Re: SIGSEGV during compaction?

h, all other things remaining the same, I put jna.jar into classpath, now it successfully completed a compaction without problems On Wed, Sep 7, 2011 at 10:06 PM, Yang wrote: > thanks Jonathan. > > I tried openJdk too, same , filed bug to both Oracle and openJdk > > > tried -XX:-UseCompressed

Re: SIGSEGV during compaction?

thanks Jonathan. I tried openJdk too, same , filed bug to both Oracle and openJdk tried -XX:-UseCompressedOops , same SEGV Oracle bug site asks "does it appear with -server and -Xint", I tried these options, so far no SEGV yet, maybe slower, but haven't measured exactly On Wed, Sep 7, 2011 a

Re: SIGSEGV during compaction?

You should report a bug to Oracle. In the meantime you could try turning off compressed oops -- that's been a source of a lot of GC bugs in the past. On Wed, Sep 7, 2011 at 8:22 PM, Yang wrote: > some info in the debug file that JVM exported: > > # > # A fatal error has been detected by the Java

Re: SIGSEGV during compaction?

unfortunately tried java7, same On Wed, Sep 7, 2011 at 6:22 PM, Yang wrote: > some info in the debug file that JVM exported: > > # > # A fatal error has been detected by the Java Runtime Environment: > # > #  SIGSEGV (0xb) at pc=0x2b37cbfa, pid=7236, tid=1179806016 > # > # JRE version: 6.

Re: SIGSEGV during compaction?

some info in the debug file that JVM exported: # # A fatal error has been detected by the Java Runtime Environment: # # SIGSEGV (0xb) at pc=0x2b37cbfa, pid=7236, tid=1179806016 # # JRE version: 6.0_27-b07 # Java VM: Java HotSpot(TM) 64-Bit Server VM (20.2-b06 mixed mode linux-amd64 compre

SIGSEGV during compaction?

I started compaction using nodetool, then always reproducibly, I get a SEGV in a code that I added to the Cassandra code, which simply calls get_slice(). have you seen SEGV associated with compaction? anyone could suggest a route on how to debug this? I filed a bug on sun website, right now the o

Re: Calculate number of nodes required based on data

Adi, just to make sure my calculation is correct, the configured ops threshold is ~2m, we have 6 nodes, does that mean each node's threshold is around 300k? I do see the when flushing happens, ops is about 300k, with several 500k. Seems like the ops threshold is throttling us. On Sep 7, 2011, a

Re: Calculate number of nodes required based on data

On Wed, Sep 7, 2011 at 2:09 PM, Hefeng Yuan wrote: > We didn't change MemtableThroughputInMB/min/maxCompactionThreshold, they're > 499/4/32. > As for why we're flushing at ~9m, I guess it has to do with this: > http://thelastpickle.com/2011/05/04/How-are-Memtables-measured/ > The only parameter I

Re: Calculate number of nodes required based on data

We didn't change MemtableThroughputInMB/min/maxCompactionThreshold, they're 499/4/32. As for why we're flushing at ~9m, I guess it has to do with this: http://thelastpickle.com/2011/05/04/How-are-Memtables-measured/ The only parameter I tried to play with is the compaction_throughput_mb_per_sec,

Unable to read byte sub-column after upgrade to Cassandra 0.8

Hi, Just wanted to share an issue I had to overcome after upgrading to Cassandra 0.8 from 0.7. My app became unable to read a BytesType sub-column. It turned out that ByteBuffer returned as a value of a sub-column can not be assumed to contain only the bytes of the sub-column. As a result one has

Re: Calculate number of nodes required based on data

On Wed, Sep 7, 2011 at 1:09 PM, Hefeng Yuan wrote: > Adi, > > The reason we're attempting to add more nodes is trying to solve the > long/simultaneous compactions, i.e. the performance issue, not the storage > issue yet. > We have RF 5 and CL QUORUM for read and write, we have currently 6 nodes,

Re: Secondary index update issue

Hi, Here is my sample row. I wanted to execute below 2 queries. CF:ip 1. get ip where ip=19268678; 2. get ip where domain='google.com'; Here both ip & domain has secondary indexes. RowKey: 19268678 => (column=country, value=in, timestamp=1315398995980) => (column=domain, value=google.com, timest

Re: Task's map reading more record than CFIF's inputSplitSize

> > 3 map tasks (from 4013) is still running after read 25 million rows. > > Can this be a bug in StorageService.getSplits(..) ? > > getSplits looks pretty foolproof to me but I guess we'd need to add > more debug logging to rule out a bug there for sure. > > I guess the main alternative would b

Re: Calculate number of nodes required based on data

Adi, The reason we're attempting to add more nodes is trying to solve the long/simultaneous compactions, i.e. the performance issue, not the storage issue yet. We have RF 5 and CL QUORUM for read and write, we have currently 6 nodes, and when 4 nodes doing compaction at the same period, we're s

Re: Calculate number of nodes required based on data

On Tue, Sep 6, 2011 at 3:53 PM, Hefeng Yuan wrote: > Hi, > > Is there any suggested way of calculating number of nodes needed based on > data? > We currently have 6 nodes (each has 8G memory) with RF5 (because we want to > be able to survive loss of 2 nodes). > The flush of memtable happens arou

Re: Task's map reading more record than CFIF's inputSplitSize

getSplits looks pretty foolproof to me but I guess we'd need to add more debug logging to rule out a bug there for sure. I guess the main alternative would be a bug in the recordreader paging. On Wed, Sep 7, 2011 at 6:35 AM, Mck wrote: > Cassandra-0.8.4 w/ ByteOrderedPartitioner > > CFIF's input

Re: Any tentative data for 0.8.5 release?

On Wed, Sep 7, 2011 at 9:15 PM, Jeremy Hanna wrote: > The voting started on Monday and is a 72 hour vote. So if there aren't any > problems that people find, it should be released sometime Thursday (7 > September). > Great. Thanks for quick info. Looking forward to it. -- Roshan Blog: http://

Re: Any tentative data for 0.8.5 release?

The voting started on Monday and is a 72 hour vote. So if there aren't any problems that people find, it should be released sometime Thursday (7 September). On Sep 7, 2011, at 10:41 AM, Roshan Dawrani wrote: > Hi, > > Quick check: is there a tentative date for release of Cassandra 0.8.5? > >

Any tentative data for 0.8.5 release?

Hi, Quick check: is there a tentative date for release of Cassandra 0.8.5? Thanks. -- Roshan Blog: http://roshandawrani.wordpress.com/ Twitter: @roshandawrani Skype: roshandawrani

Re: Cassandra 0.8.4 - doesn't support defining keyspaces in cassandra.yaml?

On Wed, Sep 7, 2011 at 7:27 PM, Jonathan Ellis wrote: > No, the "load from yaml" was only supported for upgrading from 0.6. > You'd need to create the schema programatically instead. > Thanks for confirming. I am now creating my keyspace programmatically, but running into another small cassandra

Re: Secondary index update issue

My guess would be you're querying using a different encoding and there really is no data for your query as given. Hard to say without more details. On Wed, Sep 7, 2011 at 8:13 AM, Thamizh wrote: > > Hi All, > > I have created KS & CF using cassandra-0.7.8 and inserted some rows and > column val

Re: Cassandra 0.8.4 - doesn't support defining keyspaces in cassandra.yaml?

No, the "load from yaml" was only supported for upgrading from 0.6. You'd need to create the schema programatically instead. On Wed, Sep 7, 2011 at 12:27 AM, Roshan Dawrani wrote: > Hi, > I have just started the process of upgrading Cassandra from 0.7.2 to 0.8.4, > and I am facing some issues wit

Secondary index update issue

Hi All, I have created KS & CF using cassandra-0.7.8 and inserted some rows and column values(around 1000 rows). Later, I wanted to index 2 column values. So, I issued 'update column family..' command. After, when I query based on indexed value it says "Row does not found". After indexing 1. Iss

Re: CQL and schema-less column family

Thank you very much Eric for your response. Some follow-up questions come to mind: 1. What will be the performance hit for querying a coulmn name not predefined in a schema? if it's not indexed, then I guess Cassandra will have to iterate all rows,which will impose huge overhead. 2. Assuming my g

Task's map reading more record than CFIF's inputSplitSize

Cassandra-0.8.4 w/ ByteOrderedPartitioner CFIF's inputSplitSize=196608 3 map tasks (from 4013) is still running after read 25 million rows. Can this be a bug in StorageService.getSplits(..) ? With this data I've had general headache with using tokens that are longer than usual (and trying to mo

Re: CQL and schema-less column family

On Tue, Sep 6, 2011 at 12:22 PM, osishkin osishkin wrote: > Sorry for the newbie question but I failed to find a clear answer. > Can CQL be used to query a schema-less column family? can they be indexed? > That is, query for column names that do not necessarily exist in all > rows, and were not de