Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755608AbZFULg3 (ORCPT ); Sun, 21 Jun 2009 07:36:29 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752032AbZFULgV (ORCPT ); Sun, 21 Jun 2009 07:36:21 -0400 Received: from mk-filter-4-a-1.mail.uk.tiscali.com ([212.74.100.55]:13376 "EHLO mk-filter-4-a-1.mail.uk.tiscali.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751112AbZFULgV (ORCPT ); Sun, 21 Jun 2009 07:36:21 -0400 X-Trace: 214880603/mk-filter-4.mail.uk.tiscali.com/B2C/$b2c-THROTTLED-DYNAMIC/b2c-CUSTOMER-DYNAMIC-IP/79.69.36.136/None/hugh.dickins@tiscali.co.uk X-SBRS: None X-RemoteIP: 79.69.36.136 X-IP-MAIL-FROM: hugh.dickins@tiscali.co.uk X-SMTP-AUTH: X-MUA: X-IP-BHB: Once X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AiUFAIe3PUpPRSSI/2dsb2JhbACBUcpmhAoF X-IronPort-AV: E=Sophos;i="4.42,262,1243810800"; d="scan'208";a="214880603" Date: Sun, 21 Jun 2009 12:36:22 +0100 (BST) From: Hugh Dickins X-X-Sender: hugh@sister.anvils To: Andrey Borzenkov cc: linux-kernel@vger.kernel.org Subject: Re: Why half of slabs are not shown in /proc/slabinfo? In-Reply-To: <200906211152.25100.arvidjaar@mail.ru> Message-ID: References: <200906211152.25100.arvidjaar@mail.ru> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1145 Lines: 36 On Sun, 21 Jun 2009, Andrey Borzenkov wrote: > Mandriva kernel 2.6.30 using SLUB: > > {pts/1}% grep SLUB /boot/config > CONFIG_SLUB_DEBUG=y > CONFIG_SLUB=y > # CONFIG_SLUB_DEBUG_ON is not set > # CONFIG_SLUB_STATS is not set > > Some of slabs (e.g. filp) are not shown in /proc/slabinfo; comparing > number of entries under /sys and slabinfo results in > > {pts/0}% =ls -1 /sys/kernel/slab | grep -v : | wc -l > 131 > {pts/0}% wc -l /proc/slabinfo > 68 /proc/slabinfo > {pts/0}% > > so almost half of the all entries are missing. Is it expected or there > is something wrong here? With SLUB it is expected: unlike SLAB, it merges together caches of the same size. "slabinfo -a" (from Documentation/vm/slabinfo.c) should show you which caches have got aliased together. It can be quite tiresome if you're doing an investigation: booting with "slub_nomerge" stops it behaving like that. Hugh -- 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/