9c3ce9409752  rack1
UN  10.20.42.62  332.89 GB  256          ?       e3e74ff4-c8f9-4186-b4ec-b66a6e05d9b4  rack1
UN  10.20.42.63  330.99 GB  256          ?       e51a871f-6aac-415e-9928-2ead4d3cbf6b  rack1


was (Author: tierhetze):
Unfortunatelly retest with lesser load did not help.
Now average CPU usage on all nodes was 60-70%.(when test started, not sure about entire test)
There are still some nodes down.
GC is very long (30-40 sec) before OOM occurs.

I send logs and heap shapshot attachment (test3.rar)

--  Address      Load       Tokens       Owns    Host ID                               Rack
UN  10.20.42.68  285.06 GB  256          ?       6ce9d0bf-9569-4f4a-9769-c96f76a1c87f  rack1
DN  10.20.42.69  119.4 GB   256          ?       8452fbfb-c692-403e-9c43-83493ab39201  rack1
UN  10.20.42.64  317.97 GB  256          ?       b09eb63c-0d24-4373-8379-85d0616f488e  rack1
DN  10.20.42.65  197.49 GB  256          ?       61a1561a-15a4-412b-b831-b47a6e5902a9  rack1
UN  10.20.42.66  276.96 GB  256          ?       22a3f2d8-39ea-4aa9-9b38-be8e850823f4  rack1
DN  10.20.42.67  243.97 GB  256          ?       05672e1a-581a-45b1-92fe-9c3ce9409752  rack1
UN  10.20.42.62  332.89 GB  256          ?       e3e74ff4-c8f9-4186-b4ec-b66a6e05d9b4  rack1
UN  10.20.42.63  330.99 GB  256          ?       e51a871f-6aac-415e-9928-2ead4d3cbf6b  rack1

> OOM on multiple nodes during test of insert load
> ------------------------------------------------
>
>                 Key: CASSANDRA-10937
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-10937
>             Project: Cassandra
>          Issue Type: Bug
>         Environment: Cassandra : 3.0.0
> Installed as open archive, no connection to any OS specific installer.
> Java:
> Java(TM) SE Runtime Environment (build 1.8.0_65-b17)
> OS :
> Linux version 2.6.32-431.el6.x86_64 (mockbuild@x86-023.build.eng.bos.redhat.com) (gcc
version 4.4.7 20120313 (Red Hat 4.4.7-4) (GCC) ) #1 SMP Sun Nov 10 22:19:54 EST 2013
> We have:
> 8 guests ( Linux OS as above) on 2 (VMWare managed) physical hosts. Each physical host
keeps 4 guests.
> Physical host parameters(shared by all 4 guests):
> Model: HP ProLiant DL380 Gen9
> Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz
> 46 logical processors.
> Hyperthreading - enabled
> Each guest assigned to have:
> 1 disk 300 Gb for seq. log (NOT SSD)
> 1 disk 4T for data (NOT SSD)
> 11 CPU cores
> Disks are local, not shared.
> Memory on each host -  24 Gb total.
> 8 Gb - cassandra heap
> (lshw and cpuinfo attached in file)
>            Reporter: Peter Kovgan
>         Attachments: more-logs.rar, some-heap-stats.rar, test2.rar, test3.rar
>
>
> 8 cassandra nodes.
> Load test started with 4 clients(different and not equal machines), each running 1000
threads.
> Each thread assigned in round-robin way to run one of 4 different inserts. 
> Consistency->ONE.
> I attach the full CQL schema of tables and the query of insert.
> Replication factor - 2:
> create keyspace OBLREPOSITORY_NY with replication = {'class':'NetworkTopologyStrategy','NY':2};
> Initiall throughput is:
> 215.000  inserts /sec
> or
> 54Mb/sec, considering single insert size a bit larger than 256byte.
> Data:
> all fields(5-6) are short strings, except one is BLOB of 256 bytes.
> After about a 2-3 hours of work, I was forced to increase timeout from 2000 to 5000ms,
for some requests failed for short timeout.
> Later on(after aprox. 12 hous of work) OOM happens on multiple nodes.
> (all failed nodes logs attached)
> I attach also java load client and instructions how set-up and use it.
> The test is important for our strategic project and we hope it is curable.
> Attachments:
> test2.rar -contains most of material
> more-logs.rar - contains additional nodes logs



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message