LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Adam Manzanares <Adam.Manzanares@wdc.com>
To: Jeff Moyer <jmoyer@redhat.com>
Cc: "viro@zeniv.linux.org.uk" <viro@zeniv.linux.org.uk>,
	"bcrl@kvack.org" <bcrl@kvack.org>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"linux-aio@kvack.org" <linux-aio@kvack.org>,
	"linux-api@vger.kernel.org" <linux-api@vger.kernel.org>,
	"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2] fs: Add aio iopriority support for block_dev
Date: Thu, 3 May 2018 20:24:29 +0000	[thread overview]
Message-ID: <002c2c33-2b22-01a2-dc26-4ca19ac4ac24@wdc.com> (raw)
In-Reply-To: <x49po2cr3hc.fsf@segfault.boston.devel.redhat.com>



On 5/3/18 11:36 AM, Jeff Moyer wrote:
> Hi, Adam,

Hello Jeff,

> 
> adam.manzanares@wdc.com writes:
> 
>> From: Adam Manzanares <adam.manzanares@wdc.com>
>>
>> This is the per-I/O equivalent of the ioprio_set system call.
>>
>> When IOCB_FLAG_IOPRIO is set on the iocb aio_flags field, then we set the
>> newly added kiocb ki_ioprio field to the value in the iocb aio_reqprio field.
>>
>> When a bio is created for an aio request by the block dev we set the priority
>> value of the bio to the user supplied value.
>>
>> See the following link for performance implications on a SATA HDD:
>> https://lkml.org/lkml/2016/12/6/495
>>
>> Given that WRR support for NVME devices has patches floating around and it was
>> discussed at LSFMM, we may soon have a lower latency storage device that can
>> make use of iopriorities. A per command iopriority interface seems timely
>> given these developments.
>>
>> If we want to avoid bloating struct kiocb, I suggest we turn the private field
>> into a union of the private and ki_ioprio field. It seems like the users of
>> the private field all use it at a point where we can yank the priority from
>> the kiocb before the private field is used. Comments and suggestions welcome.
> 
> The ioprio_set system call requires CAP_SYS_ADMIN for setting
> IOPRIO_CLASS_RT.  I think we need similar checks here.

I forgot how dangerous IOPRIO_CLASS_RT can be :). I will make a new 
function based on the checks in ioprio.c and reuse.

Thanks,
Adam

> 
> -Jeff
> 
>>
>> v2: merge patches
>>      use IOCB_FLAG_IOPRIO
>>      validate intended use with IOCB_IOPRIO
>>      add linux-api and linux-block to cc
>>
>> Signed-off-by: Adam Manzanares <adam.manzanares@wdc.com>
>> ---
>>   fs/aio.c                     | 10 ++++++++++
>>   fs/block_dev.c               |  2 ++
>>   include/linux/fs.h           |  2 ++
>>   include/uapi/linux/aio_abi.h |  1 +
>>   4 files changed, 15 insertions(+)
>>
>> diff --git a/fs/aio.c b/fs/aio.c
>> index 88d7927ffbc6..f36636d8ff2c 100644
>> --- a/fs/aio.c
>> +++ b/fs/aio.c
>> @@ -1597,6 +1597,16 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
>>   		req->common.ki_flags |= IOCB_EVENTFD;
>>   	}
>>   
>> +	if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
>> +		/*
>> +		 * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then
>> +		 * aio_reqprio is interpreted as an I/O scheduling
>> +		 * class and priority.
>> +		 */
>> +		req->common.ki_ioprio = iocb->aio_reqprio;
>> +		req->common.ki_flags |= IOCB_IOPRIO;
>> +	}
>> +
>>   	ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
>>   	if (unlikely(ret)) {
>>   		pr_debug("EINVAL: aio_rw_flags\n");
>> diff --git a/fs/block_dev.c b/fs/block_dev.c
>> index 7ec920e27065..970bef79caa6 100644
>> --- a/fs/block_dev.c
>> +++ b/fs/block_dev.c
>> @@ -355,6 +355,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
>>   		bio->bi_write_hint = iocb->ki_hint;
>>   		bio->bi_private = dio;
>>   		bio->bi_end_io = blkdev_bio_end_io;
>> +		if (iocb->ki_flags & IOCB_IOPRIO)
>> +			bio->bi_ioprio = iocb->ki_ioprio;
>>   
>>   		ret = bio_iov_iter_get_pages(bio, iter);
>>   		if (unlikely(ret)) {
>> diff --git a/include/linux/fs.h b/include/linux/fs.h
>> index 760d8da1b6c7..ab63ce720305 100644
>> --- a/include/linux/fs.h
>> +++ b/include/linux/fs.h
>> @@ -292,6 +292,7 @@ enum rw_hint {
>>   #define IOCB_SYNC		(1 << 5)
>>   #define IOCB_WRITE		(1 << 6)
>>   #define IOCB_NOWAIT		(1 << 7)
>> +#define IOCB_IOPRIO		(1 << 8)
>>   
>>   struct kiocb {
>>   	struct file		*ki_filp;
>> @@ -300,6 +301,7 @@ struct kiocb {
>>   	void			*private;
>>   	int			ki_flags;
>>   	enum rw_hint		ki_hint;
>> +	u16			ki_ioprio; /* See linux/ioprio.h */
>>   } __randomize_layout;
>>   
>>   static inline bool is_sync_kiocb(struct kiocb *kiocb)
>> diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
>> index a04adbc70ddf..d4593a6062ef 100644
>> --- a/include/uapi/linux/aio_abi.h
>> +++ b/include/uapi/linux/aio_abi.h
>> @@ -54,6 +54,7 @@ enum {
>>    *                   is valid.
>>    */
>>   #define IOCB_FLAG_RESFD		(1 << 0)
>> +#define IOCB_FLAG_IOPRIO	(1 << 1)
>>   
>>   /* read() from /dev/aio returns these structures. */
>>   struct io_event {

      reply	other threads:[~2018-05-03 20:24 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-03 18:21 adam.manzanares
2018-05-03 18:33 ` Matthew Wilcox
2018-05-03 20:15   ` Adam Manzanares
2018-05-03 20:24     ` Jens Axboe
2018-05-03 20:58       ` Adam Manzanares
2018-05-03 21:20         ` Jens Axboe
2018-05-03 22:43       ` Matthew Wilcox
2018-05-03 22:53         ` Jens Axboe
2018-05-03 18:36 ` Jeff Moyer
2018-05-03 20:24   ` Adam Manzanares [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=002c2c33-2b22-01a2-dc26-4ca19ac4ac24@wdc.com \
    --to=adam.manzanares@wdc.com \
    --cc=bcrl@kvack.org \
    --cc=jmoyer@redhat.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [PATCH v2] fs: Add aio iopriority support for block_dev' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).