On Fri, Mar 30, 2018 at 09:04:46AM +, Eric H. Chang wrote:
> We internally call PCIe-retimer as HBA. It's not a real Host Bus Adapter that
> translates the interface from PCIe to SATA or SAS. Sorry for the confusion.
Please don't call a PCIe retimer an "HBA"! :)
While your experiment is
On Fri, Mar 30, 2018 at 09:04:46AM +, Eric H. Chang wrote:
> We internally call PCIe-retimer as HBA. It's not a real Host Bus Adapter that
> translates the interface from PCIe to SATA or SAS. Sorry for the confusion.
Please don't call a PCIe retimer an "HBA"! :)
While your experiment is
@@ -85,7 +121,14 @@ static blk_qc_t nvme_ns_head_make_request(struct
request_queue *q,
int srcu_idx;
srcu_idx = srcu_read_lock(>srcu);
- ns = nvme_find_path(head);
+ switch (head->mpath_policy) {
+ case NVME_MPATH_ROUND_ROBIN:
+ ns =
@@ -85,7 +121,14 @@ static blk_qc_t nvme_ns_head_make_request(struct
request_queue *q,
int srcu_idx;
srcu_idx = srcu_read_lock(>srcu);
- ns = nvme_find_path(head);
+ switch (head->mpath_policy) {
+ case NVME_MPATH_ROUND_ROBIN:
+ ns =
For PCIe devices the right policy is not a round robin but to use
the pcie device closer to the node. I did a prototype for that
long ago and the concept can work. Can you look into that and
also make that policy used automatically for PCIe devices?
I think that active/active makes sense
For PCIe devices the right policy is not a round robin but to use
the pcie device closer to the node. I did a prototype for that
long ago and the concept can work. Can you look into that and
also make that policy used automatically for PCIe devices?
I think that active/active makes sense
On Fri, Mar 30, 2018 at 01:57:25PM +0900, Baegjae Sung wrote:
> Our prototype uses dual-ported PCIe NVMe connected to a single host. The
> host's HBA is connected to two switches,
What "HBA"? We are talking about NVMe here..
On Fri, Mar 30, 2018 at 01:57:25PM +0900, Baegjae Sung wrote:
> Our prototype uses dual-ported PCIe NVMe connected to a single host. The
> host's HBA is connected to two switches,
What "HBA"? We are talking about NVMe here..
2018-03-29 4:47 GMT+09:00 Keith Busch :
> On Wed, Mar 28, 2018 at 10:06:46AM +0200, Christoph Hellwig wrote:
>> For PCIe devices the right policy is not a round robin but to use
>> the pcie device closer to the node. I did a prototype for that
>> long ago and the concept
2018-03-29 4:47 GMT+09:00 Keith Busch :
> On Wed, Mar 28, 2018 at 10:06:46AM +0200, Christoph Hellwig wrote:
>> For PCIe devices the right policy is not a round robin but to use
>> the pcie device closer to the node. I did a prototype for that
>> long ago and the concept can work. Can you look
On Wed, Mar 28, 2018 at 01:47:41PM -0600, Keith Busch wrote:
> single host (single path from two hosts seems more common). If that's a
> thing, we should get some numa awareness. I couldn't find your prototype,
> though. I had one stashed locally from a while back and hope it resembles
> what you
On Wed, Mar 28, 2018 at 01:47:41PM -0600, Keith Busch wrote:
> single host (single path from two hosts seems more common). If that's a
> thing, we should get some numa awareness. I couldn't find your prototype,
> though. I had one stashed locally from a while back and hope it resembles
> what you
On Wed, Mar 28, 2018 at 10:06:46AM +0200, Christoph Hellwig wrote:
> For PCIe devices the right policy is not a round robin but to use
> the pcie device closer to the node. I did a prototype for that
> long ago and the concept can work. Can you look into that and
> also make that policy used
On Wed, Mar 28, 2018 at 10:06:46AM +0200, Christoph Hellwig wrote:
> For PCIe devices the right policy is not a round robin but to use
> the pcie device closer to the node. I did a prototype for that
> long ago and the concept can work. Can you look into that and
> also make that policy used
For PCIe devices the right policy is not a round robin but to use
the pcie device closer to the node. I did a prototype for that
long ago and the concept can work. Can you look into that and
also make that policy used automatically for PCIe devices?
For PCIe devices the right policy is not a round robin but to use
the pcie device closer to the node. I did a prototype for that
long ago and the concept can work. Can you look into that and
also make that policy used automatically for PCIe devices?
Some storage environments (e.g., dual-port NVMe SSD) provide higher
performance when using multiple paths simultaneously. Choosing a
path from multiple paths in a round-robin fashion is a simple and
efficient way to meet these requirements.
We implement the active-active round-robin path selector
Some storage environments (e.g., dual-port NVMe SSD) provide higher
performance when using multiple paths simultaneously. Choosing a
path from multiple paths in a round-robin fashion is a simple and
efficient way to meet these requirements.
We implement the active-active round-robin path selector
18 matches
Mail list logo