Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753960Ab0K0Kcx (ORCPT ); Sat, 27 Nov 2010 05:32:53 -0500 Received: from ipmail04.adl6.internode.on.net ([150.101.137.141]:34786 "EHLO ipmail04.adl6.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752829Ab0K0K0P (ORCPT ); Sat, 27 Nov 2010 05:26:15 -0500 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: ApcFAO1p8Ex5Lcx2/2dsb2JhbACVC44Acr12hUcEimGFFA Message-Id: <799862eb7c0ddb2b9c4bdb450035adb5f57b294f.1290852959.git.npiggin@kernel.dk> In-Reply-To: References: From: Nick Piggin Date: Sat, 27 Nov 2010 20:44:56 +1100 Subject: [PATCH 26/46] fs: dcache reduce prune_one_dentry locking To: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1729 Lines: 64 prune_one_dentry can avoid quite a bit of locking in the common case where ancestors have an elevated refcount. Alternatively, we could have gone the other way and made fewer trylocks in the case where d_count goes to zero, but is probably less common. Signed-off-by: Nick Piggin --- fs/dcache.c | 27 +++++++++++++++------------ 1 files changed, 15 insertions(+), 12 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index 23f6fed..4fa27b5 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -547,26 +547,29 @@ static void prune_one_dentry(struct dentry *dentry, struct dentry *parent) * Prune ancestors. */ while (dentry) { - spin_lock(&dcache_inode_lock); -again: +relock: spin_lock(&dentry->d_lock); + if (dentry->d_count > 1) { + dentry->d_count--; + spin_unlock(&dentry->d_lock); + return; + } + if (!spin_trylock(&dcache_inode_lock)) { +relock2: + spin_unlock(&dentry->d_lock); + cpu_relax(); + goto relock; + } + if (IS_ROOT(dentry)) parent = NULL; else parent = dentry->d_parent; if (parent && !spin_trylock(&parent->d_lock)) { - spin_unlock(&dentry->d_lock); - goto again; - } - dentry->d_count--; - if (dentry->d_count) { - if (parent) - spin_unlock(&parent->d_lock); - spin_unlock(&dentry->d_lock); spin_unlock(&dcache_inode_lock); - return; + goto relock2; } - + dentry->d_count--; dentry_lru_del(dentry); __d_drop(dentry); dentry = d_kill(dentry, parent); -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/