def evaluate(self, profile, plan_node_id):
"""
Determine the impact of NN RPC latency
this format:
{
"impact": the amount of slow down (in ns),
"message" : the displayed "explanation" string
}
:return:
"""
totalStorageTime = models.query_avg_fragment_metric_by_node_nid(
profile, plan_node_id, "TotalStorageWaitTime", 0)
hdfsRawReadTime = models.query_node_by_id_value(
profile, plan_node_id, "TotalRawHdfsReadTime(*)", True)
avgReadThreads = models.query_node_by_id_value(
profile, plan_node_id, "AverageHdfsReadThreadConcurrency", True)
avgReadThreads = max(1, to_double(avgReadThreads))
impact = max(
0, math.floor(
(totalStorageTime - hdfsRawReadTime) / avgReadThreads))
return {
"impact": impact,
"message": "This is the time waiting for HDFS NN RPC.",
"label": "HDFS NN RPC"
}
def evaluate(self, profile, plan_node_id):
"""
Determine if the join exploded the number of rows
this format:
{
"impact": the amount of slow down (in ns),
"message" : the displayed "explanation" string
}
:return:
"""
self.metric_names = ["Hosts", "Broadcast", "BuildRows", "ProbeRows"]
hosts = models.query_node_by_id_value(profile, plan_node_id, "Hosts",
True)
probeRows = models.query_node_by_id_value(profile, plan_node_id,
"ProbeRows", True)
probeTime = models.query_node_by_id_value(profile, plan_node_id,
"ProbeTime", True)
rowsReturned = models.query_node_by_id_value(profile, plan_node_id,
"RowsReturned", True)
impact = 0
if (rowsReturned > 0):
impact = probeTime * (rowsReturned - probeRows) / rowsReturned
return {
"impact":
impact,
"message":
"%d input rows are exploded to %d output rows" %
(probeRows, rowsReturned),
"label":
"Exploding join"
}
def evaluate(self, profile, plan_node_id):
"""
Determine if the join order/strategy is correct and evaluate the impact of this cause
to the query. The return is a json string with
this format:
{
"impact": the amount of slow down (in ns),
"message" : the displayed "explanation" string
}
:return:
"""
self.metric_names = ["Hosts", "Broadcast", "BuildRows", "ProbeRows"]
hosts = models.query_node_by_id_value(profile, plan_node_id, "Hosts",
True)
isBroadcast = models.query_node_by_id_value(profile, plan_node_id,
"Broadcast", True)
buildRows = models.query_node_by_id_value(profile, plan_node_id,
"BuildRows", True)
probeRows = models.query_node_by_id_value(profile, plan_node_id,
"ProbeRows", True)
rhsRows = 0
lhsRows = 0
networkcost = 0
if (isBroadcast == 1):
networkcost = buildRows * hosts
rhsRows = buildRows
lhsRows = probeRows * hosts
else:
networkcost = (buildRows + probeRows) * hosts
rhsRows = buildRows * hosts
lhsRows = probeRows * hosts
impact = math.floor((rhsRows - lhsRows * 1.5) / hosts / 0.01)
if (impact > 0):
return {
"impact": impact,
"message": "RHS %d; LHS %d" % (rhsRows, lhsRows),
"label": "Wrong join order"
}
bcost = rhsRows * hosts
scost = lhsRows + rhsRows
impact = math.floor(
(networkcost - min(bcost, scost) - 1) / hosts / 0.01)
return {
"impact": impact,
"message": "RHS %d; LHS %d" % (rhsRows, lhsRows),
"label": "Wrong join strategy"
}