* [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue
@ 2020-05-05 1:19 Bob Liu
2020-05-15 0:09 ` Martin K. Petersen
` (2 more replies)
0 siblings, 3 replies; 5+ messages in thread
From: Bob Liu @ 2020-05-05 1:19 UTC (permalink / raw)
To: open-iscsi; +Cc: lduncan, cleech, jejb, martin.petersen, linux-scsi, Bob Liu
Motivation:
This patch enable setting cpu affinity through "cpumask" for iscsi workqueues
(iscsi_q_xx and iscsi_eh), so as to get performance isolation.
The max number of active worker was changed form 1 to 2, because "cpumask" of
ordered workqueue isn't allowed to change.
Notes:
- Having 2 workers break the current ordering guarantees, please let me know
if anyone depends on this.
- __WQ_LEGACY have to be left because of
23d11a5(workqueue: skip flush dependency checks for legacy workqueues)
Signed-off-by: Bob Liu <bob.liu@oracle.com>
---
drivers/scsi/libiscsi.c | 4 +++-
drivers/scsi/scsi_transport_iscsi.c | 4 +++-
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 70b99c0..adf9bb4 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -2627,7 +2627,9 @@ 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 = alloc_workqueue("%s",
+ WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
+ 2, 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..bdbc4a2 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -4602,7 +4602,9 @@ static __init int iscsi_transport_init(void)
goto unregister_flashnode_bus;
}
- iscsi_eh_timer_workq = create_singlethread_workqueue("iscsi_eh");
+ iscsi_eh_timer_workq = alloc_workqueue("%s",
+ WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
+ 2, "iscsi_eh");
if (!iscsi_eh_timer_workq) {
err = -ENOMEM;
goto release_nls;
--
2.9.5
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue
2020-05-05 1:19 [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue Bob Liu
@ 2020-05-15 0:09 ` Martin K. Petersen
2020-05-25 9:16 ` Bob Liu
2020-05-27 2:12 ` Martin K. Petersen
2 siblings, 0 replies; 5+ messages in thread
From: Martin K. Petersen @ 2020-05-15 0:09 UTC (permalink / raw)
To: lduncan, cleech; +Cc: open-iscsi, Bob Liu, jejb, martin.petersen, linux-scsi
Chris/Lee: Please review!
> Motivation:
> This patch enable setting cpu affinity through "cpumask" for iscsi workqueues
> (iscsi_q_xx and iscsi_eh), so as to get performance isolation.
>
> The max number of active worker was changed form 1 to 2, because "cpumask" of
> ordered workqueue isn't allowed to change.
>
> Notes:
> - Having 2 workers break the current ordering guarantees, please let me know
> if anyone depends on this.
>
> - __WQ_LEGACY have to be left because of
> 23d11a5(workqueue: skip flush dependency checks for legacy workqueues)
>
> Signed-off-by: Bob Liu <bob.liu@oracle.com>
> ---
> drivers/scsi/libiscsi.c | 4 +++-
> drivers/scsi/scsi_transport_iscsi.c | 4 +++-
> 2 files changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
> index 70b99c0..adf9bb4 100644
> --- a/drivers/scsi/libiscsi.c
> +++ b/drivers/scsi/libiscsi.c
> @@ -2627,7 +2627,9 @@ 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 = alloc_workqueue("%s",
> + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
> + 2, 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..bdbc4a2 100644
> --- a/drivers/scsi/scsi_transport_iscsi.c
> +++ b/drivers/scsi/scsi_transport_iscsi.c
> @@ -4602,7 +4602,9 @@ static __init int iscsi_transport_init(void)
> goto unregister_flashnode_bus;
> }
>
> - iscsi_eh_timer_workq = create_singlethread_workqueue("iscsi_eh");
> + iscsi_eh_timer_workq = alloc_workqueue("%s",
> + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
> + 2, "iscsi_eh");
> if (!iscsi_eh_timer_workq) {
> err = -ENOMEM;
> goto release_nls;
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue
2020-05-05 1:19 [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue Bob Liu
2020-05-15 0:09 ` Martin K. Petersen
@ 2020-05-25 9:16 ` Bob Liu
2020-05-25 14:28 ` Lee Duncan
2020-05-27 2:12 ` Martin K. Petersen
2 siblings, 1 reply; 5+ messages in thread
From: Bob Liu @ 2020-05-25 9:16 UTC (permalink / raw)
To: open-iscsi; +Cc: lduncan, cleech, jejb, martin.petersen, linux-scsi
friendly ping.
On 5/5/20 9:19 AM, Bob Liu wrote:
> Motivation:
> This patch enable setting cpu affinity through "cpumask" for iscsi workqueues
> (iscsi_q_xx and iscsi_eh), so as to get performance isolation.
>
> The max number of active worker was changed form 1 to 2, because "cpumask" of
> ordered workqueue isn't allowed to change.
>
> Notes:
> - Having 2 workers break the current ordering guarantees, please let me know
> if anyone depends on this.
>
> - __WQ_LEGACY have to be left because of
> 23d11a5(workqueue: skip flush dependency checks for legacy workqueues)
>
> Signed-off-by: Bob Liu <bob.liu@oracle.com>
> ---
> drivers/scsi/libiscsi.c | 4 +++-
> drivers/scsi/scsi_transport_iscsi.c | 4 +++-
> 2 files changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
> index 70b99c0..adf9bb4 100644
> --- a/drivers/scsi/libiscsi.c
> +++ b/drivers/scsi/libiscsi.c
> @@ -2627,7 +2627,9 @@ 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 = alloc_workqueue("%s",
> + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
> + 2, 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..bdbc4a2 100644
> --- a/drivers/scsi/scsi_transport_iscsi.c
> +++ b/drivers/scsi/scsi_transport_iscsi.c
> @@ -4602,7 +4602,9 @@ static __init int iscsi_transport_init(void)
> goto unregister_flashnode_bus;
> }
>
> - iscsi_eh_timer_workq = create_singlethread_workqueue("iscsi_eh");
> + iscsi_eh_timer_workq = alloc_workqueue("%s",
> + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
> + 2, "iscsi_eh");
> if (!iscsi_eh_timer_workq) {
> err = -ENOMEM;
> goto release_nls;
>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue
2020-05-25 9:16 ` Bob Liu
@ 2020-05-25 14:28 ` Lee Duncan
0 siblings, 0 replies; 5+ messages in thread
From: Lee Duncan @ 2020-05-25 14:28 UTC (permalink / raw)
To: Bob Liu, open-iscsi; +Cc: cleech, jejb, martin.petersen, linux-scsi
On 5/25/20 2:16 AM, Bob Liu wrote:
> friendly ping.
>
> On 5/5/20 9:19 AM, Bob Liu wrote:
>> Motivation:
>> This patch enable setting cpu affinity through "cpumask" for iscsi workqueues
>> (iscsi_q_xx and iscsi_eh), so as to get performance isolation.
>>
>> The max number of active worker was changed form 1 to 2, because "cpumask" of
>> ordered workqueue isn't allowed to change.
>>
>> Notes:
>> - Having 2 workers break the current ordering guarantees, please let me know
>> if anyone depends on this.
>>
>> - __WQ_LEGACY have to be left because of
>> 23d11a5(workqueue: skip flush dependency checks for legacy workqueues)
>>
>> Signed-off-by: Bob Liu <bob.liu@oracle.com>
>> ---
>> drivers/scsi/libiscsi.c | 4 +++-
>> drivers/scsi/scsi_transport_iscsi.c | 4 +++-
>> 2 files changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
>> index 70b99c0..adf9bb4 100644
>> --- a/drivers/scsi/libiscsi.c
>> +++ b/drivers/scsi/libiscsi.c
>> @@ -2627,7 +2627,9 @@ 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 = alloc_workqueue("%s",
>> + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
>> + 2, 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..bdbc4a2 100644
>> --- a/drivers/scsi/scsi_transport_iscsi.c
>> +++ b/drivers/scsi/scsi_transport_iscsi.c
>> @@ -4602,7 +4602,9 @@ static __init int iscsi_transport_init(void)
>> goto unregister_flashnode_bus;
>> }
>>
>> - iscsi_eh_timer_workq = create_singlethread_workqueue("iscsi_eh");
>> + iscsi_eh_timer_workq = alloc_workqueue("%s",
>> + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
>> + 2, "iscsi_eh");
>> if (!iscsi_eh_timer_workq) {
>> err = -ENOMEM;
>> goto release_nls;
>>
>
Reviewed-by: Lee Duncan <lduncan@suse.com>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue
2020-05-05 1:19 [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue Bob Liu
2020-05-15 0:09 ` Martin K. Petersen
2020-05-25 9:16 ` Bob Liu
@ 2020-05-27 2:12 ` Martin K. Petersen
2 siblings, 0 replies; 5+ messages in thread
From: Martin K. Petersen @ 2020-05-27 2:12 UTC (permalink / raw)
To: open-iscsi, Bob Liu
Cc: Martin K . Petersen, linux-scsi, jejb, lduncan, cleech
On Tue, 5 May 2020 09:19:08 +0800, Bob Liu wrote:
> Motivation:
> This patch enable setting cpu affinity through "cpumask" for iscsi workqueues
> (iscsi_q_xx and iscsi_eh), so as to get performance isolation.
>
> The max number of active worker was changed form 1 to 2, because "cpumask" of
> ordered workqueue isn't allowed to change.
>
> [...]
Applied to 5.8/scsi-queue, thanks!
[1/1] scsi: iscsi: Register sysfs for iscsi workqueue
https://git.kernel.org/mkp/scsi/c/3ce419662dd4
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2020-05-27 2:15 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-05-05 1:19 [RFC RESEND PATCH v2] scsi: iscsi: register sysfs for iscsi workqueue Bob Liu
2020-05-15 0:09 ` Martin K. Petersen
2020-05-25 9:16 ` Bob Liu
2020-05-25 14:28 ` Lee Duncan
2020-05-27 2:12 ` Martin K. Petersen
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).