Re: [axboe-block:for-next] [block] bd4a633b6f: fsmark.files_per_sec -64.5% regression
- To: Niklas Cassel <cassel@kernel.org>
- Cc: Christoph Hellwig <hch@lst.de>, kernel test robot <oliver.sang@intel.com>, oe-lkp@lists.linux.dev, lkp@intel.com, Jens Axboe <axboe@kernel.dk>, Damien Le Moal <dlemoal@kernel.org>, Hannes Reinecke <hare@suse.de>, linux-m68k@lists.linux-m68k.org, linux-um@lists.infradead.org, linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, drbd-dev@lists.linbit.com, nbd@other.debian.org, linuxppc-dev@lists.ozlabs.org, ceph-devel@vger.kernel.org, virtualization@lists.linux.dev, xen-devel@lists.xenproject.org, linux-bcache@vger.kernel.org, dm-devel@lists.linux.dev, linux-raid@vger.kernel.org, linux-mmc@vger.kernel.org, linux-mtd@lists.infradead.org, nvdimm@lists.linux.dev, linux-nvme@lists.infradead.org, linux-s390@vger.kernel.org, linux-scsi@vger.kernel.org, ying.huang@intel.com, feng.tang@intel.com, fengwei.yin@intel.com
- Subject: Re: [axboe-block:for-next] [block] bd4a633b6f: fsmark.files_per_sec -64.5% regression
- From: Christoph Hellwig <hch@lst.de>
- Date: Mon, 24 Jun 2024 17:20:28 +0200
- Message-id: <[🔎] 20240624152028.GA11961@lst.de>
- In-reply-to: <[🔎] Znl4lXRmK2ukDB7r@ryzen.lan>
- References: <[🔎] 202406241546.6bbd44a7-oliver.sang@intel.com> <[🔎] 20240624083537.GA19941@lst.de> <[🔎] Znl4lXRmK2ukDB7r@ryzen.lan>
On Mon, Jun 24, 2024 at 03:45:57PM +0200, Niklas Cassel wrote:
> Seems to be ATA SSD:
> [🔎] 202406241546.6bbd44a7-oliver.sang@intel.com/job.yaml">https://download.01.org/0day-ci/archive/20240624/[🔎] 202406241546.6bbd44a7-oliver.sang@intel.com/job.yaml
>
> ssd_partitions: "/dev/disk/by-id/ata-INTEL_SSDSC2BG012T4_BTHC428201ZX1P2OGN-part1"
>
> Most likely btrfs does something different depending on the nonrot flag
> being set or not. (And like you are suggesting, most likely the value of
> the nonrot flag is somehow different after commit bd4a633b6f)
Yes, btrfs does. That's why I'm curious about the before and after,
as I can't see any way how they would be set differently. Right now
I can only claim with vitual AHCI devices, which claim to be rotational,
though.
Reply to: