Kafka use seek to manually manage offset, consumer lose some messages

Question

I have a script to test for at least one consume

the producer

import json
import random
import time

from confluent_kafka import Producer
import config

p = Producer({'bootstrap.servers':','.join(config.KAFKA_HOST),})
total_count = 0
c = 0
try:
    for i in range(20000):
        num = random.randint(1, 1000000)
        total_count += num
        a = {'t': num, 'time': time.time()}
        p.produce('test-topic-vv', json.dumps(a))
        c += 1
        if c %100 == 0:
            p.flush()
finally:
    p.flush()

the consumer

import json
import random
import sys

from confluent_kafka import Consumer, TopicPartition
import config
c = Consumer({
    'bootstrap.servers':','.join(config.KAFKA_HOST),
    'group.id': 'test-topic-consumer-group',
    'auto.offset.reset': 'earliest',
    'enable.auto.offset.store': False,
    'enable.auto.commit': True,
})
topic = 'test-topic-vv'

def test_for_seek():
    try:
        pp = []
        pp.append(TopicPartition(topic, partition=8))
        c.assign(pp)
        while True:
            msgs = c.consume(num_messages=10, timeout=10)
            if not msgs:
                print('no data and wait')
                for i in c.assignment():
                    print(i.topic, i.partition, i.offset, c.get_watermark_offsets(i))
                continue
            for msg in msgs:
                t1 = msg.partition()
                o1 = msg.offset()
                print('Received message: {} par {} offset {}'.format(msg.value().decode('utf-8'), t1, o1))
            break
    finally:
        c.close()

def test_for_run():
    try:
        c.subscribe([topic])
        total_count = 0
        map_par = {}
        while True:
            msgs = c.consume(num_messages=10, timeout=5)
            if not msgs:
                print('no data and wait')
                for i in c.assignment():
                    print(i.topic, i.partition, i.offset, c.get_watermark_offsets(i))
                continue
            deald = []
            for msg in msgs:
                t1 = msg.partition()
                o1 = msg.offset()
                print('Received message: {} par {} offset {}'.format(msg.value().decode('utf-8'), t1, o1))
                if random.randint(1, 100) == 9:
                    # test for deal failed then retry again
                    print('deal failed will retry msg offset {} partition {}'.format(msg.offset(), msg.partition()))
                    break
                else:
                    total_count += json.loads(msg.value())['t']
                    # test for deal success
                    if t1 in map_par:
                        if map_par[t1] + 1 != o1:
                            raise Exception('deal partition {} except last offset {} current offset {}'.format(t1, map_par[t1], o1))
                    map_par[t1] = o1
                    c.store_offsets(msg)
                    deald.append(msg)
            group_partition = {}
            for msg in msgs:
                if msg in deald:
                    continue
                partition = msg.partition()
                offset = msg.offset()
                if partition in group_partition:
                    group_partition[partition] = min(group_partition[partition], offset)
                else:
                    group_partition[partition] = offset
            # seek to deal failed partition offset
            for k, v in group_partition.items():
                c.seek(TopicPartition(topic, partition=k, offset=v))
                print('deal failed will set msg offset {} partition {}'.format(v, k))
    finally:
        c.close()

if sys.argv[1] == 'test_for_seek':
    test_for_seek()
else:
    test_for_run()

the topic test-topic-vv has 9 partition

first i run producer to add some message to topic then consume it. but i got a exception

screenshot https://user-images.githubusercontent.com/12459874/194990350-8cd13128-f3fa-4a86-a93e-771af45f93f0.png

The latest message's offset of partition 8 should be 7382 but got 7391

then i run test_for_seek to check the consumer group's actually record offset it was 7382 indeed

screenshot https://user-images.githubusercontent.com/12459874/194990593-9b8431d0-ce07-4122-800d-f9b3c129f5f3.png

I also check the broker's group offset record

screenshot https://user-images.githubusercontent.com/12459874/194990684-9d8ad773-a569-4cee-9d4c-0a898e8f8922.png

it also was 7382

So what happened to consumer when use seek to manage offset, hope any one can help me to deal with the problem.

check information

• confluent_kafka.version()==1.9.2
• confluent_kafka.libversion()==1.9.2
• Operating system: ubuntu 16.04
• Python3.8
• kafka 2.11-1.1.1