time series data with apache cassandra
DESCRIPTION
Whether it's statistics, weather forecasting, astronomy, finance, or network management, time series data plays a critical role in analytics and forecasting. Unfortunately, while many tools exist for time series storage and analysis, few are able to scale past memory limits, or provide rich query and analytics capabilities outside what is necessary to produce simple plots; For those challenged by large volumes of data, there is much room for improvement. Apache Cassandra is a fully distributed second-generation database. Cassandra stores data in key-sorted order making it ideal for time series, and its high throughput and linear scalability make it well suited to very large data sets. This talk will cover some of the requirements and challenges of large scale time series storage and analysis. Cassandra data and query modeling for this use-case will be discussed, and Newts, an open source Cassandra-based time series store under development at The OpenNMS Group will be introduced.TRANSCRIPT
Time Series Data With Apache Cassandra
Berlin BuzzwordsMay 27, 2014
Eric [email protected]
@jericevans
Open
Open
Open
Open
Network
Management
System
OpenNMS: What It Is
● Network Management System○ Discovery and Provisioning○ Service monitoring○ Data collection○ Event management, notifications
● Java, open source, GPLv3● Since 1999
Time series: RRDTool
● Round Robin Database● First released 1999● Time series storage● File-based, constant-size, self-maintaining● Automatic, incremental aggregation
… and oh yeah, graphing
Consider
● 5+ IOPs per update (read-modify-write)!● 100,000s of metrics, 1,000s IOPS● 1,000,000s of metrics, 10,000s IOPS● 15,000 RPM SAS drive, ~175-200 IOPS
Hmmm
We collect and write a great deal; We read (graph) relatively little.
So why are we aggregating everything?
Also
● Not everything is a graph● Inflexible● Incremental backups impractical● Availability subject to filesystem access
TIL
Metrics typically appear in groups that are accessed together.
Optimizing storage for grouped access is a great idea!
What OpenNMS needs:
● High throughput● High availability● Late aggregation● Grouped storage/retrieval
Cassandra
● Apache top-level project● Distributed database● Highly available● High throughput● Tunable consistency
SSTables
Writes
Commitlog
Memtable
SSTable
DiskMemory
Write Properties
● Optimized for write throughput● Sorted on disk● Perfect for time series!
Partitioning
A
B
C
Key: Apple
...
AZ
Placement
A
B
C
Key: Apple
...
Replication
A
B
C
Key: Apple
...
CAP Theorem
Consistency
Availability
Partition tolerance
Consistency
A
B
?
W=2
Consistency
?
B
C
R=2
R+W > N
Distribution Properties
● Symmetrical● Linearly scalable● Redundant● Highly available
D ata odelM
Data Modelresource
Data Modelresource
T1 T2 T3
Data Modelresource
T1
M1 M2
V1 V2
M3
V3
T2
M1 M2
V1 V2
M3
V3
T3
M1 M2
V1 V2
M3
V3
Data Model
CREATE TABLE samples ( T timestamp,
M text,
V double,
resource text,
PRIMARY KEY(resource, T, M));
Data model
V1T1 M1 V2T1 M2 T1 V3M3resource
Data model
SELECT * FROM samplesWHERE resource = ‘resource’AND T = ‘T1’;
V1T1 M1 V2T1 M2 T1 V3M3resource
Data model
T1 M1 V1resource
V1T1 M1 V2T1 M2 T1 V3M3resource
Data model
T1 M1 V1
T1 M2 V2
resource
resource
V1T1 M1 V2T1 M2 T1 V3M3resource
Data model
T1 M1 V1
T1 M2 V2
T1 M3 V3
resource
resource
resource
V1T1 M1 V2T1 M2 T1 V3M3resource
Data model
SELECT * FROM samplesWHERE resource = ‘resource’AND T >= ‘T1’ AND T <= ‘T3’;
V1T1 M1 V1T2 M1 T3 V1M1resource
Newts
● Standalone time series data-store● Raw sample storage and retrieval● Flexible aggregations (computed at read)
○ Rate (counter types)○ Functions pluggable○ Arbitrary calculations
● Cassandra-speed
Newts
● Java API● REST interface● Apache licensed● Github (http://github.com/OpenNMS/newts)
Fin