django - 使用 nginx+gunicorn+django 的间歇性 502s

Question

在过去的几周里，我们收到了越来越多的 502 错误。目前，我们的堆栈是 nginx + gunicron + django，位于由小型 RDS 实例支持的 m1.large EC2 实例上。

随着请求负载的增加，它们似乎变得更加频繁。我会在使用浏览器时看到随机的 502，但我们命中 api (Tasty Pie) 的命令行脚本通常会在第二次或第三次请求时失败。但是，如果我在脚本发出请求之前向脚本添加一个 sleep 函数，那么该请求就可以了，但下一个请求是 502。请注意，我们将摘要身份验证与请求库和 sleep 包装器一起使用——因此使用了 401、200 模式。

为了使调试更加棘手，当使用 --debug 选项运行 Gunicorn 时，问题会自行解决。如果我删除 --debug 选项但将我的 Gunicorn worker 明确限制为 1，错误仍然存​​在。

我的 nginx.conf:

user www-data;
worker_processes 4;
pid /var/run/nginx.pid;

events {
    worker_connections 768;
    # multi_accept on;
}

http {

    ##
    # Basic Settings
    ##

    sendfile on;
    tcp_nopush on;
    tcp_nodelay on;
    keepalive_timeout 65;
    types_hash_max_size 2048;
    # server_tokens off;

    # server_names_hash_bucket_size 64;
    # server_name_in_redirect off;

    include /etc/nginx/mime.types;
    default_type application/octet-stream;

    ##
    # Logging Settings
    ##

    access_log /var/log/nginx/access.log;
    error_log /var/log/nginx/error.log;

    ##
    # Gzip Settings
    ##

    gzip on;
    gzip_disable "msie6";

        gzip_proxied any;
        gzip_types application/x-ghi-packedschemafeatures-v1
        gzip_http_version 1.1;
        gzip_comp_level 1;
        gzip_min_length 500;

        proxy_buffering on;
        proxy_http_version 1.1;

    ##
    # Virtual Host Configs
    ##

    include /etc/nginx/conf.d/*.conf;
    include /etc/nginx/sites-enabled/*;
}

虚拟主机文件:

    server {
      listen 80;
      server_name pipeline.ourdomain.com;
      location / {
        rewrite ^ https://$server_name$request_uri permanent;
      }
}

server {
      listen 443;
      server_name pipeline.ourdomain.com;
      ssl on;
      ssl_protocols SSLv3 TLSv1;
      ssl_ciphers ALL:-ADH:+HIGH:+MEDIUM:-LOW:-SSLv2:-EXP;
      ssl_session_cache shared:SSL:10m;
      ssl_certificate     /etc/ssl/certs/ourdomain.com.combined.crt;
      ssl_certificate_key /etc/ssl/private/ourdomain.com.key;

      root /var/www/;
      location /static/ {
               alias /var/www/production/pipeline/public/;
      }

      location / {
             proxy_pass_header Server;
             proxy_set_header Host $http_host;
             proxy_redirect off;
             proxy_set_header X-Real-IP $remote_addr;
             proxy_set_header X-Scheme $scheme;
             proxy_set_header X-Forwarded-Protocol https;
             proxy_connect_timeout 240;
             proxy_read_timeout 280;
             proxy_pass http://localhost:8000/;
      }
      error_page 500 502 503 504 /static/50x.html;



}

unicorn 命令

#!/bin/bash
set -e
LOGFILE=/var/log/gunicorn/ea_pipeline.log
LOGDIR=$(dirname $LOGFILE)

SETTINGS=production_settings
# user/group to run as
USER=ubuntu
GROUP=ubuntu
DJANGO_PATH=$(dirname $(readlink -f $0))/../
cd $DJANGO_PATH
echo $(pwd)
. ../env/bin/activate
test -d $LOGDIR || mkdir -p $LOGDIR
exec ../env/bin/gunicorn_django \
     --user=$USER --group=$GROUP --log-level=debug \
     --preload \
     --workers=4 \
     --timeout=90 \
     --settings=$SETTINGS \
     --limit-request-line=8190 \
     --limit-request-field_size 0 \
     --pythonpath=$DJANGO_PATH \
     --log-file=$LOGFILE production_settings.py 2>>$LOGFILE

访问日志示例:

67.134.170.194 - - [24/Aug/2012:00:28:17 +0000] "GET /api/v1/storage/ HTTP/1.1" 401 5 "-" "python-requests/0.13.8 CPython/2.7.3 Linux/3.2.0-29-generic"
67.134.170.194 - - [24/Aug/2012:00:28:18 +0000] "GET /api/v1/storage/ HTTP/1.1" 200 326 "-" "python-requests/0.13.8 CPython/2.7.3 Linux/3.2.0-29-generic"
67.134.170.194 - - [24/Aug/2012:00:28:18 +0000] "GET /api/v1/customer/?client_id=lamb_01 HTTP/1.1" 502 18 "-" "python-requests/0.13.8 CPython/2.7.3 Linux/3.2.0-29-generic"
67.134.170.194 - - [24/Aug/2012:00:29:41 +0000] "GET /api/v1/storage/ HTTP/1.1" 502 18 "-" "python-requests/0.13.8 CPython/2.7.3 Linux/3.2.0-29-generic"

Nginx 错误日志:

2012/08/24 00:28:18 [error] 16490#0: *3 connect() failed (111: Connection refused) while connecting to upstream, client: 67.134.170.194, server: pipeline.ourdomain.com, request: "GET /api/v1/customer/?client_id=lamb_01 HTTP/1.1", upstream: "http://127.0.0.1:8000/api/v1/customer/?client_id=lamb_01", host: "pipeline.ourdomain.com"
2012/08/24 00:29:41 [error] 16490#0: *7 connect() failed (111: Connection refused) while connecting to upstream, client: 67.134.170.194, server: pipeline.ourdomain.com, request: "GET /api/v1/storage/ HTTP/1.1", upstream: "http://127.0.0.1:8000/api/v1/storage/", host: "pipeline.ourdomain.com"

Gunicorn 日志示例:

2012-08-24 17:03:13 [8716] [INFO] Starting gunicorn 0.14.3
2012-08-24 17:03:13 [8716] [DEBUG] Arbiter booted
2012-08-24 17:03:13 [8716] [INFO] Listening at: http://127.0.0.1:8000 (8716)
2012-08-24 17:03:13 [8716] [INFO] Using worker: sync
2012-08-24 17:03:13 [8735] [INFO] Booting worker with pid: 8735
2012-08-24 17:03:13 [8736] [INFO] Booting worker with pid: 8736
2012-08-24 17:03:13 [8737] [INFO] Booting worker with pid: 8737
2012-08-24 17:03:13 [8738] [INFO] Booting worker with pid: 8738
2012-08-24 17:03:21 [8738] [DEBUG] GET /api/v1/storage/
Assertion failed: ok (mailbox.cpp:84)
2012-08-24 17:03:21 [8738] [INFO] Parent changed, shutting down: <Worker 8738>
2012-08-24 17:03:21 [8738] [INFO] Worker exiting (pid: 8738)
Error in sys.exitfunc:
2012-08-24 17:03:21 [8737] [DEBUG] GET /api/v1/storage/
2012-08-24 17:03:22 [8838] [INFO] Starting gunicorn 0.14.3
2012-08-24 17:03:22 [8838] [ERROR] Connection in use: ('127.0.0.1', 8000)
2012-08-24 17:03:22 [8838] [ERROR] Retrying in 1 second.
2012-08-24 17:03:22 [8737] [INFO] Parent changed, shutting down: <Worker 8737>
2012-08-24 17:03:22 [8737] [INFO] Worker exiting (pid: 8737)
Error in sys.exitfunc:
2012-08-24 17:03:22 [8736] [DEBUG] GET /api/v1/customer/
2012-08-24 17:03:23 [8736] [INFO] Parent changed, shutting down: <Worker 8736>
2012-08-24 17:03:23 [8736] [INFO] Worker exiting (pid: 8736)
Error in sys.exitfunc:
2012-08-24 17:03:23 [8838] [ERROR] Connection in use: ('127.0.0.1', 8000)
2012-08-24 17:03:23 [8838] [ERROR] Retrying in 1 second.
2012-08-24 17:03:24 [8735] [DEBUG] GET /api/v1/upload_action/
2012-08-24 17:03:24 [8838] [ERROR] Connection in use: ('127.0.0.1', 8000)
2012-08-24 17:03:24 [8838] [ERROR] Retrying in 1 second.
2012-08-24 17:03:24 [8735] [INFO] Parent changed, shutting down: <Worker 8735>
2012-08-24 17:03:24 [8735] [INFO] Worker exiting (pid: 8735)
Error in sys.exitfunc:
2012-08-24 17:03:25 [8838] [DEBUG] Arbiter booted
2012-08-24 17:03:25 [8838] [INFO] Listening at: http://127.0.0.1:8000 (8838)
2012-08-24 17:03:25 [8838] [INFO] Using worker: sync
2012-08-24 17:03:25 [8907] [INFO] Booting worker with pid: 8907
2012-08-24 17:03:25 [8908] [INFO] Booting worker with pid: 8908
2012-08-24 17:03:25 [8909] [INFO] Booting worker with pid: 8909
2012-08-24 17:03:25 [8910] [INFO] Booting worker with pid: 8910

Answer 1

这是一个非常古老的帖子。但我在使用 NGinx+Gunicorn+Flask 设置时遇到了完全相同的问题。在大约每 300 个请求中，我也遇到了 502 错误，日志与您的日志相同。将 gunicorn worker 类型更改为异步为我解决了这个问题(我选择了 gthread)。希望这个答案对某人有所帮助。

如何更改设置:http://docs.gunicorn.org/en/stable/settings.html#worker-class

如何选择您的 worker 类型: http://docs.gunicorn.org/en/latest/design.html#choosing-a-worker-type

这里有一个很好的解释: How many concurrent requests does a single Flask process receive?