Return-Path: X-Original-To: archive-asf-public-internal@cust-asf2.ponee.io Delivered-To: archive-asf-public-internal@cust-asf2.ponee.io Received: from cust-asf.ponee.io (cust-asf.ponee.io [163.172.22.183]) by cust-asf2.ponee.io (Postfix) with ESMTP id 413CE200CE6 for ; Fri, 15 Sep 2017 21:52:08 +0200 (CEST) Received: by cust-asf.ponee.io (Postfix) id 400291609D5; Fri, 15 Sep 2017 19:52:08 +0000 (UTC) Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by cust-asf.ponee.io (Postfix) with SMTP id 60F3E1609D3 for ; Fri, 15 Sep 2017 21:52:07 +0200 (CEST) Received: (qmail 25495 invoked by uid 500); 15 Sep 2017 19:52:04 -0000 Mailing-List: contact commits-help@hive.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hive-dev@hive.apache.org Delivered-To: mailing list commits@hive.apache.org Received: (qmail 24416 invoked by uid 99); 15 Sep 2017 19:52:03 -0000 Received: from git1-us-west.apache.org (HELO git1-us-west.apache.org) (140.211.11.23) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 15 Sep 2017 19:52:03 +0000 Received: by git1-us-west.apache.org (ASF Mail Server at git1-us-west.apache.org, from userid 33) id 27231F5837; Fri, 15 Sep 2017 19:52:03 +0000 (UTC) Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: sershe@apache.org To: commits@hive.apache.org Date: Fri, 15 Sep 2017 19:52:16 -0000 Message-Id: <9283be8c5b2d4b23847dc63b89cbc2e3@git.apache.org> In-Reply-To: <4a8ee0b72b89425a9f879cf4215e7736@git.apache.org> References: <4a8ee0b72b89425a9f879cf4215e7736@git.apache.org> X-Mailer: ASF-Git Admin Mailer Subject: [15/31] hive git commit: HIVE-17522: cleanup old 'repl dump' dirs (Tao Li, reviewed by Daniel Dai) archived-at: Fri, 15 Sep 2017 19:52:08 -0000 HIVE-17522: cleanup old 'repl dump' dirs (Tao Li, reviewed by Daniel Dai) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/4d8b194b Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/4d8b194b Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/4d8b194b Branch: refs/heads/hive-14535 Commit: 4d8b194bd55575b29caa256d09066fce6cd86c6a Parents: c925cf8 Author: Daniel Dai Authored: Thu Sep 14 00:18:22 2017 -0700 Committer: Daniel Dai Committed: Thu Sep 14 00:18:22 2017 -0700 ---------------------------------------------------------------------- .../org/apache/hadoop/hive/conf/HiveConf.java | 6 +++ .../hadoop/hive/metastore/HiveMetaStore.java | 7 +++ .../hive/metastore/repl/DumpDirCleanerTask.java | 45 ++++++++++++++++++++ 3 files changed, 58 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/4d8b194b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java ---------------------------------------------------------------------- diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 24c5db0..e9480a9 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -449,6 +449,12 @@ public class HiveConf extends Configuration { "lead to an task increment that would cross the above limit"), REPL_PARTITIONS_DUMP_PARALLELISM("hive.repl.partitions.dump.parallelism",5, "Number of threads that will be used to dump partition data information during repl dump."), + REPL_DUMPDIR_CLEAN_FREQ("hive.repl.dumpdir.clean.freq", "0s", + new TimeValidator(TimeUnit.SECONDS), + "Frequency at which timer task runs to purge expired dump dirs."), + REPL_DUMPDIR_TTL("hive.repl.dumpdir.ttl", "7d", + new TimeValidator(TimeUnit.DAYS), + "TTL of dump dirs before cleanup."), LOCALSCRATCHDIR("hive.exec.local.scratchdir", "${system:java.io.tmpdir}" + File.separator + "${system:user.name}", "Local scratch space for Hive jobs"), http://git-wip-us.apache.org/repos/asf/hive/blob/4d8b194b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java ---------------------------------------------------------------------- diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java index 6393c8e..53cb3d9 100644 --- a/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java @@ -127,6 +127,7 @@ import org.apache.hadoop.hive.metastore.metrics.Metrics; import org.apache.hadoop.hive.metastore.metrics.MetricsConstants; import org.apache.hadoop.hive.metastore.metrics.PerfLogger; import org.apache.hadoop.hive.metastore.partition.spec.PartitionSpecProxy; +import org.apache.hadoop.hive.metastore.repl.DumpDirCleanerTask; import org.apache.hadoop.hive.metastore.security.HadoopThriftAuthBridge; import org.apache.hadoop.hive.metastore.security.MetastoreDelegationTokenManager; import org.apache.hadoop.hive.metastore.security.TUGIContainingTransport; @@ -538,6 +539,12 @@ public class HiveMetaStore extends ThriftHiveMetastore { cleaner.schedule(new EventCleanerTask(this), cleanFreq, cleanFreq); } + cleanFreq = hiveConf.getTimeVar(ConfVars.REPL_DUMPDIR_CLEAN_FREQ, TimeUnit.MILLISECONDS); + if (cleanFreq > 0) { + // In default config, there is no timer. + Timer cleaner = new Timer("Repl Dump Dir Cleaner Thread", true); + cleaner.schedule(new DumpDirCleanerTask(hiveConf), cleanFreq, cleanFreq); + } expressionProxy = PartFilterExprUtil.createExpressionProxy(hiveConf); fileMetadataManager = new FileMetadataManager((ThreadLocalRawStore)this, hiveConf); } http://git-wip-us.apache.org/repos/asf/hive/blob/4d8b194b/metastore/src/java/org/apache/hadoop/hive/metastore/repl/DumpDirCleanerTask.java ---------------------------------------------------------------------- diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/repl/DumpDirCleanerTask.java b/metastore/src/java/org/apache/hadoop/hive/metastore/repl/DumpDirCleanerTask.java new file mode 100644 index 0000000..3374789 --- /dev/null +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/repl/DumpDirCleanerTask.java @@ -0,0 +1,45 @@ +package org.apache.hadoop.hive.metastore.repl; + +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.conf.HiveConf; +import org.apache.hadoop.hive.conf.HiveConf.ConfVars; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.TimerTask; +import java.util.concurrent.TimeUnit; + +public class DumpDirCleanerTask extends TimerTask { + public static final Logger LOG = LoggerFactory.getLogger(DumpDirCleanerTask.class); + private final HiveConf conf; + private final Path dumpRoot; + private final long ttl; + + public DumpDirCleanerTask(HiveConf conf) { + this.conf = conf; + dumpRoot = new Path(conf.getVar(HiveConf.ConfVars.REPLDIR)); + ttl = conf.getTimeVar(ConfVars.REPL_DUMPDIR_TTL, TimeUnit.MILLISECONDS); + } + + @Override + public void run() { + LOG.debug("Trying to delete old dump dirs"); + try { + FileSystem fs = FileSystem.get(dumpRoot.toUri(), conf); + FileStatus[] statuses = fs.listStatus(dumpRoot); + for (FileStatus status : statuses) + { + if (status.getModificationTime() < System.currentTimeMillis() - ttl) + { + fs.delete(status.getPath(), true); + LOG.info("Deleted old dump dir: " + status.getPath()); + } + } + } catch (IOException e) { + LOG.error("Error while trying to delete dump dir", e); + } + } +}