All of lore.kernel.org
 help / color / mirror / Atom feed
From: Gerd Hoffmann <kraxel@redhat.com>
To: David Ahern <daahern@cisco.com>
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH 18/18] usb: add ehci adapter
Date: Tue, 17 May 2011 17:02:34 +0200	[thread overview]
Message-ID: <4DD28E0A.2050808@redhat.com> (raw)
In-Reply-To: <4DD27D9D.1050109@cisco.com>

   Hi,

> (And by the way, where are the focused patches for each, especially the
> last one - nuking the 8kHz code?

It's squashed in, like everything else.

> We know that it worked on linux and
> that printers, scanners and storage devices worked ok (mostly).

8 kHz is insane.

I looked closely while trying to make 8 kHz a runtime option instead of 
a compile time option, then decided to drop it altogether as it is 
totally pointless.  qemu simply can't handle that wakeup rate.  It maxed 
out at ~3 kHz wakeups in my tests.  And it burns tons of CPU time.

I also don't see what it would buy us.  We can wakeup with 1 kHz rate 
(maybe even lower), then emulate 8 (or more) microframes each time.

Throughput issues (guess this is the reason to try 8kHz wakeups) need to 
be addressed by modeling data pipes in the usb system instead of playing 
ping-pong between EHCI and USB device emulation for each single usb 
packet, at 8 kHz.

I see the ehci merge just as very first step.  USB 2.0 (and 3.0) support 
in qemu still has a loooooooong way to go.

cheers,
   Gerd

  reply	other threads:[~2011-05-17 15:02 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-16 19:56 [Qemu-devel] [PATCH 00/18] usb patch queue: add usb 2.0 Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 01/18] usb: Add Interface Association Descriptor descriptor type Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 02/18] usb: update config descriptors to identify number of interfaces Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 03/18] usb: remove fallback to bNumInterfaces if no .nif Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 04/18] usb: add support for "grouped" interfaces and the Interface Association Descriptor Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 05/18] Bug #757654: UHCI fails to signal stall response patch Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 06/18] usb: Pass the packet to the device's handle_control callback Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 07/18] usb-linux: use usb_generic_handle_packet() Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 08/18] usb-linux: fix device path aka physical port handling Gerd Hoffmann
2011-05-17 16:38   ` Markus Armbruster
2011-05-16 19:56 ` [Qemu-devel] [PATCH 09/18] usb-linux: add hostport property Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 10/18] usb-linux: track aurbs in list Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 11/18] usb-linux: walk async urb list in cancel Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 12/18] usb-linux: split large xfers Gerd Hoffmann
2011-05-17  2:45   ` David Ahern
2011-05-17  7:10     ` Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 13/18] usb-linux: fix max_packet_size for highspeed Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 14/18] usb: add usb_handle_packet Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 15/18] usb: keep track of packet owner Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 16/18] usb: move cancel callback to USBDeviceInfo Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 17/18] usb-storage: don't call usb_packet_complete twice Gerd Hoffmann
2011-05-16 19:56 ` [Qemu-devel] [PATCH 18/18] usb: add ehci adapter Gerd Hoffmann
2011-05-17  2:47   ` David Ahern
2011-05-17  7:20     ` Gerd Hoffmann
2011-05-17 12:42       ` David Ahern
2011-05-17 13:46         ` Gerd Hoffmann
2011-05-17 14:19           ` David Ahern
2011-05-17 14:36             ` Gerd Hoffmann
2011-05-17 17:15             ` Erik Rull
2011-05-17 13:52         ` David Ahern
2011-05-17 15:02           ` Gerd Hoffmann [this message]
2011-05-17 17:05             ` David Ahern
2011-05-17 17:36               ` Hans de Goede
2011-05-17 17:43                 ` [Qemu-devel] USB streaming [Re: [PATCH 18/18] usb: add ehci adapter] David Ahern
2011-05-17 18:44                   ` Hans de Goede
2011-05-17 19:10                     ` David Ahern
2011-05-17 19:18                       ` David Ahern
2011-05-18  8:25                         ` Hans de Goede
2011-05-17 17:33             ` [Qemu-devel] [PATCH 18/18] usb: add ehci adapter Hans de Goede
2011-05-17 17:00       ` David Ahern
2011-05-17 20:39     ` Blue Swirl
2011-05-17 20:51       ` David Ahern
2011-05-21 10:34       ` Andreas Färber
2011-05-16 20:04 ` [Qemu-devel] [PATCH 00/18] usb patch queue: add usb 2.0 Anthony Liguori
2011-05-17  7:36   ` Gerd Hoffmann
  -- strict thread matches above, loose matches on Subject: below --
2011-05-23  9:43 [Qemu-devel] [PULL] usb patch queue: initial usb 2.0 support Gerd Hoffmann
2011-05-23  9:43 ` [Qemu-devel] [PATCH 18/18] usb: add ehci adapter Gerd Hoffmann
2011-05-23 19:25   ` Blue Swirl
2011-05-24 15:45   ` Erik Rull

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4DD28E0A.2050808@redhat.com \
    --to=kraxel@redhat.com \
    --cc=daahern@cisco.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.