From dev-return-16959-apmail-drill-dev-archive=drill.apache.org@drill.apache.org Fri Oct 2 00:11:55 2015 Return-Path: X-Original-To: apmail-drill-dev-archive@www.apache.org Delivered-To: apmail-drill-dev-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id CF3A718D63 for ; Fri, 2 Oct 2015 00:11:55 +0000 (UTC) Received: (qmail 53514 invoked by uid 500); 2 Oct 2015 00:11:50 -0000 Delivered-To: apmail-drill-dev-archive@drill.apache.org Received: (qmail 53456 invoked by uid 500); 2 Oct 2015 00:11:50 -0000 Mailing-List: contact dev-help@drill.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@drill.apache.org Delivered-To: mailing list dev@drill.apache.org Received: (qmail 53444 invoked by uid 99); 2 Oct 2015 00:11:50 -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, 02 Oct 2015 00:11:50 +0000 Received: by git1-us-west.apache.org (ASF Mail Server at git1-us-west.apache.org, from userid 33) id B74E6E154E; Fri, 2 Oct 2015 00:11:49 +0000 (UTC) From: amansinha100 To: dev@drill.apache.org Reply-To: dev@drill.apache.org References: In-Reply-To: Subject: [GitHub] drill pull request: DRILL-3884: Fix lower parallelization issues w... Content-Type: text/plain Message-Id: <20151002001149.B74E6E154E@git1-us-west.apache.org> Date: Fri, 2 Oct 2015 00:11:49 +0000 (UTC) Github user amansinha100 commented on a diff in the pull request: https://github.com/apache/drill/pull/185#discussion_r40981727 --- Diff: contrib/storage-hive/core/src/main/java/org/apache/drill/exec/store/hive/HiveScan.java --- @@ -319,16 +319,12 @@ public ScanStats getScanStats() { estRowCount = data/1024; } - // Hive's native reader is neither memory efficient nor fast. If the rowcount is below - // HIVE_SERDE_SCAN_OVERHEAD_FACTOR, make sure it is at least HIVE_SERDE_SCAN_OVERHEAD_FACTOR to enable the planner - // to choose HiveDrillNativeParquetScan. Due to the project on top of HiveDrillNativeParquetScan, we end up - // choosing the HiveScan instead of HiveDrillNativeParquetScan if the cost is too low. - if (estRowCount <= HIVE_SERDE_SCAN_OVERHEAD_FACTOR) { - estRowCount = HIVE_SERDE_SCAN_OVERHEAD_FACTOR; - } + // Hive's native reader is neither memory efficient nor fast. Increase the CPU cost + // by a factor to let the planner choose HiveDrillNativeScan over HiveScan with SerDes. + float cpuCost = 1 * HIVE_SERDE_SCAN_OVERHEAD_FACTOR; --- End diff -- I am thinking this cost should include the number of columns as well...suppose there are lots of columns(e.g 500), we want both types of plans to be equally penalized. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastructure@apache.org or file a JIRA ticket with INFRA. ---