[
https://issues.apache.org/jira/browse/ZOOKEEPER-885?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Alexandre Hardy updated ZOOKEEPER-885:
--------------------------------------
Attachment: benchmark.csv
Here are some results with different settings of {{dirty_ratio}},
{{dirty_bytes}} (finer control), session timeouts, and io priorities (set with
{{ionice}}).
The status field indicates success or failure, 0=success and anything else is
failure.
Where failure means a zookeeper session disconnected (but did not necessarily
expire).
Each test ran for a maximum of 5 minutes. A test could also fail if it failed
to connect to zookeeper servers within the first 60 seconds, unfortunately the
return code did not differentiate properly between these cases. However pauses
of about 4 seconds were allowed between tests, during which all IO operations
(by the test program) were stopped. This should have allowed the system to
stabilize somewhat.
In this test the session timeout had the most significant influence on
stability (not too surprising) and the other system settings had far less
influence.
We have settled on a 60s session timeout for the moment (to achieve the
stability we need under the IO loads we are experiencing). But it would be
great if we could reduce this a bit.
> Zookeeper drops connections under moderate IO load
> --------------------------------------------------
>
> Key: ZOOKEEPER-885
> URL: https://issues.apache.org/jira/browse/ZOOKEEPER-885
> Project: Zookeeper
> Issue Type: Bug
> Components: server
> Affects Versions: 3.2.2, 3.3.1
> Environment: Debian (Lenny)
> 1Gb RAM
> swap disabled
> 100Mb heap for zookeeper
> Reporter: Alexandre Hardy
> Priority: Critical
> Attachments: benchmark.csv, tracezklogs.tar.gz, tracezklogs.tar.gz,
> WatcherTest.java, zklogs.tar.gz
>
>
> A zookeeper server under minimum load, with a number of clients watching
> exactly one node will fail to maintain the connection when the machine is
> subjected to moderate IO load.
> In a specific test example we had three zookeeper servers running on
> dedicated machines with 45 clients connected, watching exactly one node. The
> clients would disconnect after moderate load was added to each of the
> zookeeper servers with the command:
> {noformat}
> dd if=/dev/urandom of=/dev/mapper/nimbula-test
> {noformat}
> The {{dd}} command transferred data at a rate of about 4Mb/s.
> The same thing happens with
> {noformat}
> dd if=/dev/zero of=/dev/mapper/nimbula-test
> {noformat}
> It seems strange that such a moderate load should cause instability in the
> connection.
> Very few other processes were running, the machines were setup to test the
> connection instability we have experienced. Clients performed no other read
> or mutation operations.
> Although the documents state that minimal competing IO load should present on
> the zookeeper server, it seems reasonable that moderate IO should not cause
> problems in this case.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
