From mboxrd@z Thu Jan 1 00:00:00 1970 From: yong.wu@mediatek.com (Yong Wu) Date: Tue, 19 Jan 2016 10:55:00 +0800 Subject: [PATCH 3/3] iommu/dma: Avoid unlikely high-order allocations In-Reply-To: References: <9a84191ed813c23db7901f8c73f514d081495bdf.1450457730.git.robin.murphy@arm.com> <8014a146e90282b8cbc5868cee0d01776670d9a6.1450457730.git.robin.murphy@arm.com> Message-ID: <1453172100.17894.9.camel@mhfsdcap03> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Fri, 2015-12-18 at 14:35 -0800, Doug Anderson wrote: > Robin, > > On Fri, Dec 18, 2015 at 9:01 AM, Robin Murphy wrote: > > Doug reports that the equivalent page allocator on 32-bit ARM exhibits > > particularly pathalogical behaviour under memory pressure when > > fragmentation is high, where allocating a 4MB buffer takes tens of > > seconds and the number of calls to alloc_pages() is over 9000![1] > > > > We can drastically improve that situation without losing the other > > benefits of high-order allocations when they would succeed, by assuming > > memory pressure is relatively constant over the course of an allocation, > > and not retrying allocations at orders we know to have failed before. > > This way, the best-case behaviour remains unchanged, and in the worst > > case we should see at most a dozen or so (MAX_ORDER - 1) failed attempts > > before falling back to single pages for the remainder of the buffer. > > > > [1]:http://lists.infradead.org/pipermail/linux-arm-kernel/2015-December/394660.html > > > > Reported-by: Douglas Anderson > > Signed-off-by: Robin Murphy > > --- > > drivers/iommu/dma-iommu.c | 6 ++++-- > > 1 file changed, 4 insertions(+), 2 deletions(-) > > Presumably it makes sense to update this based on v2 of my patch to > the original code? AKA: > ? Hi Robin, Thanks very much for this patch. And Douglas has sent his v2 which improve the flow of alloc_pages. Do you have any plan to update this patch according to this v2, or any concern about it? > _______________________________________________ > iommu mailing list > iommu at lists.linux-foundation.org > https://lists.linuxfoundation.org/mailman/listinfo/iommu