[Answer]-Django memory leak

by

1👍

✅

If you have a lot of data you still may need to load & process it in chunks, try this:

CHUNK_SIZE = 23000
ports_list_save = []
for host in results['hosts']:
    for protocol in results['hosts'][host]['protocols']:
        for port in results['hosts'][host]['protocols'][protocol]:
            current_port = history.Port(number=int(port), 
                                        protocol=protocol, 
                                        state=results['hosts'][host]['protocols'][protocol][port]['state'], 
                                        service='', 
                                        version='', 
                                        address=history.Ip.objects.get(scan=self.scan, address=host))
            ports_list_save.append(current_port)
            if len(ports_list_save) > CHUNK_SIZE:
                history.Port.objects.bulk_create(ports_list_save)
                ports_list_save = []
if ports_list_save:   
    history.Port.objects.bulk_create(ports_list_save)
👤monkut

0👍

I faced with the same problem and ended up with this solution:

class BulkCreateManager(object):

    model = None
    chunk_size = None
    instances = None

    def __init__(self, model, chunk_size=None, *args):
        self.model = model
        self.chunk_size = chunk_size
        self.instances = []

    def append(self, instance):
        if self.chunk_size and len(self.instances) > self.chunk_size:
            self.create()
            self.instances = []

        self.instances.append(instance)

    def create(self):
        self.model.objects.bulk_create(self.instances)



ports_list_save = BulkCreateManager(history.Port, 23000)
for host in results['hosts']:
    for protocol in results['hosts'][host]['protocols']:
        for port in results['hosts'][host]['protocols'][protocol]:
            current_port = history.Port(number=int(port), 
                                        protocol=protocol, 
                                        state=results['hosts'][host]['protocols'][protocol][port]['state'], 
                                        service='', 
                                        version='', 
                                        address=history.Ip.objects.get(scan=self.scan, address=host))
            ports_list_save.append(current_port)

ports_list_save.create()
👤ramusus

Leave a comment