python - 为什么 Rexster Server(和 Titan)停止响应？

Question

设置

我正在使用 Titan Rexster (titan-server-0.4.4.zip) 和 Elasticsearch 后端实现一个在 Ubuntu 12.4 服务器上运行的推荐系统。为了连接到 Rexster 服务器，我使用了 Python 的 Bulbflow 库。

Beta 似乎可以正常运行 3 周，但随着负载“增加”(只有几个用户~10)，Rexster 服务器停止响应。不知道是我的rexster配置有误还是没有正确使用Bulbflow库。

Rexster/Titan 配置

这是我的 rexster-cassandra-es.xml:

    <?xml version="1.0" encoding="UTF-8"?>
    <rexster>
        <http>
            <server-port>8182</server-port>
            <server-host>0.0.0.0</server-host>
            <base-uri>http://MY_IP</base-uri>
            <web-root>public</web-root>
            <character-set>UTF-8</character-set>
            <enable-jmx>false</enable-jmx>
            <enable-doghouse>true</enable-doghouse>
            <max-post-size>2097152</max-post-size>
            <max-header-size>8192</max-header-size>
            <upload-timeout-millis>30000</upload-timeout-millis>
            <thread-pool>
                <worker>
                    <core-size>20</core-size>
                    <max-size>40</max-size>
                </worker>
                <kernal>
                    <core-size>10</core-size>
                    <max-size>20</max-size>
                </kernal>
            </thread-pool>
            <io-strategy>leader-follower</io-strategy>
        </http>
        <rexpro>
            <server-port>8184</server-port>
            <server-host>0.0.0.0</server-host>
            <session-max-idle>1790000</session-max-idle>
            <session-check-interval>3000000</session-check-interval>
            <connection-max-idle>180000</connection-max-idle>
            <connection-check-interval>3000000</connection-check-interval>
            <enable-jmx>false</enable-jmx>
            <thread-pool>
                <worker>
                    <core-size>8</core-size>
                    <max-size>8</max-size>
                </worker>
                <kernal>
                    <core-size>4</core-size>
                    <max-size>4</max-size>
                </kernal>
            </thread-pool>
            <io-strategy>leader-follower</io-strategy>
        </rexpro>
        <shutdown-port>8183</shutdown-port>
        <shutdown-host>127.0.0.1</shutdown-host>
        <script-engines>
            <script-engine>
                <name>gremlin-groovy</name>
                <reset-threshold>-1</reset-threshold>
                <imports>com.tinkerpop.gremlin.*,com.tinkerpop.gremlin.java.*,com.tinkerpop.gremlin.pipes.filter.*,com.tinkerpop.gremlin.pipes.sideeffect.*,com.tinkerpop.gremlin.pipes.transform.*,com.tinkerpop.blueprints.*,com.tinkerpop.blueprints.impls.*,com.tinkerpop.blueprints.impls.tg.*,com.tinkerpop.blueprints.impls.neo4j.*,com.tinkerpop.blueprints.impls.neo4j.batch.*,com.tinkerpop.blueprints.impls.orient.*,com.tinkerpop.blueprints.impls.orient.batch.*,com.tinkerpop.blueprints.impls.dex.*,com.tinkerpop.blueprints.impls.rexster.*,com.tinkerpop.blueprints.impls.sail.*,com.tinkerpop.blueprints.impls.sail.impls.*,com.tinkerpop.blueprints.util.*,com.tinkerpop.blueprints.util.io.*,com.tinkerpop.blueprints.util.io.gml.*,com.tinkerpop.blueprints.util.io.graphml.*,com.tinkerpop.blueprints.util.io.graphson.*,com.tinkerpop.blueprints.util.wrappers.*,com.tinkerpop.blueprints.util.wrappers.batch.*,com.tinkerpop.blueprints.util.wrappers.batch.cache.*,com.tinkerpop.blueprints.util.wrappers.event.*,com.tinkerpop.blueprints.util.wrappers.event.listener.*,com.tinkerpop.blueprints.util.wrappers.id.*,com.tinkerpop.blueprints.util.wrappers.partition.*,com.tinkerpop.blueprints.util.wrappers.readonly.*,com.tinkerpop.blueprints.oupls.sail.*,com.tinkerpop.blueprints.oupls.sail.pg.*,com.tinkerpop.blueprints.oupls.jung.*,com.tinkerpop.pipes.*,com.tinkerpop.pipes.branch.*,com.tinkerpop.pipes.filter.*,com.tinkerpop.pipes.sideeffect.*,com.tinkerpop.pipes.transform.*,com.tinkerpop.pipes.util.*,com.tinkerpop.pipes.util.iterators.*,com.tinkerpop.pipes.util.structures.*,org.apache.commons.configuration.*,com.thinkaurelius.titan.core.*,com.thinkaurelius.titan.core.attribute.*,com.thinkaurelius.titan.core.util.*,com.thinkaurelius.titan.example.*,org.apache.commons.configuration.*,com.tinkerpop.gremlin.Tokens.T,com.tinkerpop.gremlin.groovy.*</imports>
            <static-imports>com.tinkerpop.blueprints.Direction.*,com.tinkerpop.blueprints.TransactionalGraph$Conclusion.*,com.tinkerpop.blueprints.Compare.*,com.thinkaurelius.titan.core.attribute.Geo.*,com.thinkaurelius.titan.core.attribute.Text.*,com.thinkaurelius.titan.core.TypeMaker$UniquenessConsistency.*,com.tinkerpop.blueprints.Query$Compare.*</static-imports>
            </script-engine>
        </script-engines>
        <security>
            <authentication>
                <type>none</type>
                <configuration>
                    <users>
                        <user>
                            <username>rexster</username>
                            <password>rexster</password>
                        </user>
                    </users>
                </configuration>
            </authentication>
        </security>
        <metrics>
            <reporter>
                <type>jmx</type>
            </reporter>
            <reporter>
                <type>http</type>
            </reporter>
            <reporter>
                <type>console</type>
                <properties>
                    <rates-time-unit>SECONDS</rates-time-unit>
                    <duration-time-unit>SECONDS</duration-time-unit>
                    <report-period>10</report-period>
                    <report-time-unit>MINUTES</report-time-unit>
                    <includes>http.rest.*</includes>
                    <excludes>http.rest.*.delete</excludes>
                </properties>
            </reporter>
        </metrics>
        <graphs>
            <graph>
                <graph-name>newspaper</graph-name>
                <graph-type>com.thinkaurelius.titan.tinkerpop.rexster.TitanGraphConfiguration</graph-type>
                <!-- <graph-location>/tmp/titan</graph-location> -->
                <graph-read-only>false</graph-read-only>
                <properties>
                    <storage.backend>cassandra</storage.backend>
                    <storage.index.search.backend>elasticsearch</storage.index.search.backend>
                    <storage.index.search.hostname>localhost</storage.index.search.hostname>
                    <storage.index.search.client-only>true</storage.index.search.client-only>
                    <storage.index.search.local-mode>false</storage.index.search.local-mode>
                </properties>
                <extensions>
                  <allows>
                    <allow>tp:gremlin</allow>
                  </allows>
                </extensions>
            </graph>
        </graphs>
    </rexster>

我已经为 worker 和 kernal 更改了线程池的核心大小和最大大小，如果不进行更改，Rexster 服务器将挂起/不响应甚至更快。

core-size 和 max-size 的合适值是多少？

Bulbflow 用法

为了使用 bulbflow，我每次需要执行请求时都会创建一个新的 Graph 对象。有很多请求，因此经常创建这些对象。

我真的应该为每个新请求创建一个新的 Graph 对象吗？

是否可以只创建一个 Graph 对象并在每次向图形数据库发送新请求时使用它，或者我是否遇到 session 问题？

错误信息

当一切都卡住并且我强行终止程序(ctrl-c)时，我得到以下堆栈跟踪:

Exception happened during processing of request from ('my_ip', 57489)
Traceback (most recent call last):
  File "/usr/lib/python2.7/SocketServer.py", line 284, in _handle_request_noblock
    self.process_request(request, client_address)
  File "/usr/lib/python2.7/SocketServer.py", line 310, in process_request
    self.finish_request(request, client_address)
  File "/usr/lib/python2.7/SocketServer.py", line 323, in finish_request
    self.RequestHandlerClass(request, client_address, self)
  File "/usr/lib/python2.7/SocketServer.py", line 638, in __init__
    self.handle()
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/werkzeug/serving.py", line 200, in handle
    rv = BaseHTTPRequestHandler.handle(self)
  File "/usr/lib/python2.7/BaseHTTPServer.py", line 340, in handle
    self.handle_one_request()
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/werkzeug/serving.py", line 235, in handle_one_request
    return self.run_wsgi()
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/werkzeug/serving.py", line 177, in run_wsgi
    execute(self.server.app)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/werkzeug/serving.py", line 165, in execute
    application_iter = app(environ, start_response)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/flask/app.py", line 1836, in __call__
    return self.wsgi_app(environ, start_response)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/flask/app.py", line 1817, in wsgi_app
    response = self.full_dispatch_request()
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/flask/app.py", line 1475, in full_dispatch_request
    rv = self.dispatch_request()
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/flask/app.py", line 1461, in dispatch_request
    return self.view_functions[rule.endpoint](**req.view_args)
  File "/home/user/dir/recommender/project/api/start.py", line 65, in put_user
    graphdb.insert_user(user_id)
  File "project/api/graphdb.py", line 14, in insert_user
    user_with_id = g.users.index.lookup(user_sqlid=user_id)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/bulbs/titan/index.py", line 270, in lookup
    resp = self.client.lookup_vertex(self.index_name,key,value)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/bulbs/titan/client.py", line 348, in lookup_vertex
    return self.request.get(path,params)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/bulbs/rest.py", line 101, in get
    return self.request(GET, path, params)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/bulbs/rest.py", line 184, in request
    http_resp = self.http.request(uri, method, body, headers)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/httplib2/__init__.py", line 1593, in request
    (response, content) = self._request(conn, authority, uri, request_uri, method, body, headers, redirections, cachekey)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/httplib2/__init__.py", line 1335, in _request
    (response, content) = self._conn_request(conn, request_uri, method, body, headers)
  File "/home/user/dir/env/venv_python/local/lib/python2.7/site-packages/httplib2/__init__.py", line 1291, in _conn_request
    response = conn.getresponse()
  File "/usr/lib/python2.7/httplib.py", line 1030, in getresponse
    response.begin()
  File "/usr/lib/python2.7/httplib.py", line 407, in begin
    version, status, reason = self._read_status()
  File "/usr/lib/python2.7/httplib.py", line 365, in _read_status
    line = self.fp.readline()
  File "/usr/lib/python2.7/socket.py", line 430, in readline
    data = recv(1)

恢复

为了恢复，我必须关闭 rexster/titan 并重新启动它。每当我停止 Rexster 服务器 (./bin/titan -c cassandra-es stop) 时，我都会收到以下输出:

Killing Titan + Rexster (pid 26779)...
Rexster shutdown timeout exceeded (60 seconds)
Killing Cassandra (pid 26201)...

Rexster 完全卡住了。

期待收到一些有用的指导。

Answer 1

Titan 邮件列表中的以下主题可能对您有用:Rexster REST API stops responding .但是，我认为他们从未设法为 Titan 解决这个问题，而且 Rexster 开发人员无法重现它。

也就是说，我强烈建议升级到 Titan v1.0.0，它使用 TinkerPop 3.0+ Gremlin 服务器而不是 TinkerPop 2.x Rexster。您将获得更少的错误、更多的功能，尤其是更具表现力的 Gremlin 查询(请参阅 TinkerPop 3.0.1 documentation used by Titan v1.0.0)。 Titan v0.4.4 是一个非常旧的版本，我认为不值得为解决这个特定问题而费心，尤其是如果您不熟悉图形。