[
https://issues.apache.org/jira/browse/CASSANDRA-6465?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Tyler Hobbs updated CASSANDRA-6465:
-----------------------------------
Attachment: throughput.png
99th_latency.png
Attached are two graphs of throughput and 99th percentile latencies for four
runs of stress. Two runs kept the time penalty in DES, and two had it removed.
There was a normal stress read of 3 million rows with and without the time
penalty, and a second run where one of the three nodes was suspended 30 seconds
into the run and resumed 60 seconds into the run.
In short, there's no difference in throughput or median/95th/99th latencies
when a node goes down with the time penalty removed, so it looks like rapid
read protection does indeed dominate there.
> DES scores fluctuate too much for cache pinning
> -----------------------------------------------
>
> Key: CASSANDRA-6465
> URL: https://issues.apache.org/jira/browse/CASSANDRA-6465
> Project: Cassandra
> Issue Type: Bug
> Components: Core
> Environment: 1.2.11, 2 DC cluster
> Reporter: Chris Burroughs
> Assignee: Tyler Hobbs
> Priority: Minor
> Labels: gossip
> Fix For: 2.0.5
>
> Attachments: 99th_latency.png, des-score-graph.png,
> des.sample.15min.csv, get-scores.py, throughput.png
>
>
> To quote the conf:
> {noformat}
> # if set greater than zero and read_repair_chance is < 1.0, this will allow
> # 'pinning' of replicas to hosts in order to increase cache capacity.
> # The badness threshold will control how much worse the pinned host has to be
> # before the dynamic snitch will prefer other replicas over it. This is
> # expressed as a double which represents a percentage. Thus, a value of
> # 0.2 means Cassandra would continue to prefer the static snitch values
> # until the pinned host was 20% worse than the fastest.
> dynamic_snitch_badness_threshold: 0.1
> {noformat}
> An assumption of this feature is that scores will vary by less than
> dynamic_snitch_badness_threshold during normal operations. Attached is the
> result of polling a node for the scores of 6 different endpoints at 1 Hz for
> 15 minutes. The endpoints to sample were chosen with `nodetool getendpoints`
> for row that is known to get reads. The node was acting as a coordinator for
> a few hundred req/second, so it should have sufficient data to work with.
> Other traces on a second cluster have produced similar results.
> * The scores vary by far more than I would expect, as show by the difficulty
> of seeing anything useful in that graph.
> * The difference between the best and next-best score is usually > 10%
> (default dynamic_snitch_badness_threshold).
> Neither ClientRequest nor ColumFamily metrics showed wild changes during the
> data gathering period.
> Attachments:
> * jython script cobbled together to gather the data (based on work on the
> mailing list from Maki Watanabe a while back)
> * csv of DES scores for 6 endpoints, polled about once a second
> * Attempt at making a graph
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
