Thanks for the advice, Maki, especially on the ulimit! Yes, we will play with the configuration and figure out some optimal sstable size.
LeveledCompaction will use less disk space(load), but need more IO.If your traffic is too high for your disk, you will have many pending compaction tasks, and large number of sstables which wait to be compacted.Also the default sstable_size_in_mb (5MB) will be too small for large data set. You should better to have test iteration with different size configuration.Don't forget to unlimit number of file descriptors, and monitor tpstats and iostat.maki
On 2012/04/04, at 22:19, Yiming Sun <firstname.lastname@example.org> wrote:
Cool, I will look into this new leveled compaction strategy and give it a try.BTW, Aaron, I think the last word of your message meant to say "compression", correct?-- Y.On Mon, Apr 2, 2012 at 9:37 PM, aaron morton <email@example.com> wrote:If you have a workload with overwrites you will end up with some data needing compaction. Running a nightly manual compaction would remove this, but it will also soak up some IO so it may not be the best solution.I do not know if Leveled compaction would result in a smaller disk load for the same workload.I agree with other people, turn on compaction.CheersOn 3/04/2012, at 9:19 AM, Yiming Sun wrote:Yup Jeremiah, I learned a hard lesson on how cassandra behaves when it runs out of disk space :-S. I didn't try the compression, but when it ran out of disk space, or near running out, compaction would fail because it needs space to create some tmp data files.I shall get a tatoo that says keep it around 50% -- this is valuable tip.-- Y.On Sun, Apr 1, 2012 at 11:25 PM, Jeremiah Jordan <JEREMIAH.JORDAN@morningstar.com> wrote:
Is that 80% with compression? If not, the first thing to do is turn on compression. Cassandra doesn't behave well when it runs out of disk space. You really want to try and stay around 50%, 60-70% works, but only if it is spread across multiple column families, and even then you can run into issues when doing repairs.
On Apr 1, 2012, at 9:44 PM, Yiming Sun wrote:
Thanks Aaron. Well I guess it is possible the data files from sueprcolumns could've been reduced in size after compaction.
This bring yet another question. Say I am on a shoestring budget and can only put together a cluster with very limited storage space. The first iteration of pushing data into cassandra would drive the disk usage up into the 80% range. As time goes by, there will be updates to the data, and many columns will be overwritten. If I just push the updates in, the disks will run out of space on all of the cluster nodes. What would be the best way to handle such a situation if I cannot to buy larger disks? Do I need to delete the rows/columns that are going to be updated, do a compaction, and then insert the updates? Or is there a better way? Thanks
On Sat, Mar 31, 2012 at 3:28 AM, aaron morton <firstname.lastname@example.org> wrote:
No.does cassandra 1.0 perform some default compression?The on disk size depends to some degree on the work load.
If there are a lot of overwrites or deleted you may have rows/columns that need to be compacted. You may have some big old SSTables that have not been compacted for a while.
There is some overhead involved in the super columns: the super col name, length of the name and the number of columns.
On 29/03/2012, at 9:47 AM, Yiming Sun wrote:
Actually, after I read an article on cassandra 1.0 compression just now ( http://www.datastax.com/dev/blog/whats-new-in-cassandra-1-0-compression), I am more puzzled. In our schema, we didn't specify any compression options -- does cassandra 1.0 perform some default compression? or is the data reduction purely because of the schema change? Thanks.
On Wed, Mar 28, 2012 at 4:40 PM, Yiming Sun <email@example.com> wrote:
We are trying to estimate the amount of storage we need for a production cassandra cluster. While I was doing the calculation, I noticed a very dramatic difference in terms of storage space used by cassandra data files.
Our previous setup consists of a single-node cassandra 0.8.x with no replication, and the data is stored using supercolumns, and the data files total about 534GB on disk.
A few weeks ago, I put together a cluster consisting of 3 nodes running cassandra 1.0 with replication factor of 2, and the data is flattened out and stored using regular columns. And the aggregated data file size is only 488GB (would be 244GB if no replication).
This is a very dramatic reduction in terms of storage needs, and is certainly good news in terms of how much storage we need to provision. However, because of the dramatic reduction, I also would like to make sure it is absolutely correct before submitting it - and also get a sense of why there was such a difference. -- I know cassandra 1.0 does data compression, but does the schema change from supercolumn to regular column also help reduce storage usage? Thanks.