Re: [PATCH rfc 5/6] block: Add rdma affinity based queue mapping helper

[Sagi Grimberg]

shouldn't you include   and  like in
commit 8ec2ef2b66ea2f that fixes blk-mq-pci.c ?


Not really. We can lose these from blk-mq-pci.c as well.


+#include 
+#include 
+#include 
+#include 
+#include "blk-mq.h"


Is this include needed ?


You're right, I can just keep:

+#include 
+#include 
+#include 

Re: [PATCH rfc 5/6] block: Add rdma affinity based queue mapping helper

[Jens Axboe]

On 04/02/2017 07:41 AM, Sagi Grimberg wrote:
> Like pci and virtio, we add a rdma helper for affinity
> spreading. This achieves optimal mq affinity assignments
> according to the underlying rdma device affinity maps.

Reviewed-by: Jens Axboe 

-- 
Jens Axboe

Re: [PATCH rfc 5/6] block: Add rdma affinity based queue mapping helper

[Christoph Hellwig]

On Tue, Apr 04, 2017 at 10:46:54AM +0300, Max Gurtovoy wrote:
>> +if (set->nr_hw_queues > dev->num_comp_vectors)
>> +goto fallback;
>> +
>> +for (queue = 0; queue < set->nr_hw_queues; queue++) {
>> +mask = ib_get_vector_affinity(dev, first_vec + queue);
>> +if (!mask)
>> +goto fallback;
>
> Christoph,
> we can use fallback also in the blk-mq-pci.c in case pci_irq_get_affinity 
> fails, right ?

For PCI it shouldn't fail as the driver calling pci_irq_get_affinity
knows how it set up the interrupts.  So I don't think it's necessary there.

Re: [PATCH rfc 5/6] block: Add rdma affinity based queue mapping helper

[Max Gurtovoy]

diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c
new file mode 100644
index ..d402f7c93528
--- /dev/null
+++ b/block/blk-mq-rdma.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2017 Sagi Grimberg.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */


shouldn't you include   and  like in 
commit 8ec2ef2b66ea2f that fixes blk-mq-pci.c ?



+#include 
+#include 
+#include 
+#include 
+#include "blk-mq.h"


Is this include needed ?



+
+/**
+ * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
+ * @set:   tagset to provide the mapping for
+ * @dev:   rdma device associated with @set.
+ * @first_vec: first interrupt vectors to use for queues (usually 0)
+ *
+ * This function assumes the rdma device @dev has at least as many available
+ * interrupt vetors as @set has queues.  It will then query it's affinity mask
+ * and built queue mapping that maps a queue to the CPUs that have irq affinity
+ * for the corresponding vector.
+ *
+ * In case either the driver passed a @dev with less vectors than
+ * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
+ * vector, we fallback to the naive mapping.
+ */
+int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+   struct ib_device *dev, int first_vec)
+{
+   const struct cpumask *mask;
+   unsigned int queue, cpu;
+
+   if (set->nr_hw_queues > dev->num_comp_vectors)
+   goto fallback;
+
+   for (queue = 0; queue < set->nr_hw_queues; queue++) {
+   mask = ib_get_vector_affinity(dev, first_vec + queue);
+   if (!mask)
+   goto fallback;


Christoph,
we can use fallback also in the blk-mq-pci.c in case 
pci_irq_get_affinity fails, right ?



+
+   for_each_cpu(cpu, mask)
+   set->mq_map[cpu] = queue;
+   }
+
+   return 0;
+fallback:
+   return blk_mq_map_queues(set);
+}
+EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);


Otherwise, Looks good.

Reviewed-by: Max Gurtovoy 

Re: [PATCH rfc 5/6] block: Add rdma affinity based queue mapping helper

[Christoph Hellwig]

On Sun, Apr 02, 2017 at 04:41:31PM +0300, Sagi Grimberg wrote:
> Like pci and virtio, we add a rdma helper for affinity
> spreading. This achieves optimal mq affinity assignments
> according to the underlying rdma device affinity maps.
> 
> Signed-off-by: Sagi Grimberg 
> ---
>  block/Kconfig   |  5 
>  block/Makefile  |  1 +
>  block/blk-mq-rdma.c | 56 
> +
>  include/linux/blk-mq-rdma.h | 10 
>  4 files changed, 72 insertions(+)
>  create mode 100644 block/blk-mq-rdma.c
>  create mode 100644 include/linux/blk-mq-rdma.h
> 
> diff --git a/block/Kconfig b/block/Kconfig
> index 89cd28f8d051..3ab42bbb06d5 100644
> --- a/block/Kconfig
> +++ b/block/Kconfig
> @@ -206,4 +206,9 @@ config BLK_MQ_VIRTIO
>   depends on BLOCK && VIRTIO
>   default y
>  
> +config BLK_MQ_RDMA
> + bool
> + depends on BLOCK && INFINIBAND
> + default y
> +
>  source block/Kconfig.iosched
> diff --git a/block/Makefile b/block/Makefile
> index 081bb680789b..4498603dbc83 100644
> --- a/block/Makefile
> +++ b/block/Makefile
> @@ -26,6 +26,7 @@ obj-$(CONFIG_BLK_CMDLINE_PARSER)+= cmdline-parser.o
>  obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
>  obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o
>  obj-$(CONFIG_BLK_MQ_VIRTIO)  += blk-mq-virtio.o
> +obj-$(CONFIG_BLK_MQ_RDMA)+= blk-mq-rdma.o
>  obj-$(CONFIG_BLK_DEV_ZONED)  += blk-zoned.o
>  obj-$(CONFIG_BLK_WBT)+= blk-wbt.o
>  obj-$(CONFIG_BLK_DEBUG_FS)   += blk-mq-debugfs.o
> diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c
> new file mode 100644
> index ..d402f7c93528
> --- /dev/null
> +++ b/block/blk-mq-rdma.c
> @@ -0,0 +1,56 @@
> +/*
> + * Copyright (c) 2017 Sagi Grimberg.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + */
> +#include 
> +#include 
> +#include 
> +#include 
> +#include "blk-mq.h"
> +
> +/**
> + * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
> + * @set: tagset to provide the mapping for
> + * @dev: rdma device associated with @set.
> + * @first_vec:   first interrupt vectors to use for queues (usually 0)
> + *
> + * This function assumes the rdma device @dev has at least as many available
> + * interrupt vetors as @set has queues.  It will then query it's affinity 
> mask
> + * and built queue mapping that maps a queue to the CPUs that have irq 
> affinity
> + * for the corresponding vector.
> + *
> + * In case either the driver passed a @dev with less vectors than
> + * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
> + * vector, we fallback to the naive mapping.
> + */
> +int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
> + struct ib_device *dev, int first_vec)
> +{
> + const struct cpumask *mask;
> + unsigned int queue, cpu;
> +
> + if (set->nr_hw_queues > dev->num_comp_vectors)
> + goto fallback;

maybe print a warning here?

Otherwise looks fine:

Reviewed-by: Christoph Hellwig 

[PATCH rfc 5/6] block: Add rdma affinity based queue mapping helper

[Sagi Grimberg]

Like pci and virtio, we add a rdma helper for affinity
spreading. This achieves optimal mq affinity assignments
according to the underlying rdma device affinity maps.

Signed-off-by: Sagi Grimberg 
---
 block/Kconfig   |  5 
 block/Makefile  |  1 +
 block/blk-mq-rdma.c | 56 +
 include/linux/blk-mq-rdma.h | 10 
 4 files changed, 72 insertions(+)
 create mode 100644 block/blk-mq-rdma.c
 create mode 100644 include/linux/blk-mq-rdma.h

diff --git a/block/Kconfig b/block/Kconfig
index 89cd28f8d051..3ab42bbb06d5 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -206,4 +206,9 @@ config BLK_MQ_VIRTIO
depends on BLOCK && VIRTIO
default y
 
+config BLK_MQ_RDMA
+   bool
+   depends on BLOCK && INFINIBAND
+   default y
+
 source block/Kconfig.iosched
diff --git a/block/Makefile b/block/Makefile
index 081bb680789b..4498603dbc83 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_BLK_CMDLINE_PARSER)  += cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)   += blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)+= blk-mq-virtio.o
+obj-$(CONFIG_BLK_MQ_RDMA)  += blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)  += blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o
diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c
new file mode 100644
index ..d402f7c93528
--- /dev/null
+++ b/block/blk-mq-rdma.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2017 Sagi Grimberg.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include 
+#include 
+#include 
+#include 
+#include "blk-mq.h"
+
+/**
+ * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
+ * @set:   tagset to provide the mapping for
+ * @dev:   rdma device associated with @set.
+ * @first_vec: first interrupt vectors to use for queues (usually 0)
+ *
+ * This function assumes the rdma device @dev has at least as many available
+ * interrupt vetors as @set has queues.  It will then query it's affinity mask
+ * and built queue mapping that maps a queue to the CPUs that have irq affinity
+ * for the corresponding vector.
+ *
+ * In case either the driver passed a @dev with less vectors than
+ * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
+ * vector, we fallback to the naive mapping.
+ */
+int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+   struct ib_device *dev, int first_vec)
+{
+   const struct cpumask *mask;
+   unsigned int queue, cpu;
+
+   if (set->nr_hw_queues > dev->num_comp_vectors)
+   goto fallback;
+
+   for (queue = 0; queue < set->nr_hw_queues; queue++) {
+   mask = ib_get_vector_affinity(dev, first_vec + queue);
+   if (!mask)
+   goto fallback;
+
+   for_each_cpu(cpu, mask)
+   set->mq_map[cpu] = queue;
+   }
+
+   return 0;
+fallback:
+   return blk_mq_map_queues(set);
+}
+EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);
diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h
new file mode 100644
index ..b4ade198007d
--- /dev/null
+++ b/include/linux/blk-mq-rdma.h
@@ -0,0 +1,10 @@
+#ifndef _LINUX_BLK_MQ_RDMA_H
+#define _LINUX_BLK_MQ_RDMA_H
+
+struct blk_mq_tag_set;
+struct ib_device;
+
+int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+   struct ib_device *dev, int first_vec);
+
+#endif /* _LINUX_BLK_MQ_RDMA_H */
-- 
2.7.4