Hey Jakub,

Kafka has always been high throughput but has not always been low latency.
In 0.7 and lower the produce request had low latency but the end-to-end
latency (i.e. the time from when the message was sent to when it was
delivered to the consumer) could be in the hundreds of milliseconds or
longer, depending on your configuration.

In 0.8 end-to-end latency should be very low (a few ms) provided that (1)
you disable batch in the producer (enable "sync" mode) and (2) your
consumer can keep up.

On Wed, Jul 24, 2013 at 4:07 AM, Jakub Ryska <[EMAIL PROTECTED]>wrote:
NEW: Monitor These Apps!
elasticsearch, apache solr, apache hbase, hadoop, redis, casssandra, amazon cloudwatch, mysql, memcached, apache kafka, apache zookeeper, apache storm, ubuntu, centOS, red hat, debian, puppet labs, java, senseiDB