Re: [PATCH rdma-next v1 1/3] RDMA/core: Increase total number of RDMA ports across all devices

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Oct 03, 2018 at 11:15:08AM -0400, Dennis Dalessandro wrote:
> On 10/2/2018 4:13 AM, Leon Romanovsky wrote:
> > From: Leon Romanovsky <leonro@xxxxxxxxxxxx>
> >
> > IDA adds overhead to store IDs bitmap with maximal value of IDA
> > can be upto 2099202 (IDA_MAX = 0x80000000U / IDA_BITMAP_BITS - 1).
> >
> > However, there is no need to add such enormous number of devices
> > and it is enough for now to limit it to be 8192.
> >
> > Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxxxx>
> > ---
> >   drivers/infiniband/core/core_priv.h | 2 +-
> >   1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
> > index d7399d5b1cb6..f60c7b65aea9 100644
> > --- a/drivers/infiniband/core/core_priv.h
> > +++ b/drivers/infiniband/core/core_priv.h
> > @@ -44,7 +44,7 @@
> >   #include "mad_priv.h"
> >
> >   /* Total number of ports combined across all struct ib_devices's */
> > -#define RDMA_MAX_PORTS 1024
> > +#define RDMA_MAX_PORTS 8192
> >
> >   struct pkey_index_qp_list {
> >   	struct list_head    pkey_index_list;
> > --
> > 2.14.4
> >
>
> You do explain why you limit it to 8192, but why do you need to go beyond
> 1024 in the first place? Adding that detail would strengthen the commit
> message I think.

I thought that "IDA adds overhead to store IDs bitmap" sentence explains it.
Can you suggest me what to write in order to make it more clear?

Thanks

>
> -Denny

Attachment: signature.asc
Description: PGP signature


[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Photo]     [Yosemite News]     [Yosemite Photos]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux