cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Dikang Gu (JIRA)" <>
Subject [jira] [Commented] (CASSANDRA-11432) Counter values become under-counted when running repair.
Date Tue, 12 Apr 2016 22:45:25 GMT


Dikang Gu commented on CASSANDRA-11432:

some streaming logs:

2016-04-12_22:19:52.59350 INFO  22:19:52 [STREAM-IN-/2401:db00:2130:912f:face:0:13:0]: [Stream
#aa8c5160-00fc-11e6-9ed8-8723daea4be1 ID#0] Prepare completed. Receiving 207 files(2967220
bytes), sending 57 files(444705 bytes)
2016-04-12_22:19:54.00185 INFO  22:19:54 [STREAM-IN-/2401:db00:2130:9135:face:0:23:0]: [Stream
#ac374240-00fc-11e6-a8cd-65049a873696 ID#0] Prepare completed. Receiving 2 files(35759 bytes),
sending 2 files(36185 bytes)
2016-04-12_22:19:57.06246 INFO  22:19:57 [STREAM-IN-/2401:db00:2130:912f:face:0:13:0]: [Stream
#ae779550-00fc-11e6-9ed8-8723daea4be1 ID#0] Prepare completed. Receiving 69 files(1097912
bytes), sending 18 files(253570 bytes)
2016-04-12_22:19:59.58458 INFO  22:19:59 [STREAM-IN-/2401:db00:2130:9135:face:0:23:0]: [Stream
#ae988ad0-00fc-11e6-a8cd-65049a873696 ID#0] Prepare completed. Receiving 16 files(245781 bytes),
sending 19 files(292037 bytes)

> Counter values become under-counted when running repair.
> --------------------------------------------------------
>                 Key: CASSANDRA-11432
>                 URL:
>             Project: Cassandra
>          Issue Type: Bug
>            Reporter: Dikang Gu
>            Assignee: Aleksey Yeschenko
> We are experimenting Counters in Cassandra 2.2.5. Our setup is that we have 6 nodes,
across three different regions, and in each region, the replication factor is 2. Basically,
each nodes holds a full copy of the data.
> We are writing to cluster with CL = 2, and reading with CL = 1. 
> When are doing 30k/s counter increment/decrement per node, and at the meanwhile, we are
double writing to our mysql tier, so that we can measure the accuracy of C* counter, compared
to mysql.
> The experiment result was great at the beginning, the counter value in C* and mysql are
very close. The difference is less than 0.1%. 
> But when we start to run the repair on one node, the counter value in C* become much
less than the value in mysql,  the difference becomes larger than 1%.
> My question is that is it a known problem that the counter value will become under-counted
if repair is running? Should we avoid running repair for counter tables?
> Thanks. 

This message was sent by Atlassian JIRA

View raw message