[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <fe365aa8-00d5-153d-ceb2-f887a71a6927@acm.org>
Date: Wed, 8 Jun 2022 10:33:26 -0700
From: Bart Van Assche <bvanassche@....org>
To: John Garry <john.garry@...wei.com>,
damien.lemoal@...nsource.wdc.com, joro@...tes.org, will@...nel.org,
jejb@...ux.ibm.com, martin.petersen@...cle.com, hch@....de,
m.szyprowski@...sung.com, robin.murphy@....com
Cc: linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-ide@...r.kernel.org, iommu@...ts.linux-foundation.org,
linux-scsi@...r.kernel.org, liyihang6@...ilicon.com,
chenxiang66@...ilicon.com, thunder.leizhen@...wei.com
Subject: Re: [PATCH v3 3/4] scsi: core: Cap shost max_sectors according to DMA
optimum mapping limits
On 6/6/22 02:30, John Garry wrote:
> + if (dma_dev->dma_mask) {
> + shost->max_sectors = min_t(unsigned int, shost->max_sectors,
> + dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
> + }
Since IOVA_RANGE_CACHE_MAX_SIZE = 6 this limits max_sectors to 2**6 *
PAGE_SIZE or 256 KiB if the page size is 4 KiB. I think that's too
small. Some (SRP) storage arrays require much larger transfers to
achieve optimal performance.
Thanks,
Bart.
Powered by blists - more mailing lists