[ https://issues.apache.org/jira/browse/IGNITE-4214?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15842414#comment-15842414 ]
Ksenia Rybakova edited comment on IGNITE-4214 at 1/27/17 9:04 AM: ------------------------------------------------------------------ "Failed to wait for partition map exchange" and "Failed to wait for partition release feature" are reproduced during failover test with the following config: Benchmark: CacheRandomOperation Operations: put, put_all, get, get_all, invoke, invoke_all, remove, remove_all, put_if_absent, replace Heap: 8Gb for servers, 4Gb for clients 4 clients, 12 servers Number of caches: 12 Types of caches (atomicity mode): different (atomic, transactional) Types of caches (tiered storage mode): different (onheap without eviction, onheap with eviction, offheap_tired, offheap_values) Types of caches (indexing): different (with and without indexes) Types of caches (cache mode): partitioned Backups count: 5 Restart option: first bunch of 4 servers are restarted one by one, when they return to grid the second bunch of 4 servers are restarted one by one and so on. Corresponding Yardstick configs, property file and logs (all servers and one of the drivers) are attached. was (Author: krybakova): Reproduced during failover test with the following config: Benchmark: CacheRandomOperation Operations: put, put_all, get, get_all, invoke, invoke_all, remove, remove_all, put_if_absent, replace Heap: 8Gb for servers, 4Gb for clients 4 clients, 12 servers Number of caches: 12 Types of caches (atomicity mode): different (atomic, transactional) Types of caches (tiered storage mode): different (onheap without eviction, onheap with eviction, offheap_tired, offheap_values) Types of caches (indexing): different (with and without indexes) Types of caches (cache mode): partitioned Backups count: 5 Restart option: first bunch of 4 servers are restarted one by one, when they return to grid the second bunch of 4 servers are restarted one by one and so on. Corresponding Yardstick configs, property file and logs (all servers and one of the drivers) are attached. > "Failed to wait for partition map exchange" warnings during different load > tests > -------------------------------------------------------------------------------- > > Key: IGNITE-4214 > URL: https://issues.apache.org/jira/browse/IGNITE-4214 > Project: Ignite > Issue Type: Bug > Affects Versions: 1.7 > Reporter: Ksenia Rybakova > Attachments: IGNITE-4214-failover-case.logs.zip, > IGNITE-4214.logs.zip, ignite-base-load-config.xml, run-load.properties, > run-load.xml > > > "Failed to wait for partition map exchange" warnings appears during different > load tests. Grid doesn't hang though and operations are performed > successfully. > Example of load test config: > - Benchmark: CacheRandomOperation > - Operations: put, put_all, get, get_all, invoke, invoke_all, remove, > remove_all, put_if_absent, replace > - Heap: 8Gb for servers, 4Gb for clients > - 5 clients, 20 servers > - Number of caches: 12 > - Types of caches (atomicity mode): different (atomic, transactional) > - Types of caches (tiered storage mode): different (onheap without eviction, > onheap with eviction, offheap_tired, offheap_values) > - Types of caches (indexing): different (with and without indexes) > - Types of caches (cache mode): different (partitioned, replicated) > - Backups count: 12 > Corresponding Yardstick configs and property file are attached. > Some logs with the error are attached. Complete logs will be provided by > request. -- This message was sent by Atlassian JIRA (v6.3.4#6332)