Adding metrics framework intermediate updates.

- Since each host in a cluster has it's own view of the metrics
  the only time the manager would get a chance for a global view
  is the break_interval.  This update improves that time.  If a
  worker crosses 10% of the full threshold, it will send it's
  value to the manager which can then ask the rest of the cluster
  for a global view.  The manager then adds all of the values for
  each workers metric indexes together and will do the notice
  if it crosses the threshold so that it isn't dependent on
  waiting for the break interval to hit.  This functionality
  works completely independently of the break_interval too.  Logging
  will happen as normal.

- Small update for SSH bruteforcer detection to match additions in
  the metrics framework API.

- The hope is that this update is mostly invisible from anyone's
  perspective.  The only affect it should have on users is to better
  the detection of metric values crossing thresholds on cluster
  deployments.
This commit is contained in:
Seth Hall 2011-08-21 00:32:00 -04:00
parent 82f94881c0
commit a7f6e4c582
10 changed files with 303 additions and 111 deletions

View file

@ -0,0 +1,2 @@
# ts uid id.orig_h id.orig_p id.resp_h id.resp_p note msg sub src dst p n peer_descr actions policy_items dropped remote_location.country_code remote_location.region remote_location.city remote_location.latitude remote_location.longitude metric_index.host metric_index.str metric_index.network
1313897486.017657 - - - - - Test_Notice Threshold crossed by metric_index(host=1.2.3.4) 100/100 - 1.2.3.4 - - 100 manager-1 Notice::ACTION_LOG 4 - - - - - - 1.2.3.4 - -

View file

@ -1,4 +1,3 @@
# ts uid id.orig_h id.orig_p id.resp_h id.resp_p note msg sub src dst p n peer_descr actions policy_items dropped remote_location.country_code remote_location.region remote_location.city remote_location.latitude remote_location.longitude metric_index.host metric_index.str metric_index.network
1313508844.321207 - - - - - Test_Notice Metrics threshold crossed by metric_index(host=6.5.4.3) 2/1 - 6.5.4.3 - - 2 bro Notice::ACTION_LOG 4 - - - - - - 6.5.4.3 - -
1313508844.321207 - - - - - Test_Notice Metrics threshold crossed by metric_index(host=1.2.3.4) 3/1 - 1.2.3.4 - - 3 bro Notice::ACTION_LOG 4 - - - - - - 1.2.3.4 - -
1313508844.321207 - - - - - Test_Notice Metrics threshold crossed by metric_index(host=7.2.1.5) 1/1 - 7.2.1.5 - - 1 bro Notice::ACTION_LOG 4 - - - - - - 7.2.1.5 - -
1313685819.326521 - - - - - Test_Notice Threshold crossed by metric_index(host=1.2.3.4) 3/2 - 1.2.3.4 - - 3 bro Notice::ACTION_LOG 4 - - - - - - 1.2.3.4 - -
1313685819.326521 - - - - - Test_Notice Threshold crossed by metric_index(host=6.5.4.3) 2/2 - 6.5.4.3 - - 2 bro Notice::ACTION_LOG 4 - - - - - - 6.5.4.3 - -

View file

@ -24,15 +24,11 @@ event bro_init() &priority=5
Metrics::add_filter(TEST_METRIC,
[$name="foo-bar",
$break_interval=3secs]);
if ( Cluster::local_node_type() == Cluster::WORKER )
{
Metrics::add_data(TEST_METRIC, [$host=1.2.3.4], 3);
Metrics::add_data(TEST_METRIC, [$host=6.5.4.3], 2);
Metrics::add_data(TEST_METRIC, [$host=7.2.1.5], 1);
}
}
@if ( Cluster::local_node_type() == Cluster::WORKER )
event bro_init()
{
Metrics::add_data(TEST_METRIC, [$host=1.2.3.4], 3);
Metrics::add_data(TEST_METRIC, [$host=6.5.4.3], 2);
Metrics::add_data(TEST_METRIC, [$host=7.2.1.5], 1);
}
@endif

View file

@ -0,0 +1,54 @@
# @TEST-EXEC: btest-bg-run manager-1 BROPATH=$BROPATH:.. CLUSTER_NODE=manager-1 bro %INPUT
# @TEST-EXEC: btest-bg-run proxy-1 BROPATH=$BROPATH:.. CLUSTER_NODE=proxy-1 bro %INPUT
# @TEST-EXEC: sleep 1
# @TEST-EXEC: btest-bg-run worker-1 BROPATH=$BROPATH:.. CLUSTER_NODE=worker-1 bro %INPUT
# @TEST-EXEC: btest-bg-run worker-2 BROPATH=$BROPATH:.. CLUSTER_NODE=worker-2 bro %INPUT
# @TEST-EXEC: btest-bg-wait -k 5
# @TEST-EXEC: btest-diff manager-1/notice.log
@TEST-START-FILE cluster-layout.bro
redef Cluster::nodes = {
["manager-1"] = [$node_type=Cluster::MANAGER, $ip=127.0.0.1, $p=37757/tcp, $workers=set("worker-1")],
["proxy-1"] = [$node_type=Cluster::PROXY, $ip=127.0.0.1, $p=37758/tcp, $manager="manager-1", $workers=set("worker-1")],
["worker-1"] = [$node_type=Cluster::WORKER, $ip=127.0.0.1, $p=37760/tcp, $manager="manager-1", $proxy="proxy-1", $interface="eth0"],
["worker-2"] = [$node_type=Cluster::WORKER, $ip=127.0.0.1, $p=37761/tcp, $manager="manager-1", $proxy="proxy-1", $interface="eth1"],
};
@TEST-END-FILE
redef enum Notice::Type += {
Test_Notice,
};
redef enum Metrics::ID += {
TEST_METRIC,
};
event bro_init() &priority=5
{
Metrics::add_filter(TEST_METRIC,
[$name="foo-bar",
$break_interval=1hr,
$note=Test_Notice,
$notice_threshold=100,
$log=T]);
}
@if ( Cluster::local_node_type() == Cluster::WORKER )
event do_metrics(i: count)
{
# Worker-1 will trigger an intermediate update and then if everything
# works correctly, the data from worker-2 will hit the threshold and
# should trigger the notice.
Metrics::add_data(TEST_METRIC, [$host=1.2.3.4], i);
}
event bro_init()
{
if ( Cluster::node == "worker-1" )
schedule 2sec { do_metrics(99) };
if ( Cluster::node == "worker-2" )
event do_metrics(1);
}
@endif

View file

@ -1,6 +1,7 @@
# @TEST-EXEC: bro %INPUT
# @TEST-EXEC: btest-diff notice.log
redef enum Notice::Type += {
Test_Notice,
};
@ -15,7 +16,7 @@ event bro_init() &priority=5
[$name="foo-bar",
$break_interval=3secs,
$note=Test_Notice,
$notice_threshold=1,
$notice_threshold=2,
$log=F]);
Metrics::add_data(TEST_METRIC, [$host=1.2.3.4], 3);
Metrics::add_data(TEST_METRIC, [$host=6.5.4.3], 2);