check the number of hw queues mapped to sw queues
Subsystems (2)
cover check the number of hw queues mapped to sw queues
From: Ming Lin <[email protected]>
Please see patch 2 for detail bug description.
Say, on a machine with 8 CPUs, we create 6 io queues(blk-mq hw queues)
echo "transport=rdma,traddr=192.168.2.2,nqn=testiqn,nr_io_queues=6" \
> /dev/nvme-fabrics
Then actually only 4 hw queues were mapped to CPU sw queues.
HW Queue 1 <-> CPU 0,4
HW Queue 2 <-> CPU 1,5
HW Queue 3 <-> None
HW Queue 4 <-> CPU 2,6
HW Queue 5 <-> CPU 3,7
HW Queue 6 <-> None
Back to Jan 2016, I send a patch:
[PATCH] blk-mq: check if all HW queues are mapped to cpu
http://www.spinics.net/lists/linux-block/msg01038.html
It adds check code to blk_mq_update_queue_map().
But it seems too aggresive because it's not an error that some hw queues were not mapped to sw queues.
So this series just add a new function blk_mq_hctx_mapped() to check how many hw queues were mapped. And the driver(for example, nvme-rdma) that cares about it will do the check.
Ming Lin (2):
blk-mq: add a function to return number of hw queues mapped
nvme-rdma: check the number of hw queues mapped
block/blk-mq.c | 15 +++++++++++++++ drivers/nvme/host/rdma.c | 11 +++++++++++ include/linux/blk-mq.h | 1 + 3 files changed, 27 insertions(+)
Signature · 1 line
1.9.1
PATCH 1/2 blk-mq: add a function to return number of hw queues mapped
From: Ming Lin <[email protected]>
--- block/blk-mq.c | 15 +++++++++++++++ include/linux/blk-mq.h | 1 + 2 files changed, 16 insertions(+)
block/blk-mq.c +15 -0
@@ -1888,6 +1888,21 @@ static void blk_mq_map_swqueue(struct request_queue *q, } } +/* The number of hw queues that are mapped by sw queues */ +int blk_mq_hctx_mapped (struct request_queue *q) +{ +struct blk_mq_hw_ctx *hctx; +unsigned int i; +int mapped =0 ; + +queue_for_each_hw_ctx (q, hctx, i) +if (blk_mq_hw_queue_mapped (hctx)) + mapped++; + +return mapped; +} +EXPORT_SYMBOL_GPL (blk_mq_hctx_mapped); +static void queue_set_hctx_shared (struct request_queue *q,bool shared) {struct blk_mq_hw_ctx *hctx;
include/linux/blk-mq.h +1 -0
@@ -250,6 +250,7 @@ void blk_mq_freeze_queue_start(struct request_queue *q);int blk_mq_reinit_tagset (struct blk_mq_tag_set *set);void blk_mq_update_nr_hw_queues (struct blk_mq_tag_set *set,int nr_hw_queues); +int blk_mq_hctx_mapped (struct request_queue *q);/* * Driver command data is immediately after the request. So subtract request
Signature · 1 line
1.9.1
PATCH 2/2 nvme-rdma: check the number of hw queues mapped
In reply to Ming LinFrom: Ming Lin <[email protected]>
The connect_q requires all blk-mq hw queues being mapped to cpu sw queues. Otherwise, we got below crash.
[42139.726531] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [42139.734962] IP: [<ffffffff8130e3b5>] blk_mq_get_tag+0x65/0xb0
[42139.977715] Stack: [42139.980382] 0000000081306e9b ffff880035dbc380 ffff88006f71bbf8 ffffffff8130a016 [42139.988436] ffff880035dbc380 0000000000000000 0000000000000001 ffff88011887f000 [42139.996497] ffff88006f71bc50 ffffffff8130bc2a ffff880035dbc380 ffff880000000002 [42140.004560] Call Trace: [42140.007681] [<ffffffff8130a016>] __blk_mq_alloc_request+0x16/0x200 [42140.014584] [<ffffffff8130bc2a>] blk_mq_alloc_request_hctx+0x8a/0xd0 [42140.021662] [<ffffffffc087f28e>] nvme_alloc_request+0x2e/0xa0 [nvme_core] [42140.029171] [<ffffffffc087f32c>] __nvme_submit_sync_cmd+0x2c/0xc0 [nvme_core] [42140.037024] [<ffffffffc08d514a>] nvmf_connect_io_queue+0x10a/0x160 [nvme_fabrics] [42140.045228] [<ffffffffc08de255>] nvme_rdma_connect_io_queues+0x35/0x50 [nvme_rdma] [42140.053517] [<ffffffffc08e0690>] nvme_rdma_create_ctrl+0x490/0x6f0 [nvme_rdma] [42140.061464] [<ffffffffc08d4e48>] nvmf_dev_write+0x728/0x920 [nvme_fabrics] [42140.069072] [<ffffffff81197da3>] __vfs_write+0x23/0x120 [42140.075049] [<ffffffff812de193>] ? apparmor_file_permission+0x13/0x20 [42140.082225] [<ffffffff812a3ab8>] ? security_file_permission+0x38/0xc0 [42140.089391] [<ffffffff81198744>] ? rw_verify_area+0x44/0xb0 [42140.095706] [<ffffffff8119898d>] vfs_write+0xad/0x1a0 [42140.101508] [<ffffffff81199c71>] SyS_write+0x41/0xa0 [42140.107213] [<ffffffff816f1af6>] entry_SYSCALL_64_fastpath+0x1e/0xa8
Say, on a machine with 8 CPUs, we create 6 io queues,
echo "transport=rdma,traddr=192.168.2.2,nqn=testiqn,nr_io_queues=6" \
> /dev/nvme-fabrics
Then actually only 4 hw queues were mapped to CPU sw queues.
HW Queue 1 <-> CPU 0,4
HW Queue 2 <-> CPU 1,5
HW Queue 3 <-> None
HW Queue 4 <-> CPU 2,6
HW Queue 5 <-> CPU 3,7
HW Queue 6 <-> None
So when connecting to IO queue 3, it will crash in blk_mq_get_tag() because hctx->tags is NULL.
This patches doesn't really fix the hw/sw queues mapping, but it returns error if not all hw queues were mapped.
"nvme nvme4: 6 hw queues created, but only 4 were mapped to sw queues"
--- drivers/nvme/host/rdma.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
drivers/nvme/host/rdma.c +11 -0
@@ -1771,6 +1771,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {static int nvme_rdma_create_io_queues (struct nvme_rdma_ctrl *ctrl) {struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; +int hw_queue_mapped;int ret; ret =nvme_set_queue_count (&ctrl->ctrl, &opts->nr_io_queues);
@@ -1819,6 +1820,16 @@ static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl) goto out_free_tag_set; } + hw_queue_mapped =blk_mq_hctx_mapped (ctrl->ctrl.connect_q); +if (hw_queue_mapped < ctrl->ctrl.connect_q->nr_hw_queues) { +dev_err (ctrl->ctrl.device, +"%d hw queues created, but only %d were mapped to sw queues\n" , + ctrl->ctrl.connect_q->nr_hw_queues, + hw_queue_mapped); + ret = -EINVAL ; + goto out_cleanup_connect_q; + } + ret =nvme_rdma_connect_io_queues (ctrl);if (ret) goto out_cleanup_connect_q;
Signature · 1 line
1.9.1
Quoted 11 lines · Ming Lin
Back to Jan 2016, I send a patch:
[PATCH] blk-mq: check if all HW queues are mapped to cpu
http://www.spinics.net/lists/linux-block/msg01038.htmlIt adds check code to
blk_mq_update_queue_map().
But it seems too aggresive because it's not an error that some hw queues were not mapped to sw queues.So this series just add a new function
blk_mq_hctx_mapped()to check how many hw queues were mapped. And thedriver(for example, nvme-rdma)that cares about it will do the check.
Wouldn't you prefer all 6 get assigned in this scenario instead of utilizing fewer resources than your controller provides? I would like blk-mq to use them all.
I've been trying to change blk_mq_update_queue_map to do this, but it's not as easy as it sounds. The following is the simplest patch I came up with that gets a better mapping *most* of the time.
I have 31 queues and 32 CPUs, and these are the results:
# for i in $(ls -1v /sys/block/nvme0n1/mq/); do
printf "hctx_idx %2d: " $i
cat /sys/block/nvme0n1/mq/$i/cpu_list
doneBefore:
hctx_idx 0: 0, 16hctx_idx 1: 1, 17hctx_idx 3: 2, 18hctx_idx 5: 3, 19hctx_idx 7: 4, 20hctx_idx 9: 5, 21hctx_idx 11: 6, 22hctx_idx 13: 7, 23hctx_idx 15: 8, 24hctx_idx 17: 9, 25hctx_idx 19: 10, 26hctx_idx 21: 11, 27hctx_idx 23: 12, 28hctx_idx 25: 13, 29hctx_idx 27: 14, 30hctx_idx 29: 15, 31
After:
hctx_id 0: 0, 16hctx_id 1: 1hctx_id 2: 2hctx_id 3: 3hctx_id 4: 4hctx_id 5: 5hctx_id 6: 6hctx_id 7: 7hctx_id 8: 8hctx_id 9: 9hctx_id 10: 10hctx_id 11: 11hctx_id 12: 12hctx_id 13: 13hctx_id 14: 14hctx_id 15: 15hctx_id 16: 17hctx_id 17: 18hctx_id 18: 19hctx_id 19: 20hctx_id 20: 21hctx_id 21: 22hctx_id 22: 23hctx_id 23: 24hctx_id 24: 25hctx_id 25: 26hctx_id 26: 27hctx_id 27: 28hctx_id 28: 29hctx_id 29: 30hctx_id 30: 31
---
block/blk-mq-cpumap.c +4 -3
@@ -75,11 +75,12 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,*/ first_sibling =get_first_sibling (i);if (first_sibling == i) { - map[i] =cpu_to_queue_index (nr_uniq_cpus, nr_queues, - queue); + map[i] =cpu_to_queue_index (max (nr_queues, (nr_cpus - queue)), nr_queues, queue); queue++; - }else + }else { map[i] = map[first_sibling]; + --nr_cpus; + } }free_cpumask_var (cpus);
--
Quoted 9 lines · Keith Busch
Quoted 8 lines · Ming Lin
Back to Jan 2016, I send a patch:
[PATCH] blk-mq: check if all HW queues are mapped to cpu
http://www.spinics.net/lists/linux-block/msg01038.htmlIt adds check code to
blk_mq_update_queue_map().
But it seems too aggresive because it's not an error that some hw queues were not mapped to sw queues.
Quoted 7 lines
Quoted 3 lines
So this series just add a new function
blk_mq_hctx_mapped()to check how many hw queues were mapped. And thedriver(for example, nvme-rdma)that cares about it will do the check.Wouldn't you prefer all 6 get assigned in this scenario instead of utilizing fewer resources than your controller provides? I would like blk-mq to use them all.
That's ideal.
But we'll always see corner case that there is hctx(s) not mapped. So I want to at least prevent the crash and return an error in the driver.
Here is another example that I create 64 queues on a server with 72 cpus.
hctx index 0: 0, 36
hctx index 1: 1, 37
hctx index 3: 2, 38
hctx index 5: 3, 39
hctx index 7: 4, 40
hctx index 8: 5, 41
hctx index 10: 6, 42
hctx index 12: 7, 43
hctx index 14: 8, 44
hctx index 16: 9, 45
hctx index 17: 10, 46
hctx index 19: 11, 47
hctx index 21: 12, 48
hctx index 23: 13, 49
hctx index 24: 14, 50
hctx index 26: 15, 51
hctx index 28: 16, 52
hctx index 30: 17, 53
hctx index 32: 18, 54
hctx index 33: 19, 55
hctx index 35: 20, 56
hctx index 37: 21, 57
hctx index 39: 22, 58
hctx index 40: 23, 59
hctx index 42: 24, 60
hctx index 44: 25, 61
hctx index 46: 26, 62
hctx index 48: 27, 63
hctx index 49: 28, 64
hctx index 51: 29, 65
hctx index 53 30, 66
hctx index 55: 31, 67 hctx index 56: 32, 68 hctx index 58: 33, 69 hctx index 60: 34, 70 hctx index 62: 35, 71
Other hctxs are not mapped.
Quoted 4 lines
I've been trying to change
blk_mq_update_queue_mapto do this, but it's not as easy as it sounds. The following is the simplest patch I came up with that gets a better mapping *most* of the time.
Not working for my case with 6 hw queues(8 cpus):
[ 108.318247] nvme nvme0: 6 hw queues created, but only 5 were mapped
to sw queues
hctx_idx 0: 0 1 4 5hctx_idx 1: Nonehctx_idx 2: 2hctx_idx 3: 3hctx_idx 4: 6hctx_idx 5: 7
Quoted 23 lines
---
block/blk-mq-cpumap.c +4
-4@@ -75,11 +75,12 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,*/ first_sibling =get_first_sibling (i);if (first_sibling == i) { - map[i] =cpu_to_queue_index (nr_uniq_cpus, nr_queues, - queue); + map[i] =cpu_to_queue_index (max (nr_queues, (nr_cpus - queue)), nr_queues, queue); queue++; - }else + }else { map[i] = map[first_sibling]; + --nr_cpus; + } }free_cpumask_var (cpus); --
Quoted 8 lines · Ming Lin
Quoted 3 lines · Keith Busch
I've been trying to change
blk_mq_update_queue_mapto do this, but it's not as easy as it sounds. The following is the simplest patch I came up with that gets a better mapping *most* of the time.Not working for my case with 6 hw queues(8 cpus):
[ 108.318247] nvme nvme0: 6 hw queues created, but only 5 were mapped
Quoted 8 lines
to sw queues
hctx_idx0: 0 1 4 5hctx_idx1: Nonehctx_idx2: 2hctx_idx3: 3hctx_idx4: 6hctx_idx5: 7
Heh, not one of the good cases I see. I don't think there's a simple change to use all contexts. Might need a larger rewrite.
Re: [PATCH 2/2] nvme-rdma: check the number of hw queues mapped
In reply to Ming LinThis needs documentation in the form of:
/*
* XXX: blk-mq might not map all our hw contexts but this is a must for
* us for fabric connects. So until we can fix blk-mq we check that. */
Quoted 14 lines
drivers/nvme/host/rdma.c +10
-0+ hw_queue_mapped =blk_mq_hctx_mapped (ctrl->ctrl.connect_q); +if (hw_queue_mapped < ctrl->ctrl.connect_q->nr_hw_queues) { +dev_err (ctrl->ctrl.device, +"%d hw queues created, but only %d were mapped to sw queues\n" , + ctrl->ctrl.connect_q->nr_hw_queues, + hw_queue_mapped); + ret = -EINVAL ; + goto out_cleanup_connect_q; + } + ret =nvme_rdma_connect_io_queues (ctrl);if (ret) goto out_cleanup_connect_q;
Christoph Hellwig
maintainerQuoted 7 lines · Ming Lin
It adds check code to
blk_mq_update_queue_map().
But it seems too aggresive because it's not an error that some hw queues were not mapped to sw queues.So this series just add a new function
blk_mq_hctx_mapped()to check how many hw queues were mapped. And thedriver(for example, nvme-rdma)that cares about it will do the check.
I think it would be better to have this number available a structure field. Any reason not to update nr_hw_queues in the tag set with the actual number of queues?
Christoph Hellwig
maintainerRe: [PATCH 2/2] nvme-rdma: check the number of hw queues mapped
In reply to Sagi GrimbergQuoted 6 lines · Sagi Grimberg
This needs documentation in the form of:
/*
* XXX: blk-mq might not map all our hw contexts but this is a must for
* us for fabric connects. So until we can fix blk-mq we check that. */
I think the right thing to do is to have a member of actually mapped queues in the block layer, and I also don't think we need the XXX comment as there are valid reasons for not mapping all queues.
Quoted 5 lines · Christoph Hellwig
Quoted 4 lines · Ming Lin
It adds check code to
blk_mq_update_queue_map().
But it seems too aggresive because it's not an error that some hw queues were not mapped to sw queues.
Quoted 7 lines
Quoted 3 lines
So this series just add a new function
blk_mq_hctx_mapped()to check how many hw queues were mapped. And thedriver(for example, nvme-rdma)that cares about it will do the check.I think it would be better to have this number available a structure field. Any reason not to update
nr_hw_queuesin the tag set with the actual number of queues?
One reason is we don't know which hctx(s) not mapped.
HW Queue 1 <-> CPU 0,4
HW Queue 2 <-> CPU 1,5
HW Queue 3 <-> None
HW Queue 4 <-> CPU 2,6
HW Queue 5 <-> CPU 3,7
HW Queue 6 <-> None
If we updated nr_hw_queues from 6 to 4,
then queue_for_each_hw_ctx will not work.
#define queue_for_each_hw_ctx(q, hctx, i) \
for ((i) = 0; (i) < (q)->nr_hw_queues && \
({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)Re: [PATCH 2/2] nvme-rdma: check the number of hw queues mapped
In reply to Christoph HellwigQuoted 11 lines · Christoph Hellwig
Quoted 6 lines · Sagi Grimberg
This needs documentation in the form of:
/*
* XXX: blk-mq might not map all our hw contexts but this is a must for
* us for fabric connects. So until we can fix blk-mq we check that. */I think the right thing to do is to have a member of actually mapped queues in the block layer, and I also don't think we need the XXX comment as there are valid reasons for not mapping all queues.
I think it is a rare case that we need all hw contexts mapped. Seems unnecessary to add a new field to "struct request_queue" for the rare case.