[ https://issues.apache.org/jira/browse/CASSANDRA-10937?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072053#comment-15072053 ]
Peter Kovgan commented on CASSANDRA-10937: ------------------------------------------ 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 > (mockbu...@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 > > > 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)