Return-Path: X-Original-To: apmail-hadoop-hdfs-issues-archive@minotaur.apache.org Delivered-To: apmail-hadoop-hdfs-issues-archive@minotaur.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id A7FF91880C for ; Mon, 28 Sep 2015 18:16:11 +0000 (UTC) Received: (qmail 73393 invoked by uid 500); 28 Sep 2015 18:16:05 -0000 Delivered-To: apmail-hadoop-hdfs-issues-archive@hadoop.apache.org Received: (qmail 73338 invoked by uid 500); 28 Sep 2015 18:16:05 -0000 Mailing-List: contact hdfs-issues-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hdfs-issues@hadoop.apache.org Delivered-To: mailing list hdfs-issues@hadoop.apache.org Received: (qmail 73325 invoked by uid 99); 28 Sep 2015 18:16:05 -0000 Received: from arcas.apache.org (HELO arcas.apache.org) (140.211.11.28) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 28 Sep 2015 18:16:05 +0000 Date: Mon, 28 Sep 2015 18:16:05 +0000 (UTC) From: "Jing Zhao (JIRA)" To: hdfs-issues@hadoop.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Commented] (HDFS-9106) Transfer failure during pipeline recovery causes permanent write failures MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 [ https://issues.apache.org/jira/browse/HDFS-9106?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14933698#comment-14933698 ] Jing Zhao commented on HDFS-9106: --------------------------------- +1 for the latest patch. Thanks [~kihwal]. > Transfer failure during pipeline recovery causes permanent write failures > ------------------------------------------------------------------------- > > Key: HDFS-9106 > URL: https://issues.apache.org/jira/browse/HDFS-9106 > Project: Hadoop HDFS > Issue Type: Bug > Reporter: Kihwal Lee > Assignee: Kihwal Lee > Priority: Critical > Attachments: HDFS-9106-poc.patch, HDFS-9106.patch > > > When a new node is added to a write pipeline during flush/sync, if the partial block transfer fails, the write will fail permanently without retrying or continuing with whatever is in the pipeline. > The transfer often fails in busy clusters due to timeout. There is no per-packet ACK between client and datanode or between source and target datanodes. If the total transfer time exceeds the configured timeout + 10 seconds (2 * 5 seconds slack), it is considered failed. Naturally, the failure rate is higher with bigger block sizes. > I propose following changes: > - Transfer timeout needs to be different from per-packet timeout. > - transfer should be retried if fails. -- This message was sent by Atlassian JIRA (v6.3.4#6332)