[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <55249ED9.3050605@memblaze.com>
Date: Wed, 08 Apr 2015 11:22:01 +0800
From: Chong Yuan <chong.yuan@...blaze.com>
To: nimisolo <nimisolo@...yun.com>
CC: axboe <axboe@...nel.dk>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: blk-mq : blk_mq_map_swqueue maybe
nimisolo,
在 4/8/2015 10:10 AM, nimisolo 写道:
> Hi Jens,
>
> In blk_mq_map_swqueue(), all the blk_mq_hw_ctx's nr_ctx are set
> to zero, and then each blk_mq_ctx's index_hw is set to nr_ctx.
> I think the index_hw means the index of the hardware queue that map
> to this software queue, so maybe index_hw should be set to
> blk_mq_hw_ctx's queue_num.
Multiple sw queues may be dispatched to one hw queue.
So index_hw here means the index of the sw queue in corresponding hw queue.
--yc
>
> I'm a student and I probably have misunderstood this code, please help
> me to resolve this confusion. Thank you.
>
> static void blk_mq_map_swqueue(struct request_queue *q)
> {
> .........
> queue_for_each_hw_ctx(q, hctx, i) {
> .........
> hctx->nr_ctx = 0;
> }
> .........
> queue_for_each_ctx(q, ctx, i) {
> .........
> ctx->index_hw = hctx->nr_ctx;
> .........
> }
> }
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists