cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Paulo Motta <pauloricard...@gmail.com>
Subject Re: Effect of adding/removing nodes from cassandra
Date Wed, 16 Sep 2015 19:54:18 GMT
I don't see a problem with high cpu utilization on the bootstrapping node,
since it will only serve data after the bootstrap process is complete. I
think streaming is a cpu-intensive process on the receiving node because
there is lots of reading from socket and writing to memory buffers (as well
as allocation and deallocation) and also indexes, stats and metadata
creation during sstable writing process.

I'm curious about the difference in cpu utilization from node1 and node2
though. Did you perform any pre-warming with node1 before performing the
bootstrap? It seems data was somehow cached on node1 but not on node2.
Could you perform the experiment again with similar conditions from node1
and node2?  Maybe shutdown both nodes and clear operating system file cache
before performing bootstrap.

I'm more concerned about the bandwidth cap of 5MB/s though, specially since
you're not running on EC2. Are there any other network processes running?
Could you try to measure your network bandwidth between nodes to ensure
there's nothing capping the bandwidth on your network?

2015-09-16 5:58 GMT-03:00 Alain RODRIGUEZ <arodrime@gmail.com>:

> Hi again Aadil,
>
> I just had a quick look, as I don't really know the C* code, you can check
> that as well as I do (maybe even better), but I found this, it might be a
> good place to start having a look -->
> https://github.com/apache/cassandra/blob/trunk/src/java/org/apache/cassandra/streaming/ConnectionHandler.java
>
> Yet I am not a Cassandra commiter. maybe would you have more luck asking
> there --> dev@cassandra.apache.org (to subscribe send a message to
> dev-subscribe@cassandra.apache.org)
>
> Plus it might be interesting for people there to see that bootstrap (and
> streaming stuff) uses that much CPU.
>
> My 2 cents,
>
> C*heers,
>
> Alain
>
>
> 2015-09-15 0:55 GMT+02:00 Ahamed, Aadil <aahamed@akamai.com>:
>
>> Hi,
>> I just wanted to resubmit this post in case it didn’t go through.
>>
>> I used the sjk jvm-tool: https://github.com/aragozin/jvm-tools
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_aragozin_jvm-2Dtools&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=rzUSlUgnPe1HeHl5iM4Uktrz2KExlXdNyNMmgcnQlus&e=>
to
>> profile a Cassandra node being added to the cluster.
>> I ran the profiler using this command: java –jar sjk.jar ttop –s
>> localhost:7199 –o CPU –n 25
>> Here is a snapshot of the profiler when CPU Usage was highest:
>>
>>
>> As Alain hypothesized in a previous email handling the threads
>> responsible for handling the streams take up quite a bit of CPU. Is there
>> any way I can use this thread name STREAM-IN-/198.18.71.134 to figure
>> out where it is implemented in the source code or why it is using so much
>> CPU?
>>
>> Thanks for your patience,
>> Aadil
>>
>> From: Aadil Ahamed
>> Reply-To: "user@cassandra.apache.org"
>> Date: Friday, September 11, 2015 at 11:28 AM
>>
>> To: "user@cassandra.apache.org"
>> Subject: Re: Effect of adding/removing nodes from cassandra
>>
>> Hi,
>>
>> I used the sjk jvm-tool: https://github.com/aragozin/jvm-tools
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_aragozin_jvm-2Dtools&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=rzUSlUgnPe1HeHl5iM4Uktrz2KExlXdNyNMmgcnQlus&e=>
to
>> profile a Cassandra node being added to the cluster.
>> I ran the profiler using this command: java –jar sjk.jar ttop –s
>> localhost:7199 –o CPU –n 25
>> Here is a snapshot of the profiler when CPU Usage was highest:
>>
>>
>> As Alain hypothesized in a previous email handling the threads
>> responsible for handling the streams take up quite a bit of CPU. Is there
>> any way I can use this thread name STREAM-IN-/198.18.71.134 to figure
>> out where it is implemented in the source code or why it is using so much
>> CPU?
>>
>> Thanks,
>> Aadil
>>
>>
>> From: Aadil Ahamed
>> Reply-To: "user@cassandra.apache.org"
>> Date: Tuesday, September 8, 2015 at 10:41 AM
>> To: "user@cassandra.apache.org"
>> Subject: Re: Effect of adding/removing nodes from cassandra
>>
>> Hi,
>>
>> I am actually very interested in taking a look at the source code. Are
>> you aware of which file(s) are responsible for the bootstrap process?
>>
>> As for how I am measuring CPU & Network I/O:
>> I am using an open source python package called psutil
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__pythonhosted.org_psutil_&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=rZEjxqj6GvMRb_vTnClwVDC4bHb1CecRqRhKsBIchR0&e=>.
>> This package contains a library of functions for querying system related
>> information like cpu and network I/O.
>>
>> Specifically I use these functions:
>>  psutil.cpu_percent() - get average cpu utilization across all cores as a
>> percentage
>>  psutil.net_io_counters().bytes_sent – get number of bytes sent over the
>> network
>>  psutil.net_io_counters().bytes_recv  – get number of bytes received
>> over the network
>>
>> Also, thanks for linking the jvm tool
>> https://github.com/aragozin/jvm-tools
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_aragozin_jvm-2Dtools&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=rzUSlUgnPe1HeHl5iM4Uktrz2KExlXdNyNMmgcnQlus&e=>.
>> It seems like it could be really helpful. I will run it and let you know of
>> the results.
>>
>> Thanks,
>> Aadil
>>
>> From: Edouard COLE <Edouard.COLE@rgsystem.com>
>> Reply-To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>> Date: Monday, September 7, 2015 at 8:54 AM
>> To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>> Subject: RE: Effect of adding/removing nodes from cassandra
>>
>> Hi,
>>
>> Could you show us how you measure CPU & network?
>>
>> Just to be sure we're not missing something obvious
>>
>> Thanks,
>>
>>
>>
>> De : Alain RODRIGUEZ [mailto:arodrime@gmail.com <arodrime@gmail.com>]
>> Envoyé : Monday, September 07, 2015 5:19 PM
>> À : user@cassandra.apache.org
>> Objet : Re: Effect of adding/removing nodes from cassandra
>>
>> Hi, sorry I have been quite busy and was hopping that someone else could
>> answer about CPU, as told I never went that deep.
>>
>> "But if there were in fact 5 nodes then the max throughput per node would
>> be capped at 25/5 = 5MB/s"
>> This is wrong imho. Stream are globally capped, independently of the
>> total nimber of node, at any time. I mean, output of each node is capped to
>> 200 Mb, no matter you node number, so you can always reach this 200 Mb
>> theoretically, even if streaming to one node.
>> Yet I know that bandwidth is not often the bottleneck lately, something
>> else is, not sure what, you might want to "watch" this issue
>> https://issues.apache.org/jira/browse/CASSANDRA-9766
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__issues.apache.org_jira_browse_CASSANDRA-2D9766&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=yadwfhjjbxHQWUkBUccKWqJ-kyHQuKAcsLo_n25bf2Y&e=>
>> .
>>
>> About cpu, if this is not due to Compactions then I have no ideas of what
>> is happening exactly. Yet, you might want to use
>> https://github.com/aragozin/jvm-tools
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_aragozin_jvm-2Dtools&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=rzUSlUgnPe1HeHl5iM4Uktrz2KExlXdNyNMmgcnQlus&e=>
>> to find this out. Running something like "java -jar sjk-plus-0.3.6.jar ttop
>> -s localhost:7199 -o CPU -n 30" would probably help.
>>
>> About “handling all the streams” it was to say something. I have no idea
>> what happen in there but there a little work to handle streams and write
>> data... Yet this should not be 20 %, unless your CPU are
>> ridiculously inefficient / old imho.
>>
>> I have no knowledge of a documentation describing the bootstrap process.
>> I use Datastax docs a lot (
>> http://docs.datastax.com/en/cassandra/2.1/cassandra/gettingStartedCassandraIntro.html
>> <https://urldefense.proofpoint.com/v2/url?u=http-3A__docs.datastax.com_en_cassandra_2.1_cassandra_gettingStartedCassandraIntro.html&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=X78V1Bp5RTzK7I8ZR2aJMwstzlP_DlHPSxRCt2XKAIU&e=>)
>> but I don't think they go that deep, it is more a user guide than a
>> technical description. You might want to have a look at the code...
>>
>> Please keep us posted, your work is interesting (plus linked to some
>> recent issues about over throttled bootstraps).
>>
>> C*heers,
>>
>> Alain
>>
>> 2015-09-02 22:33 GMT+02:00 Ahamed, Aadil <aahamed@akamai.com>:
>> Hi Alain,
>>
>> Thank you for your prompt and detailed response. I found it very helpful.
>> As for your questions:- I am interning at Akamai. I can’t say too much
>> about the use case but we are looking at Cassandra as an option to serve
>> large volumes of sustained data.
>>
>> My Cassandra version is:  2.1.7 (thanks for the tip)
>>
>> As a follow up to your response:
>>
>> Stream Throughput
>> I ran nodetool getstreamthroughput and the output was 200Mb/s = 25 MB/s
>> so it is weird that my throughput is capped at 5MB/s. However, I do have a
>> guess for why this is occurring – Initially I had a 5 node cluster but I
>> decommissioned 2 nodes for the purpose of this test. But if there were in
>> fact 5 nodes then the max throughput per node would be capped at 25/5 =
>> 5MB/s. Based on the issue you raised it does not look like Cassandra can
>> adapt the per node streaming throughput (5MB/s) to take full advanatage of
>> the total stream throughput (25 MB/s). This still raises the question: Why
>> isn’t the per node stream throughput changed to 25/3 = 8.33MB/s after 2
>> nodes are decommissioned from the 5 node cluster? Does it have something to
>> do with  Cassandra expecting decommissioned nodes to rejoin the cluster
>> eventually? Of course, my guess could be wrong and the problem could be a
>> result of a completely different issue.
>>
>> CPU usage for Bootstrapping
>> I have tried adding nodes with auto-compaction disabled (nodetool
>> disableautocompaction) and it still results in similar amounts of cpu usage
>> so I don’t think compaction is the main cause. In addition, you said that
>>  handling all the stream also consume CPU. Could you explain a little more
>> on what you mean by “handling all the streams”?. Also, if you know any
>> sites/documents that have more in depth information about the bootstrap
>> process please let me know.
>>
>> Thanks again for your help. I really appreciate it.
>> Aadil
>>
>>
>>
>> From: Alain RODRIGUEZ <arodrime@gmail.com>
>> Reply-To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>> Date: Tuesday, September 1, 2015 at 5:26 AM
>> To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>> Subject: Re: Effect of adding/removing nodes from cassandra
>>
>> Hi Aadil, and welcome then !
>> Graph for initial node 1, 2:
>> 1. You can set "stream_throughput_outbound_megabits_per_sec" in
>> cassandra.yaml configuration for permanent change. The point here is not to
>> take all the bandwidth while adding a node to let transactional network to
>> run as normally as possible. Also look at "nodetool setstreamthroughput"
>> (and "getstreamthroughput") if you want to adjust during an operation
>> without restarting the node. This will be overridden on node restart, back
>> to the value  in the cassandra.yaml
>> This limit the outgoing traffic, meaning that this will increase for each
>> node you add, if using vnodes, on certain operations like repair,
>> removenode, ... You might want to take this into consideration. I created a
>> not very popular issue about this, at least I detail the issue there -->
>> https://issues.apache.org/jira/browse/CASSANDRA-9509
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__issues.apache.org_jira_browse_CASSANDRA-2D9509&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=C7uRF8x-FbxnIB46zhjNo0YXGg9liM2sDKS6M8U5GS4&e=>.
>> In your exemple see that you receive 2 * 5 = 10 MB/s, then one node
>> finishes, and you keep receiving 5 MB/s.
>> Though, default is 200 Mbps (25 MB) , not sure why you are limited to 5
>> MB there, unless you changed this or I miscalculated something, this use to
>> happen to me :D... Also maybe something relative to
>> https://issues.apache.org/jira/browse/CASSANDRA-9766
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__issues.apache.org_jira_browse_CASSANDRA-2D9766&d=BQMF-g&c=96ZbZZcaMF4w0F4jpN6LZg&r=IPrliSk1Ijg-U4peH4IIW6Lcj4i6GMuxpxu3zDH-l0w&m=bZUdJplcHM5O0utN6k29Q7-osMmhK8tYqLUvl_xhTFg&s=yadwfhjjbxHQWUkBUccKWqJ-kyHQuKAcsLo_n25bf2Y&e=>
>> (btw, ou might want to add your version of Cassandra when posting, it would
>> be easier to point you to known bugs or to the right options etc)
>> Graph for added node:
>> 1. Adding a node is CPU intensive I guess it is mainly because you have
>> to compact all the data you accumulated quite fast on the bootstrapping
>> node (maybe there is more reason, other people might explain this better, I
>> never needed to go that deep, I imagine handling all the stream also
>> consume CPU)
>> 2. You partially answered yourself, one node ended streaming. The other
>> half of the question, about the reason why the other node don't send more
>> data is explained above. Limitations are on outgoing traffic, so this looks
>> normal to me.
>> The only weird thing to me is the threshold of you streaming throughput,
>> unless you changed it.
>> Btw, I am very curious, please feel free not to answer this if you are
>> under a NDA or whatever. Are you working for Akamai ? What's your use case
>> for Cassandra ?
>> Hope this will help !
>> C*heers,
>> Alain
>>
>> Hi,
>>
>> This is my first post to this mailing list so I want to apologize in
>> advance if I break any rules or guidelines. I have also inserted images of
>> graphs and I am not sure if they will show up. Please let me know if I can
>> improve my post in any way.
>>
>> I am investigating the effect of adding and removing nodes from a
>> Cassandra cluster by collecting metrics on cpu utilization, memory usage
>> etc.
>> Basically I want to have a quantitative measurement of how intensive the
>> add/remove operation is so we know what to expect when
>> increasing/decreasing capacity on our production cluster.
>> I wrote a tool to measure this effect but I need help interpreting the
>> data I have collected.
>>
>> Here is a sample testcase:
>>
>> Relevant Machine Information:
>> Logical cores: 8
>> Core model: Intel Xeon(R) CPU E31270 @ 3.4GHz
>> RAM: 16GB
>> Non-Volatile storage: Hard Disk
>>
>> Test Info:
>> Keyspace: Simple strategy with replication factor 2
>> Initial no. of nodes on cluster: 2 [198.18.71.132, 198.18.71.133]
>> Initial load on each node: 30GB
>> No. of added nodes: 1 [198.18.71.134]
>> Final load on each node: 18GB
>>
>> *The x-axis for all graphs is in seconds
>>
>> Graph for initial node 1:
>>
>>
>>
>> Graph for initial node 2:
>>
>>
>>
>> Graph for added node:
>>
>>
>>
>> Here are my questions:
>>
>> Graph for initial node 1, 2:
>>
>> 1. Why is the KBytes/s sent over the network stay constant at around
>> ~5000 KB/s? Can I change it to something higher?
>>
>> Graph for added node:
>>
>> 1.  Why is the cpu usage so high?
>> It is close to 30% for ~800 seconds and 10% for another 400 seconds. I
>> did not expect the cpu usage to be this high and I did not expect it to
>> stay high for such a long period of time. Based on my understanding the
>> only cpu intensive process during bootstrap is token range recalculation.
>> However, based on the graph the cpu usage seems to be proportional to the
>> amount of data that is streamed to the node at any given moment in time.
>>
>> 2. Why does the Kbytes/s received over the network drop from - ~10000 ->
>> ~5000  - at around 800 seconds?
>> I can see that initial node 1 stops streaming data at around 800 seconds
>> but why does initial node 2 not bump up its outgoing rate of transfer?
>>
>>
>> Thanks for your help,
>> Aadil
>>
>>
>>
>>
>

Mime
View raw message