mirror of
https://github.com/zulip/zulip.git
synced 2025-11-07 23:43:43 +00:00
2a12fedcf1
We can compute the intended number of processes from the sharding configuration. In doing so, also validate that all of the ports are contiguous. This removes a discrepancy between `scripts/lib/sharding.py` and other parts of the codebase about if merely having a `[tornado_sharding]` section is sufficient to enable sharding. Having behaviour which changes merely based on if an empty section exists is surprising. This does require that a (presumably empty) `9800` configuration line exist, but making that default explicit is useful. After this commit, configuring sharding can be done by adding to `zulip.conf`: ``` [tornado_sharding] 9800 = # default 9801 = other_realm ``` Followed by running `./scripts/refresh-sharding-and-restart`.
79 lines
2.3 KiB
Python
Executable File
79 lines
2.3 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
import argparse
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
from collections import defaultdict
|
|
from typing import Dict
|
|
|
|
ZULIP_PATH = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
sys.path.append(ZULIP_PATH)
|
|
from scripts.lib.check_rabbitmq_queue import normal_queues
|
|
from scripts.lib.zulip_tools import get_config_file, get_tornado_ports
|
|
|
|
states = {
|
|
0: "OK",
|
|
1: "WARNING",
|
|
2: "CRITICAL",
|
|
3: "UNKNOWN",
|
|
}
|
|
|
|
if 'USER' in os.environ and not os.environ['USER'] in ['root', 'rabbitmq']:
|
|
print("This script must be run as the root or rabbitmq user")
|
|
|
|
|
|
usage = """Usage: check-rabbitmq-consumers --queue=[queue-name] --min-threshold=[min-threshold]"""
|
|
|
|
parser = argparse.ArgumentParser(usage=usage)
|
|
parser.add_argument('--min-threshold',
|
|
dest='min_count',
|
|
type=int,
|
|
default=1)
|
|
|
|
options = parser.parse_args()
|
|
|
|
config_file = get_config_file()
|
|
TORNADO_PROCESSES = len(get_tornado_ports(config_file))
|
|
|
|
output = subprocess.check_output(['/usr/sbin/rabbitmqctl', 'list_consumers'],
|
|
universal_newlines=True)
|
|
|
|
consumers: Dict[str, int] = defaultdict(int)
|
|
|
|
queues = {
|
|
*normal_queues,
|
|
# These queues may not be present if settings.TORNADO_PROCESSES > 1
|
|
'notify_tornado',
|
|
}
|
|
|
|
for queue_name in queues:
|
|
queue_name = queue_name.strip()
|
|
consumers[queue_name] = 0
|
|
|
|
for line in output.split('\n'):
|
|
parts = line.split('\t')
|
|
if len(parts) >= 2:
|
|
queue_name = parts[0]
|
|
if queue_name.startswith("notify_tornado_"):
|
|
queue_name = "notify_tornado"
|
|
consumers[queue_name] += 1
|
|
|
|
now = int(time.time())
|
|
|
|
for queue_name in consumers.keys():
|
|
state_file_path = "/var/lib/nagios_state/check-rabbitmq-consumers-" + queue_name
|
|
state_file_tmp = state_file_path + "-tmp"
|
|
|
|
target_count = options.min_count
|
|
if queue_name == "notify_tornado":
|
|
target_count = TORNADO_PROCESSES
|
|
|
|
if consumers[queue_name] < target_count:
|
|
status = 2
|
|
else:
|
|
status = 0
|
|
with open(state_file_tmp, "w") as f:
|
|
f.write(f"{now}|{status}|{states[status]}|queue {queue_name} has {consumers[queue_name]} consumers, needs {target_count}\n")
|
|
os.rename(state_file_tmp, state_file_path)
|