Apache Cassandra™ 2.0

cfhistograms

Provides statistics about a table that could be used to plot a frequency function.

Synopsis

nodetool <options> cfhistograms -- <keyspace> <table>
  • options are:
    • ( -h | --host ) <host name> | <ip address>
    • ( -p | --port ) <port number>
    • ( -pw | --password ) <password >
    • ( -u | --username ) <user name>
  • -- Separates an option from an argument that could be mistaken for a option.
  • keyspace is the name of a keyspace.
  • table is the name of a table.

Synopsis Legend

  • Angle brackets (< >) mean not literal, a variable
  • Italics mean optional
  • The pipe (|) symbol means OR or AND/OR
  • Ellipsis (...) means repeatable
  • Orange ( and ) means not literal, indicates scope

Description

The nodetool cfhistograms command provides statistics about a table, including number of SSTables, read/write latency, partition (row) size, and cell count.

Example

After performing the Wikipedia demo, run this command to get statistics about the solr table in the wiki keyspace.
nodetool cfhistograms wiki solr
The output shows latencies in microseconds (µs), partition (formerly called row) size in bytes, and the number of SSTables and the cell count. The Offset column corresponds to the x-axis in a histogram. It represents buckets of values, which are a series of ranges. Each offset includes the range of values greater than the previous offset and less than or equal to the current offset. The offsets start at 1 and each subsequent offset is calculated by multiplying the previous offset by 1.2, rounding up, and removing duplicates. The offsets can range from 1 to approximately 25 million, with less precision as the offsets get larger.

For example:

  • Offset 1 shows that 3579 requests only had to look at one SSTable. The SSTables column corresponds to how many SSTables were involved in a read request.
  • Offset 86 shows that there were 663 requests with a write latency between 73 and 86 µs. The range falls into the 73 to 86 bucket.

On some versions of Cassandra, the output looks like this:

wiki/solr histograms
Offset      SSTables     Write Latency      Read Latency          Row Size      Column Count
1               3579                 0                 0                 0                 0
2                  0                 0                 0                 0                 0
. . .
35                 0                 0                 0                 0                 0
42                 0                 0                27                 0                 0
50                 0                 0               187                 0                 0
60                 0                10               460                 0                 0
72                 0               200               689                 0                 0
86                 0               663               552                 0                 0
103                0               796               367                 0                 0
124                0               297               736                 0                 0
149                0               265               243                 0                 0
179                0               460               263                 0                 0
. . .
25109160           0                 0                 0                 0                 0

On other versions of Cassandra 2.0.x, the output does not label the columns. The offset is on the left, the latency on the right:

SSTables per Read
1 sstables: 3579

Write Latency (microseconds)
  50 us: 1
  60 us: 195
  72 us: 1029
  86 us: 876
 103 us: 433
 124 us: 170
 149 us: 208
 179 us: 247
 215 us: 216
 258 us: 137
 310 us: 43
 372 us: 9
 446 us: 4
 535 us: 1
 642 us: 2
 770 us: 2
 924 us: 1
1109 us: 1
1331 us: 2
1597 us: 0
1916 us: 0
2299 us: 1
2759 us: 1

Read Latency (microseconds)
   50 us: 4
   60 us: 69
   72 us: 384
   86 us: 802
  103 us: 936
  124 us: 523
  149 us: 452
  179 us: 271
  215 us: 106
  258 us: 13
  310 us: 4
  372 us: 6
  446 us: 1
  535 us: 3
  642 us: 3
  770 us: 0
  924 us: 0
 1109 us: 0
 1331 us: 1
 1597 us: 0
 1916 us: 0
 2299 us: 0
 2759 us: 0
 3311 us: 0
 3973 us: 0
 4768 us: 0
 5722 us: 0
 6866 us: 0
 8239 us: 0
 9887 us: 0
11864 us: 0
14237 us: 1

Partition Size (bytes)
No Data

Cell Count per Partition
No Data

OpsCenter displays the same information in a better format for understanding the statistics.

Show/hide