>Subject: Re: [PATCH v2] block: fix rdma queue mapping
>
>
>> Sagi - From what I can tell, i40iw is also exposed to this same issue
>> if the IRQ affinity is configured by user.
>
>managed affinity does not allow setting smp_affinity from userspace.
OK. But our device IRQs are not set-up as to be
On Mon, Oct 29, 2018 at 02:32:34PM -0700, Bart Van Assche wrote:
> > Well the potential integer truncation that could happen is here:
> >
> > case 'l': len = strtoul(optarg, NULL, 0); break;
>
> If the data type of 'len' would be changed into unsigned long, how could that
>
On Mon, 2018-10-29 at 17:08 -0400, Theodore Y. Ts'o wrote:
> On Mon, Oct 29, 2018 at 09:26:43AM -0700, Bart Van Assche wrote:
> >
> > Have you considered to change the data type of 'len' from size_t into
> > unsigned long
> > instead of inserting this cast? That would make it clear that no
On Mon, Oct 29, 2018 at 09:26:43AM -0700, Bart Van Assche wrote:
>
> Have you considered to change the data type of 'len' from size_t into
> unsigned long
> instead of inserting this cast? That would make it clear that no integer
> truncation
> happens in the iov.append() call.
Well the
On 10/29/18 9:51 AM, Mike Snitzer wrote:
> On Mon, Oct 29 2018 at 10:25am -0400,
> Jens Axboe wrote:
>
>> On 10/29/18 1:10 AM, Hannes Reinecke wrote:
>>> On 10/25/18 11:10 PM, Jens Axboe wrote:
Nobody sets the helper, so we always return 0. Kill it.
Signed-off-by: Jens Axboe
On Mon, 2018-10-29 at 12:15 -0400, Theodore Ts'o wrote:
> Signed-off-by: Theodore Ts'o
> ---
> src/discontiguous-io.cpp | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/src/discontiguous-io.cpp b/src/discontiguous-io.cpp
> index 5e0ee0f..a59c18d 100644
> ---
Signed-off-by: Theodore Ts'o
---
check | 3 +++
1 file changed, 3 insertions(+)
diff --git a/check b/check
index f6c3537..ebd87c0 100755
--- a/check
+++ b/check
@@ -319,6 +319,7 @@ _call_test() {
local dmesg_marker=""
CHECK_DMESG=0
fi
+ $LOGGER_PROG
Signed-off-by: Theodore Ts'o
---
src/discontiguous-io.cpp | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/discontiguous-io.cpp b/src/discontiguous-io.cpp
index 5e0ee0f..a59c18d 100644
--- a/src/discontiguous-io.cpp
+++ b/src/discontiguous-io.cpp
@@ -291,7 +291,7 @@ int
On 10/29/18 5:11 AM, Matias Bjorling wrote:
> Looks good to me. One nitpick, might be better to rename the sysfs
> attribute nr_conv_zones to zone_nr_conv or similar to keep the zone
> attributes grouped together.
Yeah I agree, that's the only real way to inject some sanity into having
a
Obviously the created writesame bio has to be aligned with logical block
size, and use bio_allowed_max_sectors() to retrieve this number.
Fixes: b49a0871be31a745b2ef ("block: remove split code in
blkdev_issue_{discard,write_same}")
Cc: Rui Salvaterra
Cc: sta...@vger.kernel.org
Cc: Mike Snitzer
Cleanup __blkdev_issue_discard() a bit:
- remove local variable of 'end_sect'
- remove code block of 'fail'
Cc: Rui Salvaterra
Cc: Mike Snitzer
Cc: Christoph Hellwig
Cc: Xiao Ni
Cc: Mariusz Dabrowski
Signed-off-by: Ming Lei
---
block/blk-lib.c | 23 ++-
1 file changed,
Hi,
The 1st & 3rd patch fixes bio size alignment issue.
The 2nd patch cleans up __blkdev_issue_discard() a bit.
V2:
- introduce helper of bio_allowed_max_sectors()
- add commit log for patch 2
Ming Lei (3):
block: make sure discard bio is aligned with logical block size
Obviously the created discard bio has to be aligned with logical block size.
This patch introduces the helper of bio_allowed_max_sectors() for
this purpose.
Fixes: 744889b7cbb56a6 ("block: don't deal with discard limit in
blkdev_issue_discard()")
Fixes: a22c4d7e34402cc ("block: re-add
> On 22 Oct 2018, at 12.36, Igor Konopko wrote:
>
> Currently pblk and lightnvm does only check for size
> of OOB metadata and does not care wheather this meta
> is located in separate buffer or is interleaved with
> data in single buffer.
>
> In reality only the first scenario is supported,
> On 22 Oct 2018, at 12.36, Igor Konopko wrote:
>
> Currently whole lightnvm and pblk uses single DMA pool,
> for which entry size is always equal to PAGE_SIZE.
> PPA list always needs 8b*64, so there is only 56b*64
> space for OOB meta. Since NVMe OOB meta can be bigger,
> such as 128b, this
On 10/22/2018 01:25 PM, Masato Suzuki wrote:
> Allow the creation of conventional zones by adding the nr_conv_zones
> configuration attribute. This new attribute is used only for zoned devices and
> indicates the number of conventional zones to create. The default value is 0.
> Since host-managed
> On 22 Oct 2018, at 12.36, Igor Konopko wrote:
>
> Currently pblk assumes that size of OOB metadata on drive is always
> equal to size of pblk_sec_meta struct. This commit add helpers which will
> allow to handle different sizes of OOB metadata on drive.
Probably want to mention the constrain
> On 22 Oct 2018, at 12.36, Igor Konopko wrote:
>
> Currently DMA allocated memory is reused on partial read
> for lba_list_mem and lba_list_media arrays. In preparation
> for dynamic DMA pool sizes we need to move this arrays
> into pblk_pr_ctx structures.
>
> Signed-off-by: Igor Konopko
>
On 10/29/18 11:00 AM, Jens Axboe wrote:
> On 10/28/18 8:40 PM, jianchao.wang wrote:
>>
>>
>> On 10/29/18 10:02 AM, jianchao.wang wrote:
>>> Hi Jens
>>>
>>> On 10/28/18 12:52 AM, Jens Axboe wrote:
On 10/27/18 10:48 AM, Jens Axboe wrote:
> On 10/27/18 8:19 AM, jianchao.wang wrote:
>>
On 2018/10/22 20:25, Masato Suzuki wrote:
> Allow the creation of conventional zones by adding the nr_conv_zones
> configuration attribute. This new attribute is used only for zoned devices and
> indicates the number of conventional zones to create. The default value is 0.
> Since host-managed
On 10/25/18 11:16 PM, Jens Axboe wrote:
Adds support for defining a variable number of poll queues, currently
configurable with the 'poll_queues' module parameter. Defaults to
a single poll queue.
And now we finally have poll support without triggering interrupts!
Signed-off-by: Jens Axboe
On 10/25/18 11:16 PM, Jens Axboe wrote:
We use IOCB_HIPRI to poll for IO in the caller instead of scheduling.
This information is not available for (or after) IO submission. The
driver may make different queue choices based on the type of IO, so
make the fact that we will poll for this IO known
On 10/25/18 11:16 PM, Jens Axboe wrote:
NVMe does round-robin between queues by default, which means that
sharing a queue map for both reads and writes can be problematic
in terms of read servicing. It's much easier to flood the queue
with writes and reduce the read servicing.
Implement two
On 10/25/18 11:16 PM, Jens Axboe wrote:
Add a queue offset to the tag map. This enables users to map
iteratively, for each queue map type they support.
Bump maximum number of supported maps to 2, we're now fully
able to support more than 1 map.
Signed-off-by: Jens Axboe
---
On 10/25/18 11:16 PM, Jens Axboe wrote:
Since we insert per hardware queue, we have to ensure that every
request on the plug list being inserted belongs to the same
hardware queue.
Signed-off-by: Jens Axboe
---
block/blk-mq.c | 27 +--
1 file changed, 25
On 10/25/18 11:16 PM, Jens Axboe wrote:
With multiple maps, nr_cpu_ids is no longer the maximum number of
hardware queues we support on a given devices. The initializer of
the tag_set can have set ->nr_hw_queues larger than the available
number of CPUs, since we can exceed that with multiple
On 10/25/18 11:16 PM, Jens Axboe wrote:
Add support for the tag set carrying multiple queue maps, and
for the driver to inform blk-mq how many it wishes to support
through setting set->nr_maps.
This adds an mq_ops helper for drivers that support more than 1
map, mq_ops->flags_to_type(). The
On 10/25/18 11:16 PM, Jens Axboe wrote:
It can be useful for a user to verify what type a given hardware
queue is, expose this information in sysfs.
Signed-off-by: Jens Axboe
---
block/blk-mq-sysfs.c | 10 ++
1 file changed, 10 insertions(+)
Reviewed-by: Hannes Reinecke
Cheers,
On 10/25/18 11:16 PM, Jens Axboe wrote:
The mapping used to be dependent on just the CPU location, but
now it's a tuple of { type, cpu} instead. This is a prep patch
for allowing a single software queue to map to multiple hardware
queues. No functional changes in this patch.
Signed-off-by: Jens
On 10/25/18 11:16 PM, Jens Axboe wrote:
Prep patch for being able to place request based not just on
CPU location, but also on the type of request.
Signed-off-by: Jens Axboe
---
block/blk-flush.c | 7 +++---
block/blk-mq-debugfs.c | 4 +++-
block/blk-mq-sched.c | 16 ++
On 10/25/18 11:16 PM, Jens Axboe wrote:
Doesn't do anything right now, but it's needed as a prep patch
to get the interfaces right.
Signed-off-by: Jens Axboe
---
block/blk-mq.h | 6 ++
1 file changed, 6 insertions(+)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index
On 10/25/18 11:16 PM, Jens Axboe wrote:
This is in preparation for allowing multiple sets of maps per
queue, if so desired.
Signed-off-by: Jens Axboe
---
block/blk-mq-cpumap.c | 10
block/blk-mq-pci.c| 10
block/blk-mq-rdma.c
On 10/25/18 11:16 PM, Jens Axboe wrote:
It's just a pointer to set->mq_map, use that instead.
Signed-off-by: Jens Axboe
---
block/blk-mq.c | 13 -
block/blk-mq.h | 4 +++-
include/linux/blkdev.h | 2 --
3 files changed, 7 insertions(+), 12 deletions(-)
33 matches
Mail list logo