Improve Python + Influxdb import performance
INADA Naoki
songofacandy at gmail.com
Mon Apr 3 12:22:04 EDT 2017
You can reuse connection, instead of creating for each request. (HTTP
keep-alive).
On Tue, Apr 4, 2017 at 1:11 AM, Prathamesh <prathamesh.nimkar at gmail.com> wrote:
> Hello World
>
> The following script is an extract from
>
> https://github.com/RittmanMead/obi-metrics-agent/blob/master/obi-metrics-agent.py
>
> <<Code begins>>
>
> import calendar, time
> import sys
> import getopt
>
> print '---------------------------------------'
>
> # Check the arguments to this script are as expected.
> # argv[0] is script name.
> argLen = len(sys.argv)
> if argLen -1 < 2:
> print "ERROR: got ", argLen -1, " args, must be at least two."
> print '$FMW_HOME/oracle_common/common/bin/wlst.sh obi-metrics-agent.py <AdminUserName> <AdminPassword> [<AdminServer_t3_url>] [<Carbon|InfluxDB>] [<target host>] [<target port>] [targetDB influx db>'
> exit()
>
> outputFormat='CSV'
> url='t3://localhost:7001'
> targetHost='localhost'
> targetDB='obi'
> targetPort='8086'
>
> try:
> wls_user = sys.argv[1]
> wls_pw = sys.argv[2]
> url = sys.argv[3]
> outputFormat=sys.argv[4]
> targetHost=sys.argv[5]
> targetPort=sys.argv[6]
> targetDB=sys.argv[7]
> except:
> print ''
>
> print wls_user, wls_pw,url, outputFormat,targetHost,targetPort,targetDB
>
> now_epoch = calendar.timegm(time.gmtime())*1000
>
> if outputFormat=='InfluxDB':
> import httplib
> influx_msgs=''
>
> connect(wls_user,wls_pw,url)
> results = displayMetricTables('Oracle_BI*','dms_cProcessInfo')
> for table in results:
> tableName = table.get('Table')
> rows = table.get('Rows')
> rowCollection = rows.values()
> iter = rowCollection.iterator()
> while iter.hasNext():
> row = iter.next()
> rowType = row.getCompositeType()
> keys = rowType.keySet()
> keyIter = keys.iterator()
> inst_name= row.get('Name').replace(' ','-')
> try:
> server= row.get('Servername').replace(' ','-').replace('/','_')
> except:
> try:
> server= row.get('ServerName').replace(' ','-').replace('/','_')
> except:
> server='unknown'
> try:
> host= row.get('Host').replace(' ','-')
> except:
> host=''
> while keyIter.hasNext():
> columnName = keyIter.next()
> value = row.get(columnName )
> if columnName.find('.value')>0:
> metric_name=columnName.replace('.value','')
> if value is not None:
> if value != 0:
> if outputFormat=='InfluxDB':
> influx_msg= ('%s,server=%s,host=%s,metric_group=%s,metric_instance=%s value=%s %s') % (metric_name,server,host,tableName,inst_name, value,now_epoch*1000000)
> influx_msgs+='\n%s' % influx_msg
> conn = httplib.HTTPConnection('%s:%s' % (targetHost,targetPort))
> ## TODO pretty sure should be urlencoding this ...
> a=conn.request("POST", ("/write?db=%s" % targetDB), influx_msg)
> r=conn.getresponse()
>
> <<Code ends>>
>
> It currently takes about 3 minutes to execute completely and I was thinking of a way to make it run faster
>
> Data alignment (Influx line protocol) & data loading - done together takes up most of the time
>
> Influxdb is currently loading data at around 3 points/second
>
> Any way to align the data separately, store it and load it as a batch?
>
> I feel that would help improve performance
>
> Please let me know if you have any pointers
> I can send the data sheet if required
>
> Thanks P
> --
> https://mail.python.org/mailman/listinfo/python-list
More information about the Python-list
mailing list