httpclient 4.3 连接池卡住问题

static {
    try {
        SSLContextBuilder builder = new SSLContextBuilder();
        builder.loadTrustMaterial(null, new TrustSelfSignedStrategy());
        SSLConnectionSocketFactory sslsf = new SSLConnectionSocketFactory(builder.build());

        CookieSpecProvider easySpecProvider = new CookieSpecProvider() {

            public CookieSpec create(HttpContext context) {
                return new BrowserCompatSpec() {
                    @Override
                    public void validate(Cookie cookie, CookieOrigin origin) throws MalformedCookieException {
                        // Oh, I am easy
                    }
                };
            }

        };
        Registry<CookieSpecProvider> r = RegistryBuilder.<CookieSpecProvider> create()
                .register(CookieSpecs.BEST_MATCH, new BestMatchSpecFactory())
                .register(CookieSpecs.BROWSER_COMPATIBILITY, new BrowserCompatSpecFactory())
                .register("easy", easySpecProvider).build();
        // 5秒超时
        RequestConfig requestConfig = RequestConfig.custom().setConnectionRequestTimeout(5000)
                .setSocketTimeout(10000).setConnectTimeout(10000).setCookieSpec("easy").setRedirectsEnabled(false)
                .build();

        PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
        cm.setMaxTotal(100);// 连接池最大并发连接数
        cm.setDefaultMaxPerRoute(10);// 单路由最大并发数

        client = HttpClients.custom().setConnectionManager(cm).setDefaultCookieSpecRegistry(r)
                .setSSLSocketFactory(sslsf).setDefaultRequestConfig(requestConfig).build();
    } catch (Exception e) {
        logger.error("http client 初始化失败!", e);
    }
}

public static String execute(HttpRequest httpRequest) {
    CloseableHttpResponse response = null;
    HttpGet httpGet = null;
    HttpEntity httpEntity = null;

    try {
        httpGet = new HttpGet(httpRequest.getUrl());

        httpGet.setHeader("Connection", "close"); // 短链接
        if (httpRequest.isUseGzip()) {
            httpGet.addHeader("Accept-Encoding", "gzip,deflate,sdch");
        }
        if (!StringUtils.isEmpty(httpRequest.getContentType())) {
            httpRequest.setContentType(httpRequest.getContentType());
        }
        httpGet.addHeader("User-Agent",
                "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63");

        response = client.execute(httpGet);
        httpEntity = response.getEntity();

        // 不管状态如何, response 都需要读取
        byte[] bytes = null;
        try {
            bytes = EntityUtils.toByteArray(httpEntity);
        } catch (Exception e) {
            return null;
        }

        if (response.getStatusLine().getStatusCode() != 200) {
            logger.warn("请求异常! StatusCode: " + response.getStatusLine().getStatusCode() + ", url: "
                    + httpRequest.getUrl());
            return null;
        }
        // 确认网页编码
        @SuppressWarnings("deprecation")
        String charset = EntityUtils.getContentCharSet(httpEntity);
        if (StringUtils.isEmpty(charset)) {
            Matcher match = charsetPatterm.matcher(new String(bytes));

            if (match.find()) {
                charset = match.group(1);
            }
        }
        if (!StringUtils.isEmpty(charset)) {
            String strUtf8 = new String(new String(bytes, charset).getBytes(), GlobalConfig.ENCODING);

            return StringEscapeUtils.unescapeHtml4(strUtf8);
        }
    } catch (Exception e) {
        logger.error("抓取页面异常! url [" + httpRequest.getUrl() + "]", e);
    } finally {
        try {
            if (httpEntity != null) {
                EntityUtils.consume(httpEntity);
            }
            if (response != null) {
                response.close();
            }
            if (httpGet != null) {
                httpGet.abort();
            }
        } catch (Exception e) {
            // ignore
        }
    }

    return null;
}

这个是 httpclient 4.3 使用的代码,程序跑了一段时间使用 jstack 查看线程状态发现。

"pool-1-thread-10" prio=10 tid=0x00007f7168003000 nid=0x3e4d waiting on condition [0x00007f717c398000]
   java.lang.Thread.State: WAITING (parking)
        at sun.misc.Unsafe.park(Native Method)
        - parking to wait for  <0x00000000e69d7350> (a java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject)
        at java.util.concurrent.locks.LockSupport.park(LockSupport.java:186)
        at java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:2043)
        at org.apache.http.pool.PoolEntryFuture.await(PoolEntryFuture.java:133)
        at org.apache.http.pool.AbstractConnPool.getPoolEntryBlocking(AbstractConnPool.java:282)
        at org.apache.http.pool.AbstractConnPool.access$000(AbstractConnPool.java:64)
        at org.apache.http.pool.AbstractConnPool$2.getPoolEntry(AbstractConnPool.java:177)
        at org.apache.http.pool.AbstractConnPool$2.getPoolEntry(AbstractConnPool.java:170)
        at org.apache.http.pool.PoolEntryFuture.get(PoolEntryFuture.java:102)
        at org.apache.http.impl.conn.PoolingHttpClientConnectionManager.leaseConnection(PoolingHttpClientConnectionManager.jav
a:244)
        at org.apache.http.impl.conn.PoolingHttpClientConnectionManager$1.get(PoolingHttpClientConnectionManager.java:231)
        at org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:173)
        at org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:195)
        at org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:86)
        at org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:108)
        at org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:184)
        at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:82)
        at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:106)

其中一些线程一直卡在这,这是为什么原因呢?

阅读 22.5k
5 个回答
新手上路,请多包涵

很不幸,我遇到了和你一样的问题。请问你现在解决了吗?
我没有找到原因,我用一个map来标记每一个httpclient,发现这个httpclient处理时间过长就主动close掉,虽然比较low但是目前只有这个办法。

新手上路,请多包涵

请问下楼主这个问题的根结找到了吗?解决思路是啥?
看了我上面的评论“2.5. 连接回收策略
经典阻塞I/O模型的一个主要缺点就是只有当组侧I/O时,socket才能对I/O事件做出反应。当连接被管理器收回后,这个连接仍然存活,但是却无法监控socket的状态,也无法对I/O事件做出反馈。如果连接被服务器端关闭了,客户端监测不到连接的状态变化(也就无法根据连接状态的变化,关闭本地的socket)。
HttpClient为了缓解这一问题造成的影响,会在使用某个连接前,监测这个连接是否已经过时,如果服务器端关”
感觉有点像这个问题导致的。
急啊,在线等。。。

撰写回答
你尚未登录,登录后可以
  • 和开发者交流问题的细节
  • 关注并接收问题和回答的更新提醒
  • 参与内容的编辑和改进,让解决方法与时俱进