From patchwork Fri Oct 10 14:23:23 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jan Kara X-Patchwork-Id: 5066091 Return-Path: X-Original-To: patchwork-ocfs2-devel@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork2.web.kernel.org (Postfix) with ESMTP id 12323C11AC for ; Fri, 10 Oct 2014 14:28:45 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 25F6620222 for ; Fri, 10 Oct 2014 14:28:44 +0000 (UTC) Received: from aserp1040.oracle.com (aserp1040.oracle.com [141.146.126.69]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 1866E2020F for ; Fri, 10 Oct 2014 14:28:43 +0000 (UTC) Received: from acsinet22.oracle.com (acsinet22.oracle.com [141.146.126.238]) by aserp1040.oracle.com (Sentrion-MTA-4.3.2/Sentrion-MTA-4.3.2) with ESMTP id s9AESSwR019141 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 10 Oct 2014 14:28:28 GMT Received: from oss.oracle.com (oss-external.oracle.com [137.254.96.51]) by acsinet22.oracle.com (8.14.4+Sun/8.14.4) with ESMTP id s9AESR9i007556 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 10 Oct 2014 14:28:28 GMT Received: from localhost ([127.0.0.1] helo=oss.oracle.com) by oss.oracle.com with esmtp (Exim 4.63) (envelope-from ) id 1Xcb8A-0001CV-Nm; Fri, 10 Oct 2014 07:25:18 -0700 Received: from ucsinet22.oracle.com ([156.151.31.94]) by oss.oracle.com with esmtp (Exim 4.63) (envelope-from ) id 1Xcb75-00012j-1Q for ocfs2-devel@oss.oracle.com; Fri, 10 Oct 2014 07:24:11 -0700 Received: from userp1020.oracle.com (userp1020.oracle.com [156.151.31.79]) by ucsinet22.oracle.com (8.14.5+Sun/8.14.5) with ESMTP id s9AEOALK008358 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=FAIL) for ; Fri, 10 Oct 2014 14:24:10 GMT Received: from userp2030.oracle.com (userp2030.oracle.com [156.151.31.89]) by userp1020.oracle.com (Sentrion-MTA-4.3.2/Sentrion-MTA-4.3.2) with ESMTP id s9AEOAwb004465 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Fri, 10 Oct 2014 14:24:10 GMT Received: from pps.filterd (userp2030.oracle.com [127.0.0.1]) by userp2030.oracle.com (8.14.7/8.14.7) with SMTP id s9AENsLs036946 for ; Fri, 10 Oct 2014 14:24:10 GMT Received: from mx2.suse.de (cantor2.suse.de [195.135.220.15]) by userp2030.oracle.com with ESMTP id 1px7147ht1-1 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NOT) for ; Fri, 10 Oct 2014 14:24:09 +0000 Received: from relay1.suse.de (charybdis-ext.suse.de [195.135.220.254]) by mx2.suse.de (Postfix) with ESMTP id C5CE7ADE4; Fri, 10 Oct 2014 14:24:03 +0000 (UTC) Received: by quack.suse.cz (Postfix, from userid 1000) id B97C581FE4; Fri, 10 Oct 2014 16:24:01 +0200 (CEST) From: Jan Kara To: linux-fsdevel@vger.kernel.org Date: Fri, 10 Oct 2014 16:23:23 +0200 Message-Id: <1412951028-4085-19-git-send-email-jack@suse.cz> X-Mailer: git-send-email 1.8.1.4 In-Reply-To: <1412951028-4085-1-git-send-email-jack@suse.cz> References: <1412951028-4085-1-git-send-email-jack@suse.cz> X-ServerName: cantor2.suse.de X-Proofpoint-Virus-Version: vendor=nai engine=5600 definitions=7586 signatures=670543 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 suspectscore=3 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=7.0.1-1402240000 definitions=main-1410100121 Cc: Dave Kleikamp , jfs-discussion@lists.sourceforge.net, tytso@mit.edu, Jeff Mahoney , Mark Fasheh , Dave Chinner , reiserfs-devel@vger.kernel.org, xfs@oss.sgi.com, cluster-devel@redhat.com, Jan Kara , linux-ext4@vger.kernel.org, Steven Whitehouse , ocfs2-devel@oss.oracle.com, viro@zeniv.linux.org.uk Subject: [Ocfs2-devel] [PATCH 1/2] jbd2: Avoid pointless scanning of checkpoint lists X-BeenThere: ocfs2-devel@oss.oracle.com X-Mailman-Version: 2.1.9 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: ocfs2-devel-bounces@oss.oracle.com Errors-To: ocfs2-devel-bounces@oss.oracle.com X-Source-IP: acsinet22.oracle.com [141.146.126.238] X-Spam-Status: No, score=-5.2 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_MED, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Yuanhan has reported that when he is running fsync(2) heavy workload creating new files over ramdisk, significant amount of time is spent in __jbd2_journal_clean_checkpoint_list() trying to clean old transactions (but they cannot be cleaned up because flusher hasn't yet checkpointed those buffers). The workload can be generated by: fs_mark -d /fs/ram0/1 -D 2 -N 2560 -n 1000000 -L 1 -S 1 -s 4096 Reduce the amount of scanning by stopping to scan the transaction list once we find a transaction that cannot be checkpointed. Note that this way of cleaning is still enough to keep freeing space in the journal after fully checkpointed transactions. Reported-and-tested-by: Yuanhan Liu Signed-off-by: Jan Kara --- fs/jbd2/checkpoint.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 7f34f4716165..e39b2d0e1079 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -478,7 +478,6 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * Find all the written-back checkpoint buffers in the given list and * release them. * - * Called with the journal locked. * Called with j_list_lock held. * Returns number of buffers reaped (for debug) */ @@ -498,12 +497,12 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released) jh = next_jh; next_jh = jh->b_cpnext; ret = __try_to_free_cp_buf(jh); - if (ret) { - freed++; - if (ret == 2) { - *released = 1; - return freed; - } + if (!ret) + return freed; + freed++; + if (ret == 2) { + *released = 1; + return freed; } /* * This function only frees up some memory @@ -523,7 +522,6 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released) * * Find all the written-back checkpoint buffers in the journal and release them. * - * Called with the journal locked. * Called with j_list_lock held. * Returns number of buffers reaped (for debug) */ @@ -531,7 +529,8 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released) int __jbd2_journal_clean_checkpoint_list(journal_t *journal) { transaction_t *transaction, *last_transaction, *next_transaction; - int ret = 0; + int ret; + int freed = 0; int released; transaction = journal->j_checkpoint_transactions; @@ -543,17 +542,21 @@ int __jbd2_journal_clean_checkpoint_list(journal_t *journal) do { transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret += journal_clean_one_cp_list(transaction-> + ret = journal_clean_one_cp_list(transaction-> t_checkpoint_list, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if * preemption requested: */ - if (need_resched()) + if (need_resched()) { + freed += ret; goto out; - if (released) + } + if (released) { + freed += ret; continue; + } /* * It is essential that we are as careful as in the case of * t_checkpoint_list with removing the buffer from the list as @@ -561,11 +564,12 @@ int __jbd2_journal_clean_checkpoint_list(journal_t *journal) */ ret += journal_clean_one_cp_list(transaction-> t_checkpoint_io_list, &released); - if (need_resched()) + freed += ret; + if (need_resched() || !ret) goto out; } while (transaction != last_transaction); out: - return ret; + return freed; } /*