Re: relayd patch for websocket upgrade

2021-10-19 Thread Jonathon Fletcher
On Sun, May 02, 2021 at 11:05:16AM -0700, Jonathon Fletcher wrote: > On Sun, Mar 07, 2021 at 06:22:04PM -0800, Jonathon Fletcher wrote: > > On Sun, Mar 07, 2021 at 06:46:33PM +0100, Marcus MERIGHI wrote: > > > Hello Jonathon! > > > > > > welcome to t

Re: relayd patch for websocket upgrade

2021-05-02 Thread Jonathon Fletcher
On Sun, Mar 07, 2021 at 06:22:04PM -0800, Jonathon Fletcher wrote: > On Sun, Mar 07, 2021 at 06:46:33PM +0100, Marcus MERIGHI wrote: > > Hello Jonathon! > > > > welcome to the party: > > > > https://marc.info/?t=15833439123 > > &

Re: relayd patch for websocket upgrade

2021-03-07 Thread Jonathon Fletcher
; https://marc.info/?m=16135019371 > > reyk@ removed from CC: on purpose: > https://twitter.com/reykfloeter/status/1284868070901776384 > > Marcus > > jonathon.fletc...@gmail.com (Jonathon Fletcher), 2021.03.06 (Sat) 21:02 (CET): > > When relayd relays a conn

relayd patch for websocket upgrade

2021-03-06 Thread Jonathon Fletcher
When relayd relays a connection upgrade to a websocket, it relays the outbound "Connection: Upgrade" header from the interal server. It also tags on a "Connection: close" header to the outbound response - ie the response goes out with two "Connection" header lines. Chrome and Netscape work

Re: xhci zero length transfers 'leak' one transfer buffer count

2020-10-11 Thread Jonathon Fletcher
On Sun, Oct 11, 2020 at 12:14:22PM +0200, Patrick Wildt wrote: > On Sun, Oct 11, 2020 at 08:12:29AM +0200, Martin Pieuchot wrote: > > On 09/10/20(Fri) 12:37, Jonathon Fletcher wrote: > > > In xhci_xfer_get_trb, the count of transfer buffers in the pipe > > > (xp->fr

xhci zero length transfers 'leak' one transfer buffer count

2020-10-09 Thread Jonathon Fletcher
In xhci_xfer_get_trb, the count of transfer buffers in the pipe (xp->free_trbs) is always decremented but the count of transfer buffers used in the transfer (xx->ntrb) is not incremented for zero-length transfers. The result of this is that, at the end of a zero length transfer, xp->free_trbs

Re: Improve ure(4) performance

2020-08-03 Thread Jonathon Fletcher
On Thu, Jul 30, 2020 at 06:56:48PM +, Mikolaj Kucharski wrote: > On Thu, Jul 30, 2020 at 07:58:23AM -0700, Jonathon Fletcher wrote: > > > > Mikolaj, > > > > I hope the patch has been stable for you. I do have an update - it appears > > that a splx(s) got

Re: Improve ure(4) performance

2020-07-30 Thread Jonathon Fletcher
On Mon, Jul 27, 2020 at 07:13:33PM +, Mikolaj Kucharski wrote: > On Mon, Jul 27, 2020 at 11:58:02AM -0700, Jonathon Fletcher wrote: > > > > Are you ok using patch's -l option for this patch? > > > > Sure, can do. New kernel compiled, will switch my machine tonig

Re: Improve ure(4) performance

2020-07-27 Thread Jonathon Fletcher
On Mon, Jul 27, 2020 at 07:13:33PM +, Mikolaj Kucharski wrote: > On Mon, Jul 27, 2020 at 11:58:02AM -0700, Jonathon Fletcher wrote: > > > > Are you ok using patch's -l option for this patch? > > Sure, can do. New kernel compiled, will switch my machine tonight. Will >

Re: Improve ure(4) performance

2020-07-27 Thread Jonathon Fletcher
> On Jul 27, 2020, at 11:47 AM, Mikolaj Kucharski > wrote: > > On Mon, Jul 27, 2020 at 11:24:55AM -0700, Jonathon Fletcher wrote: >> >> I have attached an updated patch - which includes Kevin's changes from >> his earlier email - that also corrects t

Re: Improve ure(4) performance

2020-07-27 Thread Jonathon Fletcher
On Sun, Jul 26, 2020 at 10:12 PM Mikolaj Kucharski wrote: > > On Sun, Jul 26, 2020 at 06:47:32PM -0700, Jonathon Fletcher wrote: > > Mikolaj, > > > > Thank you for testing my patch. > > > > I am very interested to know what xhci (or ehci) hardware yo

Re: Improve ure(4) performance

2020-07-26 Thread Jonathon Fletcher
> On Jul 26, 2020, at 1:24 PM, Mikolaj Kucharski wrote: > > Hi Kevin, Jonathon, > > On Tue, Jul 21, 2020 at 02:38:55PM +0800, Kevin Lo wrote: >> Hi, >> >> Jonathon Fletcher has been helping get the better performance out of ure(4). >> I ran the tc