Return-Path: X-Original-To: apmail-cassandra-commits-archive@www.apache.org Delivered-To: apmail-cassandra-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 30C3D18C46 for ; Mon, 22 Feb 2016 17:30:48 +0000 (UTC) Received: (qmail 48645 invoked by uid 500); 22 Feb 2016 17:30:22 -0000 Delivered-To: apmail-cassandra-commits-archive@cassandra.apache.org Received: (qmail 48513 invoked by uid 500); 22 Feb 2016 17:30:18 -0000 Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@cassandra.apache.org Delivered-To: mailing list commits@cassandra.apache.org Received: (qmail 48477 invoked by uid 99); 22 Feb 2016 17:30:18 -0000 Received: from arcas.apache.org (HELO arcas) (140.211.11.28) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 22 Feb 2016 17:30:18 +0000 Received: from arcas.apache.org (localhost [127.0.0.1]) by arcas (Postfix) with ESMTP id 5DDE32C14E1 for ; Mon, 22 Feb 2016 17:30:18 +0000 (UTC) Date: Mon, 22 Feb 2016 17:30:18 +0000 (UTC) From: "Michael Kjellman (JIRA)" To: commits@cassandra.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Commented] (CASSANDRA-11206) Support large partitions on the 3.0 sstable format 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/CASSANDRA-11206?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15157346#comment-15157346 ] Michael Kjellman commented on CASSANDRA-11206: ---------------------------------------------- The IndexEntry objects are currently variable length [~jbellis] which might make this a bit complicated on the read path. Also, how many elements would need to be deserialized at minimum? Whatever the bucket size used for the skip list implementation? > Support large partitions on the 3.0 sstable format > -------------------------------------------------- > > Key: CASSANDRA-11206 > URL: https://issues.apache.org/jira/browse/CASSANDRA-11206 > Project: Cassandra > Issue Type: Improvement > Reporter: Jonathan Ellis > Fix For: 3.x > > > Cassandra saves a sample of IndexInfo objects that store the offset within each partition of every 64KB (by default) range of rows. To find a row, we binary search this sample, then scan the partition of the appropriate range. > The problem is that this scales poorly as partitions grow: on a cache miss, we deserialize the entire set of IndexInfo, which both creates a lot of GC overhead (as noted in CASSANDRA-9754) but is also non-negligible i/o activity (relative to reading a single 64KB row range) as partitions get truly large. > We introduced an "offset map" in CASSANDRA-10314 that allows us to perform the IndexInfo bsearch while only deserializing IndexInfo that we need to compare against, i.e. log(N) deserializations. -- This message was sent by Atlassian JIRA (v6.3.4#6332)