Make read_iter_zero() to honor IOCB_NOWAIT, so /dev/zero can be
advertised as FMODE_NOWAIT. This helps subsystems like io_uring to use
it more effectively. Set FMODE_NOWAIT for /dev/null as well, it never
waits and therefore trivially meets the criteria.
Signed-off-by: Pavel Begunkov <[email protected]>
---
drivers/char/mem.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 1c596b5cdb27..531f144d7132 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -495,6 +495,8 @@ static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
written += n;
if (signal_pending(current))
return written ? written : -ERESTARTSYS;
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return written ? written : -EAGAIN;
cond_resched();
}
return written;
@@ -696,11 +698,11 @@ static const struct memdev {
#ifdef CONFIG_DEVMEM
[DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
#endif
- [3] = { "null", 0666, &null_fops, 0 },
+ [3] = { "null", 0666, &null_fops, FMODE_NOWAIT },
#ifdef CONFIG_DEVPORT
[4] = { "port", 0, &port_fops, 0 },
#endif
- [5] = { "zero", 0666, &zero_fops, 0 },
+ [5] = { "zero", 0666, &zero_fops, FMODE_NOWAIT },
[7] = { "full", 0666, &full_fops, 0 },
[8] = { "random", 0666, &random_fops, 0 },
[9] = { "urandom", 0666, &urandom_fops, 0 },
--
2.33.0
On Wed, Sep 08, 2021 at 11:06:51AM +0100, Pavel Begunkov wrote:
> Make read_iter_zero() to honor IOCB_NOWAIT, so /dev/zero can be
> advertised as FMODE_NOWAIT. This helps subsystems like io_uring to use
> it more effectively. Set FMODE_NOWAIT for /dev/null as well, it never
> waits and therefore trivially meets the criteria.
I do not understand, why would io_uring need to use /dev/zero and how is
this going to help anything?
What workload does this help with?
thanks,
greg k-h
On 9/8/21 11:25 AM, Greg Kroah-Hartman wrote:
> On Wed, Sep 08, 2021 at 11:06:51AM +0100, Pavel Begunkov wrote:
>> Make read_iter_zero() to honor IOCB_NOWAIT, so /dev/zero can be
>> advertised as FMODE_NOWAIT. This helps subsystems like io_uring to use
>> it more effectively. Set FMODE_NOWAIT for /dev/null as well, it never
>> waits and therefore trivially meets the criteria.
>
> I do not understand, why would io_uring need to use /dev/zero
Not directly, users can issue I/O against it via io_uring.
> and how is this going to help anything?
For files not supporting nowait io_uring goes through a quite slow path.
> What workload does this help with?
Personally for me it's dumping output and benchmarking (not benchmarking
/dev/zero, of course). But I'd also expect any tool that may be using
it but rewritten with io_uring being able to normally use it without a
performance hit.
--
Pavel Begunkov
On 9/8/21 4:06 AM, Pavel Begunkov wrote:
> Make read_iter_zero() to honor IOCB_NOWAIT, so /dev/zero can be
> advertised as FMODE_NOWAIT. This helps subsystems like io_uring to use
> it more effectively. Set FMODE_NOWAIT for /dev/null as well, it never
> waits and therefore trivially meets the criteria.
>
> Signed-off-by: Pavel Begunkov <[email protected]>
> ---
> drivers/char/mem.c | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/char/mem.c b/drivers/char/mem.c
> index 1c596b5cdb27..531f144d7132 100644
> --- a/drivers/char/mem.c
> +++ b/drivers/char/mem.c
> @@ -495,6 +495,8 @@ static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
> written += n;
> if (signal_pending(current))
> return written ? written : -ERESTARTSYS;
> + if (iocb->ki_flags & IOCB_NOWAIT)
> + return written ? written : -EAGAIN;
> cond_resched();
> }
I don't think this part is needed.
> return written;
> @@ -696,11 +698,11 @@ static const struct memdev {
> #ifdef CONFIG_DEVMEM
> [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
> #endif
> - [3] = { "null", 0666, &null_fops, 0 },
> + [3] = { "null", 0666, &null_fops, FMODE_NOWAIT },
> #ifdef CONFIG_DEVPORT
> [4] = { "port", 0, &port_fops, 0 },
> #endif
> - [5] = { "zero", 0666, &zero_fops, 0 },
> + [5] = { "zero", 0666, &zero_fops, FMODE_NOWAIT },
> [7] = { "full", 0666, &full_fops, 0 },
> [8] = { "random", 0666, &random_fops, 0 },
> [9] = { "urandom", 0666, &urandom_fops, 0 },
>
This looks fine.
--
Jens Axboe
On 9/8/21 1:57 PM, Jens Axboe wrote:
> On 9/8/21 4:06 AM, Pavel Begunkov wrote:
>> Make read_iter_zero() to honor IOCB_NOWAIT, so /dev/zero can be
>> advertised as FMODE_NOWAIT. This helps subsystems like io_uring to use
>> it more effectively. Set FMODE_NOWAIT for /dev/null as well, it never
>> waits and therefore trivially meets the criteria.
>>
>> Signed-off-by: Pavel Begunkov <[email protected]>
>> ---
>> drivers/char/mem.c | 6 ++++--
>> 1 file changed, 4 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/char/mem.c b/drivers/char/mem.c
>> index 1c596b5cdb27..531f144d7132 100644
>> --- a/drivers/char/mem.c
>> +++ b/drivers/char/mem.c
>> @@ -495,6 +495,8 @@ static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
>> written += n;
>> if (signal_pending(current))
>> return written ? written : -ERESTARTSYS;
>> + if (iocb->ki_flags & IOCB_NOWAIT)
>> + return written ? written : -EAGAIN;
>> cond_resched();
>> }
>
> I don't think this part is needed.
It can be clearing gigabytes in one go. Won't it be too much of a
delay when nowait is expected?
>> return written;
>> @@ -696,11 +698,11 @@ static const struct memdev {
>> #ifdef CONFIG_DEVMEM
>> [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
>> #endif
>> - [3] = { "null", 0666, &null_fops, 0 },
>> + [3] = { "null", 0666, &null_fops, FMODE_NOWAIT },
>> #ifdef CONFIG_DEVPORT
>> [4] = { "port", 0, &port_fops, 0 },
>> #endif
>> - [5] = { "zero", 0666, &zero_fops, 0 },
>> + [5] = { "zero", 0666, &zero_fops, FMODE_NOWAIT },
>> [7] = { "full", 0666, &full_fops, 0 },
>> [8] = { "random", 0666, &random_fops, 0 },
>> [9] = { "urandom", 0666, &urandom_fops, 0 },
>>
>
> This looks fine.
>
--
Pavel Begunkov
On 9/8/21 7:07 AM, Pavel Begunkov wrote:
> On 9/8/21 1:57 PM, Jens Axboe wrote:
>> On 9/8/21 4:06 AM, Pavel Begunkov wrote:
>>> Make read_iter_zero() to honor IOCB_NOWAIT, so /dev/zero can be
>>> advertised as FMODE_NOWAIT. This helps subsystems like io_uring to use
>>> it more effectively. Set FMODE_NOWAIT for /dev/null as well, it never
>>> waits and therefore trivially meets the criteria.
>>>
>>> Signed-off-by: Pavel Begunkov <[email protected]>
>>> ---
>>> drivers/char/mem.c | 6 ++++--
>>> 1 file changed, 4 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/char/mem.c b/drivers/char/mem.c
>>> index 1c596b5cdb27..531f144d7132 100644
>>> --- a/drivers/char/mem.c
>>> +++ b/drivers/char/mem.c
>>> @@ -495,6 +495,8 @@ static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
>>> written += n;
>>> if (signal_pending(current))
>>> return written ? written : -ERESTARTSYS;
>>> + if (iocb->ki_flags & IOCB_NOWAIT)
>>> + return written ? written : -EAGAIN;
>>> cond_resched();
>>> }
>>
>> I don't think this part is needed.
>
> It can be clearing gigabytes in one go. Won't it be too much of a
> delay when nowait is expected?
I guess it can't hurt, but then it should be changed to:
if (!need_resched())
continue;
if (iocb->ki_flags & IOCB_NOWAIT)
return written ? written : -EAGAIN;
cond_resched();
to avoid doing -EAGAIN just because there's more than one segment in the
buffer. Even that may be excessive though, but definitely a lot better.
--
Jens Axboe