Current code always set 'Unbound && max_active == 1' workqueues to ordered
implicitly, while this may be not an expected behaviour for some use cases.
E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
to different cpu so as to get better isolation, but their cpumask can't be
changed because WQ_ORDERED is set implicitly.
This patch adds a flag __WQ_ORDERED_DISABLE and also
create_singlethread_workqueue_noorder() to offer an new option.
Signed-off-by: Bob Liu <[email protected]>
---
include/linux/workqueue.h | 4 ++++
kernel/workqueue.c | 4 +++-
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index e48554e..4c86913 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -344,6 +344,7 @@ enum {
__WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
__WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
__WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
+ __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
@@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
#define create_singlethread_workqueue(name) \
alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
+#define create_singlethread_workqueue_noorder(name) \
+ alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
+ WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
extern void destroy_workqueue(struct workqueue_struct *wq);
struct workqueue_attrs *alloc_workqueue_attrs(void);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4e01c44..2167013 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4237,7 +4237,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
* on NUMA.
*/
if ((flags & WQ_UNBOUND) && max_active == 1)
- flags |= __WQ_ORDERED;
+ /* the caller may don't want __WQ_ORDERED to be set implicitly. */
+ if (!(flags & __WQ_ORDERED_DISABLE))
+ flags |= __WQ_ORDERED;
/* see the comment above the definition of WQ_POWER_EFFICIENT */
if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
--
2.9.5
This patch enable setting cpu affinity through "cpumask" for below
scsi/iscsi workqueues, so as to get better isolation.
- scsi_wq_*
- scsi_tmf_*
- iscsi_q_xx
- iscsi_eh
Signed-off-by: Bob Liu <[email protected]>
---
drivers/scsi/hosts.c | 4 ++--
drivers/scsi/libiscsi.c | 2 +-
drivers/scsi/scsi_transport_iscsi.c | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 1d669e4..4b9f80d 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -272,7 +272,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
if (shost->transportt->create_work_queue) {
snprintf(shost->work_q_name, sizeof(shost->work_q_name),
"scsi_wq_%d", shost->host_no);
- shost->work_q = create_singlethread_workqueue(
+ shost->work_q = create_singlethread_workqueue_noorder(
shost->work_q_name);
if (!shost->work_q) {
error = -EINVAL;
@@ -487,7 +487,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
}
shost->tmf_work_q = alloc_workqueue("scsi_tmf_%d",
- WQ_UNBOUND | WQ_MEM_RECLAIM,
+ WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS | __WQ_ORDERED_DISABLE,
1, shost->host_no);
if (!shost->tmf_work_q) {
shost_printk(KERN_WARNING, shost,
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 70b99c0..6808cf3 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -2627,7 +2627,7 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
if (xmit_can_sleep) {
snprintf(ihost->workq_name, sizeof(ihost->workq_name),
"iscsi_q_%d", shost->host_no);
- ihost->workq = create_singlethread_workqueue(ihost->workq_name);
+ ihost->workq = create_singlethread_workqueue_noorder(ihost->workq_name);
if (!ihost->workq)
goto free_host;
}
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index dfc726f..d07a0e4 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -4602,7 +4602,7 @@ static __init int iscsi_transport_init(void)
goto unregister_flashnode_bus;
}
- iscsi_eh_timer_workq = create_singlethread_workqueue("iscsi_eh");
+ iscsi_eh_timer_workq = create_singlethread_workqueue_noorder("iscsi_eh");
if (!iscsi_eh_timer_workq) {
err = -ENOMEM;
goto release_nls;
--
2.9.5
ping..
On 6/11/20 6:07 PM, Bob Liu wrote:
> Current code always set 'Unbound && max_active == 1' workqueues to ordered
> implicitly, while this may be not an expected behaviour for some use cases.
>
> E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
> to different cpu so as to get better isolation, but their cpumask can't be
> changed because WQ_ORDERED is set implicitly.
>
> This patch adds a flag __WQ_ORDERED_DISABLE and also
> create_singlethread_workqueue_noorder() to offer an new option.
>
> Signed-off-by: Bob Liu <[email protected]>
> ---
> include/linux/workqueue.h | 4 ++++
> kernel/workqueue.c | 4 +++-
> 2 files changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
> index e48554e..4c86913 100644
> --- a/include/linux/workqueue.h
> +++ b/include/linux/workqueue.h
> @@ -344,6 +344,7 @@ enum {
> __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
> __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
> __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
> + __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
>
> WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
> WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
> @@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
> #define create_singlethread_workqueue(name) \
> alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
>
> +#define create_singlethread_workqueue_noorder(name) \
> + alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
> + WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
> extern void destroy_workqueue(struct workqueue_struct *wq);
>
> struct workqueue_attrs *alloc_workqueue_attrs(void);
> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
> index 4e01c44..2167013 100644
> --- a/kernel/workqueue.c
> +++ b/kernel/workqueue.c
> @@ -4237,7 +4237,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
> * on NUMA.
> */
> if ((flags & WQ_UNBOUND) && max_active == 1)
> - flags |= __WQ_ORDERED;
> + /* the caller may don't want __WQ_ORDERED to be set implicitly. */
> + if (!(flags & __WQ_ORDERED_DISABLE))
> + flags |= __WQ_ORDERED;
>
> /* see the comment above the definition of WQ_POWER_EFFICIENT */
> if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
>
On 6/11/20 5:07 AM, Bob Liu wrote:
> This patch enable setting cpu affinity through "cpumask" for below
> scsi/iscsi workqueues, so as to get better isolation.
> - scsi_wq_*
> - scsi_tmf_*
> - iscsi_q_xx
> - iscsi_eh
>
> Signed-off-by: Bob Liu <[email protected]>
> ---
> drivers/scsi/hosts.c | 4 ++--
> drivers/scsi/libiscsi.c | 2 +-
> drivers/scsi/scsi_transport_iscsi.c | 2 +-
> 3 files changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
> index 1d669e4..4b9f80d 100644
> --- a/drivers/scsi/hosts.c
> +++ b/drivers/scsi/hosts.c
> @@ -272,7 +272,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
> if (shost->transportt->create_work_queue) {
> snprintf(shost->work_q_name, sizeof(shost->work_q_name),
> "scsi_wq_%d", shost->host_no);
> - shost->work_q = create_singlethread_workqueue(
> + shost->work_q = create_singlethread_workqueue_noorder(
> shost->work_q_name);
> if (!shost->work_q) {
> error = -EINVAL;
This patch seems ok for the iscsi, fc, tmf, and non transport class scan
uses. We are either heavy handed with flushes or did not need ordering.
I don't know about the zfcp use though, so I cc'd the developers listed
as maintainers. It looks like for zfcp we can do:
zfcp_scsi_rport_register->fc_remote_port_add->fc_remote_port_create->scsi_queue_work
to scan the scsi target on the rport.
and then zfcp_scsi_rport_register can call zfcp_unit_queue_scsi_scan->
scsi_queue_work which will scan for a specific lun.
It looks ok if those are not ordered, but I would get their review to
make sure.
On Mon, Jun 22, 2020 at 10:40:09AM -0500, Mike Christie wrote:
> On 6/11/20 5:07 AM, Bob Liu wrote:
> > This patch enable setting cpu affinity through "cpumask" for below
> > scsi/iscsi workqueues, so as to get better isolation.
> > - scsi_wq_*
> > - scsi_tmf_*
> > - iscsi_q_xx
> > - iscsi_eh
> >
> > Signed-off-by: Bob Liu <[email protected]>
> > ---
> > drivers/scsi/hosts.c | 4 ++--
> > drivers/scsi/libiscsi.c | 2 +-
> > drivers/scsi/scsi_transport_iscsi.c | 2 +-
> > 3 files changed, 4 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
> > index 1d669e4..4b9f80d 100644
> > --- a/drivers/scsi/hosts.c
> > +++ b/drivers/scsi/hosts.c
> > @@ -272,7 +272,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
> > if (shost->transportt->create_work_queue) {
> > snprintf(shost->work_q_name, sizeof(shost->work_q_name),
> > "scsi_wq_%d", shost->host_no);
> > - shost->work_q = create_singlethread_workqueue(
> > + shost->work_q = create_singlethread_workqueue_noorder(
> > shost->work_q_name);
> > if (!shost->work_q) {
> > error = -EINVAL;
>
> This patch seems ok for the iscsi, fc, tmf, and non transport class scan
> uses. We are either heavy handed with flushes or did not need ordering.
>
> I don't know about the zfcp use though, so I cc'd the developers listed as
> maintainers. It looks like for zfcp we can do:
Thx for the notice.
>
> zfcp_scsi_rport_register->fc_remote_port_add->fc_remote_port_create->scsi_queue_work
> to scan the scsi target on the rport.
>
> and then zfcp_scsi_rport_register can call zfcp_unit_queue_scsi_scan->
> scsi_queue_work which will scan for a specific lun.
>
> It looks ok if those are not ordered, but I would get their review to make
> sure.
I am not aware of any temporal requirements of those LUN-scans, so I
think making them not explicitly ordered shouldn't hurt us.
The target scan itself is protected again by `shost->scan_mutex`.. so
all fine I think.
--
Best Regards, Benjamin Block / Linux on IBM Z Kernel Development / IBM Systems
IBM Deutschland Research & Development GmbH / https://www.ibm.com/privacy
Vorsitz. AufsR.: Gregor Pillen / Gesch?ftsf?hrung: Dirk Wittkopp
Sitz der Gesellschaft: B?blingen / Registergericht: AmtsG Stuttgart, HRB 243294
On Thu, Jun 11, 2020 at 6:29 PM Bob Liu <[email protected]> wrote:
>
> Current code always set 'Unbound && max_active == 1' workqueues to ordered
> implicitly, while this may be not an expected behaviour for some use cases.
>
> E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
> to different cpu so as to get better isolation, but their cpumask can't be
> changed because WQ_ORDERED is set implicitly.
Hello
If I read the code correctly, the reason why their cpumask can't
be changed is because __WQ_ORDERED_EXPLICIT, not __WQ_ORDERED.
>
> This patch adds a flag __WQ_ORDERED_DISABLE and also
> create_singlethread_workqueue_noorder() to offer an new option.
>
> Signed-off-by: Bob Liu <[email protected]>
> ---
> include/linux/workqueue.h | 4 ++++
> kernel/workqueue.c | 4 +++-
> 2 files changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
> index e48554e..4c86913 100644
> --- a/include/linux/workqueue.h
> +++ b/include/linux/workqueue.h
> @@ -344,6 +344,7 @@ enum {
> __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
> __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
> __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
> + __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
>
> WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
> WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
> @@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
> #define create_singlethread_workqueue(name) \
> alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
>
> +#define create_singlethread_workqueue_noorder(name) \
> + alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
> + WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
I think using __WQ_ORDERED without __WQ_ORDERED_EXPLICIT is what you
need, in which case cpumask is allowed to be changed.
Just use alloc_workqueue() with __WQ_ORDERED and max_active=1. It can
be wrapped as a new function or macro, but I don't think
create_singlethread_workqueue_noorder() is a good name for it.
> extern void destroy_workqueue(struct workqueue_struct *wq);
>
> struct workqueue_attrs *alloc_workqueue_attrs(void);
> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
> index 4e01c44..2167013 100644
> --- a/kernel/workqueue.c
> +++ b/kernel/workqueue.c
> @@ -4237,7 +4237,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
> * on NUMA.
> */
> if ((flags & WQ_UNBOUND) && max_active == 1)
> - flags |= __WQ_ORDERED;
> + /* the caller may don't want __WQ_ORDERED to be set implicitly. */
> + if (!(flags & __WQ_ORDERED_DISABLE))
> + flags |= __WQ_ORDERED;
>
> /* see the comment above the definition of WQ_POWER_EFFICIENT */
> if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
> --
> 2.9.5
>
On 6/28/20 11:54 PM, Lai Jiangshan wrote:
> On Thu, Jun 11, 2020 at 6:29 PM Bob Liu <[email protected]> wrote:
>>
>> Current code always set 'Unbound && max_active == 1' workqueues to ordered
>> implicitly, while this may be not an expected behaviour for some use cases.
>>
>> E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
>> to different cpu so as to get better isolation, but their cpumask can't be
>> changed because WQ_ORDERED is set implicitly.
>
> Hello
>
> If I read the code correctly, the reason why their cpumask can't
> be changed is because __WQ_ORDERED_EXPLICIT, not __WQ_ORDERED.
>
>>
>> This patch adds a flag __WQ_ORDERED_DISABLE and also
>> create_singlethread_workqueue_noorder() to offer an new option.
>>
>> Signed-off-by: Bob Liu <[email protected]>
>> ---
>> include/linux/workqueue.h | 4 ++++
>> kernel/workqueue.c | 4 +++-
>> 2 files changed, 7 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
>> index e48554e..4c86913 100644
>> --- a/include/linux/workqueue.h
>> +++ b/include/linux/workqueue.h
>> @@ -344,6 +344,7 @@ enum {
>> __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
>> __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
>> __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
>> + __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
>>
>> WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
>> WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
>> @@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
>> #define create_singlethread_workqueue(name) \
>> alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
>>
>> +#define create_singlethread_workqueue_noorder(name) \
>> + alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
>> + WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
>
> I think using __WQ_ORDERED without __WQ_ORDERED_EXPLICIT is what you
> need, in which case cpumask is allowed to be changed.
>
I don't think so, see function workqueue_apply_unbound_cpumask():
wq_unbound_cpumask_store()
> workqueue_set_unbound_cpumask()
> workqueue_apply_unbound_cpumask() {
...
5276 /* creating multiple pwqs breaks ordering guarantee */
5277 if (wq->flags & __WQ_ORDERED)
5278 continue;
^^^^
Here will skip apply cpumask if only __WQ_ORDERED is set.
5280 ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs);
}
Thanks for your review.
Bob
> Just use alloc_workqueue() with __WQ_ORDERED and max_active=1. It can
> be wrapped as a new function or macro, but I don't think> create_singlethread_workqueue_noorder() is a good name for it.
>
>> extern void destroy_workqueue(struct workqueue_struct *wq);
>>
>> struct workqueue_attrs *alloc_workqueue_attrs(void);
>> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
>> index 4e01c44..2167013 100644
>> --- a/kernel/workqueue.c
>> +++ b/kernel/workqueue.c
>> @@ -4237,7 +4237,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
>> * on NUMA.
>> */
>> if ((flags & WQ_UNBOUND) && max_active == 1)
>> - flags |= __WQ_ORDERED;
>> + /* the caller may don't want __WQ_ORDERED to be set implicitly. */
>> + if (!(flags & __WQ_ORDERED_DISABLE))
>> + flags |= __WQ_ORDERED;
>>
>> /* see the comment above the definition of WQ_POWER_EFFICIENT */
>> if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
>> --
>> 2.9.5
>>
On Mon, Jun 29, 2020 at 8:13 AM Bob Liu <[email protected]> wrote:
>
> On 6/28/20 11:54 PM, Lai Jiangshan wrote:
> > On Thu, Jun 11, 2020 at 6:29 PM Bob Liu <[email protected]> wrote:
> >>
> >> Current code always set 'Unbound && max_active == 1' workqueues to ordered
> >> implicitly, while this may be not an expected behaviour for some use cases.
> >>
> >> E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
> >> to different cpu so as to get better isolation, but their cpumask can't be
> >> changed because WQ_ORDERED is set implicitly.
> >
> > Hello
> >
> > If I read the code correctly, the reason why their cpumask can't
> > be changed is because __WQ_ORDERED_EXPLICIT, not __WQ_ORDERED.
> >
> >>
> >> This patch adds a flag __WQ_ORDERED_DISABLE and also
> >> create_singlethread_workqueue_noorder() to offer an new option.
> >>
> >> Signed-off-by: Bob Liu <[email protected]>
> >> ---
> >> include/linux/workqueue.h | 4 ++++
> >> kernel/workqueue.c | 4 +++-
> >> 2 files changed, 7 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
> >> index e48554e..4c86913 100644
> >> --- a/include/linux/workqueue.h
> >> +++ b/include/linux/workqueue.h
> >> @@ -344,6 +344,7 @@ enum {
> >> __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
> >> __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
> >> __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
> >> + __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
> >>
> >> WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
> >> WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
> >> @@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
> >> #define create_singlethread_workqueue(name) \
> >> alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
> >>
> >> +#define create_singlethread_workqueue_noorder(name) \
> >> + alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
> >> + WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
> >
> > I think using __WQ_ORDERED without __WQ_ORDERED_EXPLICIT is what you
> > need, in which case cpumask is allowed to be changed.
> >
>
> I don't think so, see function workqueue_apply_unbound_cpumask():
>
> wq_unbound_cpumask_store()
> > workqueue_set_unbound_cpumask()
> > workqueue_apply_unbound_cpumask() {
> ...
> 5276 /* creating multiple pwqs breaks ordering guarantee */
> 5277 if (wq->flags & __WQ_ORDERED)
> 5278 continue;
> ^^^^
> Here will skip apply cpumask if only __WQ_ORDERED is set.
wq_unbound_cpumask_store() is for changing the cpumask of
*all* workqueues. I don't think it can be used to make
scsi and iscsi workqueues bound to different cpu.
apply_workqueue_attrs() is for changing the cpumask of the specific
workqueue, which can change the cpumask of __WQ_ORDERED workqueue
(but without __WQ_ORDERED_EXPLICIT).
>
> 5280 ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs);
>
> }
>
> Thanks for your review.
> Bob
>
> > Just use alloc_workqueue() with __WQ_ORDERED and max_active=1. It can
> > be wrapped as a new function or macro, but I don't think> create_singlethread_workqueue_noorder() is a good name for it.
> >
> >> extern void destroy_workqueue(struct workqueue_struct *wq);
> >>
> >> struct workqueue_attrs *alloc_workqueue_attrs(void);
> >> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
> >> index 4e01c44..2167013 100644
> >> --- a/kernel/workqueue.c
> >> +++ b/kernel/workqueue.c
> >> @@ -4237,7 +4237,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
> >> * on NUMA.
> >> */
> >> if ((flags & WQ_UNBOUND) && max_active == 1)
> >> - flags |= __WQ_ORDERED;
> >> + /* the caller may don't want __WQ_ORDERED to be set implicitly. */
> >> + if (!(flags & __WQ_ORDERED_DISABLE))
> >> + flags |= __WQ_ORDERED;
> >>
> >> /* see the comment above the definition of WQ_POWER_EFFICIENT */
> >> if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
> >> --
> >> 2.9.5
> >>
>
On 6/29/20 8:37 AM, Lai Jiangshan wrote:
> On Mon, Jun 29, 2020 at 8:13 AM Bob Liu <[email protected]> wrote:
>>
>> On 6/28/20 11:54 PM, Lai Jiangshan wrote:
>>> On Thu, Jun 11, 2020 at 6:29 PM Bob Liu <[email protected]> wrote:
>>>>
>>>> Current code always set 'Unbound && max_active == 1' workqueues to ordered
>>>> implicitly, while this may be not an expected behaviour for some use cases.
>>>>
>>>> E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
>>>> to different cpu so as to get better isolation, but their cpumask can't be
>>>> changed because WQ_ORDERED is set implicitly.
>>>
>>> Hello
>>>
>>> If I read the code correctly, the reason why their cpumask can't
>>> be changed is because __WQ_ORDERED_EXPLICIT, not __WQ_ORDERED.
>>>
>>>>
>>>> This patch adds a flag __WQ_ORDERED_DISABLE and also
>>>> create_singlethread_workqueue_noorder() to offer an new option.
>>>>
>>>> Signed-off-by: Bob Liu <[email protected]>
>>>> ---
>>>> include/linux/workqueue.h | 4 ++++
>>>> kernel/workqueue.c | 4 +++-
>>>> 2 files changed, 7 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
>>>> index e48554e..4c86913 100644
>>>> --- a/include/linux/workqueue.h
>>>> +++ b/include/linux/workqueue.h
>>>> @@ -344,6 +344,7 @@ enum {
>>>> __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
>>>> __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
>>>> __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
>>>> + __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
>>>>
>>>> WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
>>>> WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
>>>> @@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
>>>> #define create_singlethread_workqueue(name) \
>>>> alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
>>>>
>>>> +#define create_singlethread_workqueue_noorder(name) \
>>>> + alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
>>>> + WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
>>>
>>> I think using __WQ_ORDERED without __WQ_ORDERED_EXPLICIT is what you
>>> need, in which case cpumask is allowed to be changed.
>>>
>>
>> I don't think so, see function workqueue_apply_unbound_cpumask():
>>
>> wq_unbound_cpumask_store()
>> > workqueue_set_unbound_cpumask()
>> > workqueue_apply_unbound_cpumask() {
>> ...
>> 5276 /* creating multiple pwqs breaks ordering guarantee */
>> 5277 if (wq->flags & __WQ_ORDERED)
>> 5278 continue;
>> ^^^^
>> Here will skip apply cpumask if only __WQ_ORDERED is set.
>
> wq_unbound_cpumask_store() is for changing the cpumask of
> *all* workqueues.
Isn't '/sys/bus/workqueue/devices/xxxx/cpumask' using the same function to change cpumask of
specific workqueue?
Am I missing something..
> I don't think it can be used to make
> scsi and iscsi workqueues bound to different cpu.
>
The idea is to register scsi/iscsi workqueues with WQ_SYSFS, and then they can be bounded to different
cpu by writing cpu number to "/sys/bus/workqueue/devices/xxxx/cpumask".
> apply_workqueue_attrs() is for changing the cpumask of the specific
> workqueue, which can change the cpumask of __WQ_ORDERED workqueue
> (but without __WQ_ORDERED_EXPLICIT).
>
>>
>> 5280 ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs);
>>
>> }
>>
>> Thanks for your review.
>> Bob
>>
>>> Just use alloc_workqueue() with __WQ_ORDERED and max_active=1. It can
>>> be wrapped as a new function or macro, but I don't think> create_singlethread_workqueue_noorder() is a good name for it.
>>>
>>>> extern void destroy_workqueue(struct workqueue_struct *wq);
>>>>
>>>> struct workqueue_attrs *alloc_workqueue_attrs(void);
>>>> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
>>>> index 4e01c44..2167013 100644
>>>> --- a/kernel/workqueue.c
>>>> +++ b/kernel/workqueue.c
>>>> @@ -4237,7 +4237,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
>>>> * on NUMA.
>>>> */
>>>> if ((flags & WQ_UNBOUND) && max_active == 1)
>>>> - flags |= __WQ_ORDERED;
>>>> + /* the caller may don't want __WQ_ORDERED to be set implicitly. */
>>>> + if (!(flags & __WQ_ORDERED_DISABLE))
>>>> + flags |= __WQ_ORDERED;
>>>>
>>>> /* see the comment above the definition of WQ_POWER_EFFICIENT */
>>>> if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
>>>> --
>>>> 2.9.5
>>>>
>>
On 6/29/20 8:37 AM, Lai Jiangshan wrote:
> On Mon, Jun 29, 2020 at 8:13 AM Bob Liu <[email protected]> wrote:
>>
>> On 6/28/20 11:54 PM, Lai Jiangshan wrote:
>>> On Thu, Jun 11, 2020 at 6:29 PM Bob Liu <[email protected]> wrote:
>>>>
>>>> Current code always set 'Unbound && max_active == 1' workqueues to ordered
>>>> implicitly, while this may be not an expected behaviour for some use cases.
>>>>
>>>> E.g some scsi and iscsi workqueues(unbound && max_active = 1) want to be bind
>>>> to different cpu so as to get better isolation, but their cpumask can't be
>>>> changed because WQ_ORDERED is set implicitly.
>>>
>>> Hello
>>>
>>> If I read the code correctly, the reason why their cpumask can't
>>> be changed is because __WQ_ORDERED_EXPLICIT, not __WQ_ORDERED.
>>>
>>>>
>>>> This patch adds a flag __WQ_ORDERED_DISABLE and also
>>>> create_singlethread_workqueue_noorder() to offer an new option.
>>>>
>>>> Signed-off-by: Bob Liu <[email protected]>
>>>> ---
>>>> include/linux/workqueue.h | 4 ++++
>>>> kernel/workqueue.c | 4 +++-
>>>> 2 files changed, 7 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
>>>> index e48554e..4c86913 100644
>>>> --- a/include/linux/workqueue.h
>>>> +++ b/include/linux/workqueue.h
>>>> @@ -344,6 +344,7 @@ enum {
>>>> __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
>>>> __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
>>>> __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
>>>> + __WQ_ORDERED_DISABLE = 1 << 20, /* internal: don't set __WQ_ORDERED implicitly */
>>>>
>>>> WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
>>>> WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
>>>> @@ -433,6 +434,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
>>>> #define create_singlethread_workqueue(name) \
>>>> alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
>>>>
>>>> +#define create_singlethread_workqueue_noorder(name) \
>>>> + alloc_workqueue("%s", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | \
>>>> + WQ_UNBOUND | __WQ_ORDERED_DISABLE, 1, (name))
>>>
>>> I think using __WQ_ORDERED without __WQ_ORDERED_EXPLICIT is what you
>>> need, in which case cpumask is allowed to be changed.
>>>
>>
>> I don't think so, see function workqueue_apply_unbound_cpumask():
>>
>> wq_unbound_cpumask_store()
>> > workqueue_set_unbound_cpumask()
>> > workqueue_apply_unbound_cpumask() {
>> ...
>> 5276 /* creating multiple pwqs breaks ordering guarantee */
>> 5277 if (wq->flags & __WQ_ORDERED)
>> 5278 continue;
>> ^^^^
>> Here will skip apply cpumask if only __WQ_ORDERED is set.
>
> wq_unbound_cpumask_store() is for changing the cpumask of
> *all* workqueues. I don't think it can be used to make
> scsi and iscsi workqueues bound to different cpu.
>
> apply_workqueue_attrs() is for changing the cpumask of the specific
> workqueue, which can change the cpumask of __WQ_ORDERED workqueue
> (but without __WQ_ORDERED_EXPLICIT).
>
Yes, you are right. I made a mistake.
Sorry for the noise.
Regards,
Bob
>>
>> 5280 ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs);
>>
>> }