> >> worst case is 2 or 3, depending on row size:
> >>
> >> one seek to read the right row index block
> >> one seek to read the row header (bloom filter + column index)
> >> if it's a big row, one seek to read the column block (block size is
> >> configurable, default is 256KB)
> >
> > [This is al
> > What if we have 10B rows in the column family? What sort of index do you
> use
> > that would only require one iop to find the row index block?
>
> basically what is described in sections 5.3 and 5.4 here:
> http://labs.google.com/papers/bigtable.html
>
Incorrect. Section 4 of the paper descri
> If I have 10B rows in my CF, and I can fit 10k rows per
> > SStable, and the SStables are spread across 5 nodes, and I have 1 bloom
> > filter false positive and 1 tombstone and ask the wrong node for the key,
> > then:
> >
> > Mv = (((2B/10k)+1+1)*3)+1 == ((200,000)+2)*3+1 == 300,007 iops to rea
This sounds similar to /proc/sys/vm/swappiness misconfiguration. Is it zero
or close to zero? If setting it 0 solves your problem, make sure all your
nodes get this:
/etc/sysctl.conf:
vm.swappiness=0
On Wed, Apr 28, 2010 at 12:12 PM, Kyusik Chung wrote:
> Hello. I am using Cassandra 0.6.1 on
