incubator-cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ilya Maykov <ivmay...@gmail.com>
Subject Re: Overwhelming a cluster with writes?
Date Tue, 06 Apr 2010 06:48:47 GMT
No, the disks on all nodes have about 750GB free space. Also as
mentioned in my follow-up email, writing with ConsistencyLevel.ALL
makes the slowdowns / crashes go away.

-- Ilya

On Mon, Apr 5, 2010 at 11:46 PM, Ran Tavory <rantav@gmail.com> wrote:
> Do you see one of the disks used by cassandra filled up when a node crashes?
>
> On Tue, Apr 6, 2010 at 9:39 AM, Ilya Maykov <ivmaykov@gmail.com> wrote:
>>
>> I'm running the nodes with a JVM heap size of 6GB, and here are the
>> related options from my storage-conf.xml. As mentioned in the first
>> email, I left everything at the default value. I briefly googled
>> around for "Cassandra performance tuning" etc but haven't found a
>> definitive guide ... any help with tuning these parameters is greatly
>> appreciated!
>>
>>  <DiskAccessMode>auto</DiskAccessMode>
>>  <RowWarningThresholdInMB>512</RowWarningThresholdInMB>
>>  <SlicedBufferSizeInKB>64</SlicedBufferSizeInKB>
>>  <FlushDataBufferSizeInMB>32</FlushDataBufferSizeInMB>
>>  <FlushIndexBufferSizeInMB>8</FlushIndexBufferSizeInMB>
>>  <ColumnIndexSizeInKB>64</ColumnIndexSizeInKB>
>>  <MemtableThroughputInMB>64</MemtableThroughputInMB>
>>  <BinaryMemtableThroughputInMB>256</BinaryMemtableThroughputInMB>
>>  <MemtableOperationsInMillions>0.3</MemtableOperationsInMillions>
>>  <MemtableFlushAfterMinutes>60</MemtableFlushAfterMinutes>
>>  <ConcurrentReads>8</ConcurrentReads>
>>  <ConcurrentWrites>64</ConcurrentWrites>
>>  <CommitLogSync>periodic</CommitLogSync>
>>  <CommitLogSyncPeriodInMS>10000</CommitLogSyncPeriodInMS>
>>  <GCGraceSeconds>864000</GCGraceSeconds>
>>
>> -- Ilya
>>
>> On Mon, Apr 5, 2010 at 11:26 PM, Boris Shulman <shulmanb@gmail.com> wrote:
>> > You are running out of memory on your nodes. Before the final crash
>> > your nodes are probably slow  due to GC. What is your memtable size?
>> > What cache options did you configure?
>> >
>> > On Tue, Apr 6, 2010 at 7:31 AM, Ilya Maykov <ivmaykov@gmail.com> wrote:
>> >> Hi all,
>> >>
>> >> I've just started experimenting with Cassandra to get a feel for the
>> >> system. I've set up a test cluster and to get a ballpark idea of its
>> >> performance I wrote a simple tool to load some toy data into the
>> >> system. Surprisingly, I am able to "overwhelm" my 4-node cluster with
>> >> writes from a single client. I'm trying to figure out if this is a
>> >> problem with my setup, if I'm hitting bugs in the Cassandra codebase,
>> >> or if this is intended behavior. Sorry this email is kind of long,
>> >> here is the TLDR version:
>> >>
>> >> While writing to Cassandra from a single node, I am able to get the
>> >> cluster into a bad state, where nodes are randomly disconnecting from
>> >> each other, write performance plummets, and sometimes nodes even
>> >> crash. Further, the nodes do not recover as long as the writes
>> >> continue (even at a much lower rate), and sometimes do not recover at
>> >> all unless I restart them. I can get this to happen simply by throwing
>> >> data at the cluster fast enough, and I'm wondering if this is a known
>> >> issue or if I need to tweak my setup.
>> >>
>> >> Now, the details.
>> >>
>> >> First, a little bit about the setup:
>> >>
>> >> 4-node cluster of identical machines, running cassandra-0.6.0-rc1 with
>> >> the fixes for CASSANDRA-933, CASSANDRA-934, and CASSANDRA-936 patched
>> >> in. Node specs:
>> >> 8-core Intel Xeon E5405@2.00GHz
>> >> 8GB RAM
>> >> 1Gbit ethernet
>> >> Red Hat Linux 2.6.18
>> >> JVM 1.6.0_19 64-bit
>> >> 1TB spinning disk houses both commitlog and data directories (which I
>> >> know is not ideal).
>> >> The client machine is on the same local network and has very similar
>> >> specs.
>> >>
>> >> The cassandra nodes are started with the following JVM options:
>> >>
>> >> ./cassandra JVM_OPTS="-Xms6144m -Xmx6144m -XX:+UseConcMarkSweepGC -d64
>> >> -XX:NewSize=1024m -XX:MaxNewSize=1024m -XX:+DisableExplicitGC"
>> >>
>> >> I'm using default settings for all of the tunable stuff at the bottom
>> >> of storage-conf.xml. I also selected my initial tokens to evenly
>> >> partition the key space when the cluster was bootstrapped. I am using
>> >> the RandomPartitioner.
>> >>
>> >> Now, about the test. Basically I am trying to get an idea of just how
>> >> fast I can make this thing go. I am writing ~250M data records into
>> >> the cluster, replicated at 3x, using Ran Tavory's Hector client
>> >> (Java), writing with ConsistencyLevel.ZERO and
>> >> FailoverPolicy.FAIL_FAST. The client is using 32 threads with 8
>> >> threads talking to each of the 4 nodes in the cluster. Records are
>> >> identified by a numeric id, and I'm writing them in batches of up to
>> >> 10k records per row, with each record in its own column. The row key
>> >> identifies the bucket into which records fall. So, records with ids 0
>> >> - 9999 are written to row "0", 10000 - 19999 are written to row
>> >> "10000", etc. Each record is a JSON object with ~10-20 fields.
>> >>
>> >> Records: {  // Column Family
>> >>   0 : {  // row key for the start of the bucket. Buckets span a range
>> >> of up to 10000 records
>> >>     1 : "{ /* some JSON */ }",  // Column for record with id=1
>> >>     3 : "{ /* some more JSON */ }",  // Column for record with id=3
>> >>    ...
>> >>    9999 : "{ /* ... */ }"
>> >>   },
>> >>  10000 : {  // row key for the start of the next bucket
>> >>    10001 : ...
>> >>    10004 :
>> >> }
>> >>
>> >> I am reading the data out of a local, sorted file on the client, so I
>> >> only write a row to Cassandra once all records for that row have been
>> >> read, and each row is written to exactly once. I'm using a
>> >> producer-consumer queue to pump data from the input reader thread to
>> >> the output writer threads. I found that I have to throttle the reader
>> >> thread heavily in order to get good behavior. So, if I make the reader
>> >> sleep for 7 seconds every 1M records, everything is fine - the data
>> >> loads in about an hour, half of which is spent by the reader thread
>> >> sleeping. In between the sleeps, I see ~40-50 MB/s throughput on the
>> >> client's network interface while the reader is not sleeping, and it
>> >> takes ~7-8 seconds to write each batch of 1M records.
>> >>
>> >> Now, if I remove the 7 second sleeps on the client side, things get
>> >> bad after the first ~8M records are written to the client. Write
>> >> throughput drops to <5 MB/s. I start seeing messages about nodes
>> >> disconnecting and reconnecting in Cassandra's system.log, as well as
>> >> lots of GC messages:
>> >>
>> >> ...
>> >>  INFO [Timer-1] 2010-04-06 04:03:27,178 Gossiper.java (line 179)
>> >> InetAddress /10.15.38.88 is now dead.
>> >>  INFO [GC inspection] 2010-04-06 04:03:30,259 GCInspector.java (line
>> >> 110) GC for ConcurrentMarkSweep: 2989 ms, 55326320 reclaimed leaving
>> >> 1035998648 used; max is 1211170816
>> >>  INFO [GC inspection] 2010-04-06 04:03:41,838 GCInspector.java (line
>> >> 110) GC for ConcurrentMarkSweep: 3004 ms, 24377240 reclaimed leaving
>> >> 1066120952 used; max is 1211170816
>> >>  INFO [Timer-1] 2010-04-06 04:03:44,136 Gossiper.java (line 179)
>> >> InetAddress /10.15.38.55 is now dead.
>> >>  INFO [GMFD:1] 2010-04-06 04:03:44,138 Gossiper.java (line 568)
>> >> InetAddress /10.15.38.55 is now UP
>> >>  INFO [GC inspection] 2010-04-06 04:03:52,957 GCInspector.java (line
>> >> 110) GC for ConcurrentMarkSweep: 2319 ms, 4504888 reclaimed leaving
>> >> 1086023832 used; max is 1211170816
>> >>  INFO [Timer-1] 2010-04-06 04:04:19,508 Gossiper.java (line 179)
>> >> InetAddress /10.15.38.242 is now dead.
>> >>  INFO [Timer-1] 2010-04-06 04:05:03,039 Gossiper.java (line 179)
>> >> InetAddress /10.15.38.55 is now dead.
>> >>  INFO [GMFD:1] 2010-04-06 04:05:03,041 Gossiper.java (line 568)
>> >> InetAddress /10.15.38.55 is now UP
>> >>  INFO [GC inspection] 2010-04-06 04:05:08,539 GCInspector.java (line
>> >> 110) GC for ConcurrentMarkSweep: 2375 ms, 39534920 reclaimed leaving
>> >> 1051620856 used; max is 1211170816
>> >> ...
>> >>
>> >> Finally followed by this and some/all nodes going down:
>> >>
>> >> ERROR [COMPACTION-POOL:1] 2010-04-06 04:05:05,475
>> >> DebuggableThreadPoolExecutor.java (line 94) Error in executor
>> >> futuretask
>> >> java.util.concurrent.ExecutionException: java.lang.OutOfMemoryError:
>> >> Java heap space
>> >>        at java.util.concurrent.FutureTask$Sync.innerGet(Unknown Source)
>> >>        at java.util.concurrent.FutureTask.get(Unknown Source)
>> >>        at
>> >> org.apache.cassandra.concurrent.DebuggableThreadPoolExecutor.afterExecute(DebuggableThreadPoolExecutor.java:86)
>> >>        at
>> >> org.apache.cassandra.db.CompactionManager$CompactionExecutor.afterExecute(CompactionManager.java:582)
>> >>        at
>> >> java.util.concurrent.ThreadPoolExecutor$Worker.runTask(Unknown Source)
>> >>        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown
>> >> Source)
>> >>        at java.lang.Thread.run(Unknown Source)
>> >> Caused by: java.lang.OutOfMemoryError: Java heap space
>> >>        at java.util.Arrays.copyOf(Unknown Source)
>> >>        at java.io.ByteArrayOutputStream.write(Unknown Source)
>> >>        at java.io.DataOutputStream.write(Unknown Source)
>> >>        at
>> >> org.apache.cassandra.io.IteratingRow.echoData(IteratingRow.java:69)
>> >>        at
>> >> org.apache.cassandra.io.CompactionIterator.getReduced(CompactionIterator.java:138)
>> >>        at
>> >> org.apache.cassandra.io.CompactionIterator.getReduced(CompactionIterator.java:1)
>> >>        at
>> >> org.apache.cassandra.utils.ReducingIterator.computeNext(ReducingIterator.java:73)
>> >>        at
>> >> com.google.common.collect.AbstractIterator.tryToComputeNext(AbstractIterator.java:135)
>> >>        at
>> >> com.google.common.collect.AbstractIterator.hasNext(AbstractIterator.java:130)
>> >>        at
>> >> org.apache.commons.collections.iterators.FilterIterator.setNextObject(FilterIterator.java:183)
>> >>        at
>> >> org.apache.commons.collections.iterators.FilterIterator.hasNext(FilterIterator.java:94)
>> >>        at
>> >> org.apache.cassandra.db.CompactionManager.doCompaction(CompactionManager.java:299)
>> >>        at
>> >> org.apache.cassandra.db.CompactionManager$1.call(CompactionManager.java:102)
>> >>        at
>> >> org.apache.cassandra.db.CompactionManager$1.call(CompactionManager.java:1)
>> >>        at java.util.concurrent.FutureTask$Sync.innerRun(Unknown Source)
>> >>        at java.util.concurrent.FutureTask.run(Unknown Source)
>> >>        ... 3 more
>> >>
>> >> At first I thought that with ConsistencyLevel.ZERO I must be doing
>> >> async writes so Cassandra can't push back on the client threads (by
>> >> blocking them), thus the server is getting overwhelmed. But, I would
>> >> expect it to start dropping data and not crash in that case (after
>> >> all, I did say ZERO so I can't expect any reliability, right?).
>> >> However, I see similar slowdown / node dropout behavior when I set the
>> >> consistency level to ONE. Does Cassandra push back on writers under
>> >> heavy load? Is there some magic setting I need to tune to have it not
>> >> fall over? Do I just need a bigger cluster? Thanks in advance,
>> >>
>> >> -- Ilya
>> >>
>> >> P.S. I realize that it's still handling a LOT of data with just 4
>> >> nodes, and in practice nobody would run a system that gets 125k writes
>> >> per second on top of a 4 node cluster. I was just surprised that I
>> >> could make Cassandra fall over at all using a single client that's
>> >> pumping data at 40-50 MB/s.
>> >>
>> >
>
>

Mime
View raw message