2011-08-18 00:37:32

by Peter Hurley

Subject: [RFC v2 2/5] Bluetooth: Minor optimization for multiple tx connections
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2011-08-18 07:49:48

by Luiz Augusto von Dentz

Subject: Re: [RFC v2 2/5] Bluetooth: Minor optimization for multiple tx connections

Hi Peter,

On Thu, Aug 18, 2011 at 3:37 AM, Peter Hurley <[email protected]> wrote:
> When assigning tx quotas for multiple connections, bump fractional
> amounts to the next higher integer. This can reduce the number of
> iterations through the tx scheduler. For example, if 5 avail acl
> buffers are to be used by 3 transmitting connections, the current
> scheduler will produce quotas of 1, 1, 1, 1, 1. This
> optimization will instead produce quotas of 2, 2, 1 (ie., 2 less
> iterations of the tx scheduler).
>
> Signed-off-by: Peter Hurley <[email protected]>
> ---
> ?net/bluetooth/hci_core.c | ? ?5 ++---
> ?1 files changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
> index 47a31fa..0defa83 100644
> --- a/net/bluetooth/hci_core.c
> +++ b/net/bluetooth/hci_core.c
> @@ -1826,7 +1826,7 @@ static inline struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int
> ? ? ? ?}
>
> ? ? ? ?if (conn) {
> - ? ? ? ? ? ? ? int cnt, q;
> + ? ? ? ? ? ? ? int cnt;
>
> ? ? ? ? ? ? ? ?switch (conn->type) {
> ? ? ? ? ? ? ? ?case ACL_LINK:
> @@ -1844,8 +1844,7 @@ static inline struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int
> ? ? ? ? ? ? ? ? ? ? ? ?BT_ERR("Unknown link type");
> ? ? ? ? ? ? ? ?}
>
> - ? ? ? ? ? ? ? q = cnt / num;
> - ? ? ? ? ? ? ? *quote = q ? q : 1;
> + ? ? ? ? ? ? ? *quote = (cnt + (num - 1)) / num;
> ? ? ? ?} else
> ? ? ? ? ? ? ? ?*quote = 0;
>
> --
> 1.7.4.1
>

Nice catch, actually after seeing your patch I realize one of my
patches is wrong in assuming an HCI Channel can only be scheduled once
per tx_task, but I guess with your changes we can probably assume so,
right?


--
Luiz Augusto von Dentz