[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Tue, 4 Apr 2017 15:09:26 +0200
From: Christoph Hellwig <hch@....de>
To: Max Gurtovoy <maxg@...lanox.com>
Cc: Sagi Grimberg <sagi@...mberg.me>, linux-rdma@...r.kernel.org,
linux-nvme@...ts.infradead.org, linux-block@...r.kernel.org,
netdev@...r.kernel.org, Saeed Mahameed <saeedm@...lanox.com>,
Or Gerlitz <ogerlitz@...lanox.com>,
Christoph Hellwig <hch@....de>
Subject: Re: [PATCH rfc 5/6] block: Add rdma affinity based queue mapping
helper
On Tue, Apr 04, 2017 at 10:46:54AM +0300, Max Gurtovoy wrote:
>> + if (set->nr_hw_queues > dev->num_comp_vectors)
>> + goto fallback;
>> +
>> + for (queue = 0; queue < set->nr_hw_queues; queue++) {
>> + mask = ib_get_vector_affinity(dev, first_vec + queue);
>> + if (!mask)
>> + goto fallback;
>
> Christoph,
> we can use fallback also in the blk-mq-pci.c in case pci_irq_get_affinity
> fails, right ?
For PCI it shouldn't fail as the driver calling pci_irq_get_affinity
knows how it set up the interrupts. So I don't think it's necessary there.
Powered by blists - more mailing lists