Re: sstable count=0, why nodetool ring is not 0

2011-12-07 Thread 祝海通
I count the disk usage. I found that from nodetool information, space used (live) is about the nodetool ring info. space used(total) is about the disk usage. thx On Thu, Dec 8, 2011 at 9:53 AM, 祝海通 wrote: > > We are testing the the performance of Cassandra for Big Data. Now I also > have the p

Re: sstable count=0, why nodetool ring is not 0

2011-12-07 Thread 祝海通
We are testing the the performance of Cassandra for Big Data. Now I also have the problem. From nodetool cfstats, the space used (live) is 7 times than the Space used (total). Why? thx On Wed, Dec 7, 2011 at 5:58 PM, Dotan N. wrote: > Hi, > What kind of process did you use for loading 400GB of

Re: sstable count=0, why nodetool ring is not 0

2011-12-07 Thread Dotan N.
Hi, What kind of process did you use for loading 400GB of data? Thanks -- Dotan, @jondot On Wed, Dec 7, 2011 at 5:57 AM, 祝海通 wrote: > hi,all > > We are using Cassandra 1.0.2. I am testing the TTL with loading 400G. > When all the data are expired, I waited for some

Re: sstable count=0, why nodetool ring is not 0

2011-12-07 Thread 祝海通
in the Cassandra wiki, I found this " ColumnFamilyStoreMBean exposes sstable space used as getLiveDiskSpaceUsed (only includes size of non-obsolete files) and getTotalDiskSpaceUsed (includes everything)." maybe this is the answer. On Wed, Dec 7, 2011 at 11:57 AM, 祝海通 wrote: > hi,all > > We are