Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760096AbXJEJrU (ORCPT ); Fri, 5 Oct 2007 05:47:20 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754064AbXJEJrK (ORCPT ); Fri, 5 Oct 2007 05:47:10 -0400 Received: from viefep18-int.chello.at ([213.46.255.22]:18436 "EHLO viefep33-int.chello.at" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753928AbXJEJrI (ORCPT ); Fri, 5 Oct 2007 05:47:08 -0400 Subject: Re: [PATCH] remove throttle_vm_writeout() From: Peter Zijlstra To: Miklos Szeredi Cc: akpm@linux-foundation.org, wfg@mail.ustc.edu.cn, linux-mm@kvack.org, linux-kernel@vger.kernel.org In-Reply-To: References: <20071004145640.18ced770.akpm@linux-foundation.org> <20071004160941.e0c0c7e5.akpm@linux-foundation.org> <20071004164801.d8478727.akpm@linux-foundation.org> <20071004174851.b34a3220.akpm@linux-foundation.org> <1191572520.22357.42.camel@twins> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-sTHr541QelHxWYI4WmLX" Date: Fri, 05 Oct 2007 11:47:03 +0200 Message-Id: <1191577623.22357.69.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.10.1 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3428 Lines: 110 --=-sTHr541QelHxWYI4WmLX Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Fri, 2007-10-05 at 11:22 +0200, Miklos Szeredi wrote: > > So how do we end up with more writeback pages than that? should we teac= h > > pdflush about these limits as well? >=20 > Ugh. >=20 > I think we should rather fix vmscan to not spin when all pages of a > zone are already under writeout. Which is the _real_ problem, > according to Andrew. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 4ef4d22..eff2438 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -88,7 +88,7 @@ static inline void wait_on_inode(struct inode *inode) int wakeup_pdflush(long nr_pages); void laptop_io_completion(void); void laptop_sync_completion(void); -void throttle_vm_writeout(gfp_t gfp_mask); +void throttle_vm_writeout(struct zone *zone, gfp_t gfp_mask); =20 /* These are exported to sysctl. */ extern int dirty_background_ratio; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index eec1481..f949997 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -326,11 +326,8 @@ void balance_dirty_pages_ratelimited_nr(struct address= _space *mapping, } EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr); =20 -void throttle_vm_writeout(gfp_t gfp_mask) +void throttle_vm_writeout(struct zone *zone, gfp_t gfp_mask) { - long background_thresh; - long dirty_thresh; - if ((gfp_mask & (__GFP_FS|__GFP_IO)) !=3D (__GFP_FS|__GFP_IO)) { /* * The caller might hold locks which can prevent IO completion @@ -342,17 +339,16 @@ void throttle_vm_writeout(gfp_t gfp_mask) } =20 for ( ; ; ) { - get_dirty_limits(&background_thresh, &dirty_thresh, NULL); + unsigned long thresh =3D zone_page_state(zone, NR_ACTIVE) + + zone_page_state(zone, NR_INACTIVE); =20 - /* - * Boost the allowable dirty threshold a bit for page - * allocators so they don't get DoS'ed by heavy writers - */ - dirty_thresh +=3D dirty_thresh / 10; /* wheeee... */ + /* + * wait when 75% of the zone's pages are under writeback + */ + thresh -=3D thresh >> 2; + if (zone_page_state(zone, NR_WRITEBACK) < thresh) + break; =20 - if (global_page_state(NR_UNSTABLE_NFS) + - global_page_state(NR_WRITEBACK) <=3D dirty_thresh) - break; congestion_wait(WRITE, HZ/10); } } diff --git a/mm/vmscan.c b/mm/vmscan.c index 1be5a63..7dd6bd9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -948,7 +948,7 @@ static unsigned long shrink_zone(int priority, struct z= one *zone, } } =20 - throttle_vm_writeout(sc->gfp_mask); + throttle_vm_writeout(zone, sc->gfp_mask); =20 atomic_dec(&zone->reclaim_in_progress); return nr_reclaimed; --=-sTHr541QelHxWYI4WmLX Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQBHBggXXA2jU0ANEf4RAoYxAJ0SsPUjcXeXb4YNTjDKwSqGJ/vtQwCfaqfU FhuArBz9ahCcgdqUfMFP97w= =ADs0 -----END PGP SIGNATURE----- --=-sTHr541QelHxWYI4WmLX-- - 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/