[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH 09/15] swiotlb: make the swiotlb_init interface more useful
- To: Nathan Chancellor <nathan@xxxxxxxxxx>
- From: Christoph Hellwig <hch@xxxxxx>
- Date: Wed, 1 Jun 2022 19:57:43 +0200
- Cc: Christoph Hellwig <hch@xxxxxx>, iommu@xxxxxxxxxxxxxxxxxxxxxxxxxx, x86@xxxxxxxxxx, Anshuman Khandual <anshuman.khandual@xxxxxxx>, Tom Lendacky <thomas.lendacky@xxxxxxx>, Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>, Stefano Stabellini <sstabellini@xxxxxxxxxx>, Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>, Juergen Gross <jgross@xxxxxxxx>, Joerg Roedel <joro@xxxxxxxxxx>, David Woodhouse <dwmw2@xxxxxxxxxxxxx>, Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>, Robin Murphy <robin.murphy@xxxxxxx>, linux-arm-kernel@xxxxxxxxxxxxxxxxxxx, xen-devel@xxxxxxxxxxxxxxxxxxxx, linux-ia64@xxxxxxxxxxxxxxx, linux-mips@xxxxxxxxxxxxxxx, linuxppc-dev@xxxxxxxxxxxxxxxx, linux-riscv@xxxxxxxxxxxxxxxxxxx, linux-s390@xxxxxxxxxxxxxxx, linux-hyperv@xxxxxxxxxxxxxxx, tboot-devel@xxxxxxxxxxxxxxxxxxxxx, linux-pci@xxxxxxxxxxxxxxx
- Delivery-date: Wed, 01 Jun 2022 17:58:02 +0000
- List-id: Xen developer discussion <xen-devel.lists.xenproject.org>
On Wed, Jun 01, 2022 at 10:46:54AM -0700, Nathan Chancellor wrote:
> On Wed, Jun 01, 2022 at 07:34:41PM +0200, Christoph Hellwig wrote:
> > Can you send me the full dmesg and the content of
> > /sys/kernel/debug/swiotlb/io_tlb_nslabs for a good and a bad boot?
>
> Sure thing, they are attached! If there is anything else I can provide
> or test, I am more than happy to do so.
Nothing interesting. But the performance numbers almost look like
swiotlb=force got ignored before (even if I can't explain why).
Do you get a similar performance with the new kernel without
swiotlb=force as the old one with that argument by any chance?
|
