From: "Matias Bjørling" <[email protected]>
To: Jens Axboe <[email protected]>,
"[email protected]" <[email protected]>,
Damien Le Moal <[email protected]>
Cc: Kanchan Joshi <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>
Subject: Re: [PATCH 3/3] io_uring: add support for zone-append
Date: Fri, 19 Jun 2020 17:14:48 +0200 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 19/06/2020 16.18, Jens Axboe wrote:
> On 6/19/20 5:15 AM, Matias Bjørling wrote:
>> On 19/06/2020 11.41, [email protected] wrote:
>>> Jens,
>>>
>>> Would you have time to answer a question below in this thread?
>>>
>>> On 18.06.2020 11:11, [email protected] wrote:
>>>> On 18.06.2020 08:47, Damien Le Moal wrote:
>>>>> On 2020/06/18 17:35, [email protected] wrote:
>>>>>> On 18.06.2020 07:39, Damien Le Moal wrote:
>>>>>>> On 2020/06/18 2:27, Kanchan Joshi wrote:
>>>>>>>> From: Selvakumar S <[email protected]>
>>>>>>>>
>>>>>>>> Introduce three new opcodes for zone-append -
>>>>>>>>
>>>>>>>> IORING_OP_ZONE_APPEND : non-vectord, similiar to
>>>>>>>> IORING_OP_WRITE
>>>>>>>> IORING_OP_ZONE_APPENDV : vectored, similar to IORING_OP_WRITEV
>>>>>>>> IORING_OP_ZONE_APPEND_FIXED : append using fixed-buffers
>>>>>>>>
>>>>>>>> Repurpose cqe->flags to return zone-relative offset.
>>>>>>>>
>>>>>>>> Signed-off-by: SelvaKumar S <[email protected]>
>>>>>>>> Signed-off-by: Kanchan Joshi <[email protected]>
>>>>>>>> Signed-off-by: Nitesh Shetty <[email protected]>
>>>>>>>> Signed-off-by: Javier Gonzalez <[email protected]>
>>>>>>>> ---
>>>>>>>> fs/io_uring.c | 72
>>>>>>>> +++++++++++++++++++++++++++++++++++++++++--
>>>>>>>> include/uapi/linux/io_uring.h | 8 ++++-
>>>>>>>> 2 files changed, 77 insertions(+), 3 deletions(-)
>>>>>>>>
>>>>>>>> diff --git a/fs/io_uring.c b/fs/io_uring.c
>>>>>>>> index 155f3d8..c14c873 100644
>>>>>>>> --- a/fs/io_uring.c
>>>>>>>> +++ b/fs/io_uring.c
>>>>>>>> @@ -649,6 +649,10 @@ struct io_kiocb {
>>>>>>>> unsigned long fsize;
>>>>>>>> u64 user_data;
>>>>>>>> u32 result;
>>>>>>>> +#ifdef CONFIG_BLK_DEV_ZONED
>>>>>>>> + /* zone-relative offset for append, in bytes */
>>>>>>>> + u32 append_offset;
>>>>>>> this can overflow. u64 is needed.
>>>>>> We chose to do it this way to start with because struct io_uring_cqe
>>>>>> only has space for u32 when we reuse the flags.
>>>>>>
>>>>>> We can of course create a new cqe structure, but that will come with
>>>>>> larger changes to io_uring for supporting append.
>>>>>>
>>>>>> Do you believe this is a better approach?
>>>>> The problem is that zone size are 32 bits in the kernel, as a number
>>>>> of sectors.
>>>>> So any device that has a zone size smaller or equal to 2^31 512B
>>>>> sectors can be
>>>>> accepted. Using a zone relative offset in bytes for returning zone
>>>>> append result
>>>>> is OK-ish, but to match the kernel supported range of possible zone
>>>>> size, you
>>>>> need 31+9 bits... 32 does not cut it.
>>>> Agree. Our initial assumption was that u32 would cover current zone size
>>>> requirements, but if this is a no-go, we will take the longer path.
>>> Converting to u64 will require a new version of io_uring_cqe, where we
>>> extend at least 32 bits. I believe this will need a whole new allocation
>>> and probably ioctl().
>>>
>>> Is this an acceptable change for you? We will of course add support for
>>> liburing when we agree on the right way to do this.
>> I took a quick look at the code. No expert, but why not use the existing
>> userdata variable? use the lowest bits (40 bits) for the Zone Starting
>> LBA, and use the highest (24 bits) as index into the completion data
>> structure?
>>
>> If you want to pass the memory address (same as what fio does) for the
>> data structure used for completion, one may also play some tricks by
>> using a relative memory address to the data structure. For example, the
>> x86_64 architecture uses 48 address bits for its memory addresses. With
>> 24 bit, one can allocate the completion entries in a 32MB memory range,
>> and then use base_address + index to get back to the completion data
>> structure specified in the sqe.
> For any current request, sqe->user_data is just provided back as
> cqe->user_data. This would make these requests behave differently
> from everything else in that sense, which seems very confusing to me
> if I was an application writer.
>
> But generally I do agree with you, there are lots of ways to make
> < 64-bit work as a tag without losing anything or having to jump
> through hoops to do so. The lack of consistency introduced by having
> zone append work differently is ugly, though.
>
Yep, agree, and extending to three cachelines is big no-go. We could add
a flag that said the kernel has changes the userdata variable. That'll
make it very explicit.
next prev parent reply other threads:[~2020-06-19 15:59 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20200617172653epcas5p488de50090415eb802e62acc0e23d8812@epcas5p4.samsung.com>
2020-06-17 17:23 ` [PATCH 0/3] zone-append support in aio and io-uring Kanchan Joshi
[not found] ` <CGME20200617172702epcas5p4dbf4729d31d9a85ab1d261d04f238e61@epcas5p4.samsung.com>
2020-06-17 17:23 ` [PATCH 1/3] fs,block: Introduce IOCB_ZONE_APPEND and direct-io handling Kanchan Joshi
2020-06-17 19:02 ` Pavel Begunkov
2020-06-18 7:16 ` Damien Le Moal
2020-06-18 18:35 ` Kanchan Joshi
[not found] ` <CGME20200617172706epcas5p4dcbc164063f58bad95b211b9d6dfbfa9@epcas5p4.samsung.com>
2020-06-17 17:23 ` [PATCH 2/3] aio: add support for zone-append Kanchan Joshi
2020-06-18 7:33 ` Damien Le Moal
[not found] ` <CGME20200617172713epcas5p352f2907a12bd4ee3c97be1c7d8e1569e@epcas5p3.samsung.com>
2020-06-17 17:23 ` [PATCH 3/3] io_uring: " Kanchan Joshi
2020-06-17 18:55 ` Pavel Begunkov
2020-06-18 7:39 ` Damien Le Moal
2020-06-18 8:35 ` [email protected]
2020-06-18 8:47 ` Damien Le Moal
2020-06-18 9:11 ` [email protected]
2020-06-19 9:41 ` [email protected]
2020-06-19 11:15 ` Matias Bjørling
2020-06-19 14:18 ` Jens Axboe
2020-06-19 15:14 ` Matias Bjørling [this message]
2020-06-19 15:20 ` Jens Axboe
2020-06-19 15:40 ` Matias Bjørling
2020-06-19 15:44 ` Jens Axboe
2020-06-21 18:55 ` [email protected]
2020-06-19 14:15 ` Jens Axboe
2020-06-19 14:59 ` Pavel Begunkov
2020-06-19 15:02 ` Jens Axboe
2020-06-21 18:52 ` [email protected]
2020-06-17 17:42 ` [PATCH 0/3] zone-append support in aio and io-uring Matthew Wilcox
2020-06-18 6:56 ` Christoph Hellwig
2020-06-18 8:29 ` Javier González
2020-06-18 17:52 ` Kanchan Joshi
2020-06-19 3:08 ` Damien Le Moal
2020-06-19 7:56 ` Christoph Hellwig
2020-06-18 8:04 ` Matias Bjørling
2020-06-18 8:27 ` Javier González
2020-06-18 8:32 ` Matias Bjørling
2020-06-18 8:39 ` Javier González
2020-06-18 8:46 ` Matias Bjørling
2020-06-18 14:16 ` Christoph Hellwig
2020-06-18 19:21 ` Kanchan Joshi
2020-06-18 20:04 ` Matias Bjørling
2020-06-19 1:03 ` Damien Le Moal
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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox