Date:	Mon, 17 Dec 2012 21:44:40 +0000
From:	"Vick, Matthew" <matthew.vick@...el.com>
To:	Ulf samuelsson <netdev@...gii.com>
CC:	"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: RE: Launch Time Support

> -----Original Message-----
> From: Ulf samuelsson [mailto:netdev@...gii.com]
> Sent: Friday, December 14, 2012 11:35 PM
> To: Vick, Matthew
> Cc: netdev@...r.kernel.org
> Subject: Re: Launch Time Support
> 
> 
> 15 dec 2012 kl. 01:45 skrev "Vick, Matthew" <matthew.vick@...el.com>:
> 
> >> -----Original Message-----
> >> From: netdev-owner@...r.kernel.org [mailto:netdev-
> >> owner@...r.kernel.org] On Behalf Of Ulf Samuelsson
> >> Sent: Wednesday, December 12, 2012 5:04 PM
> >> To: netdev@...r.kernel.org
> >> Subject: RFC: Launch Time Support
> >>
> >> Hi, I am looking for some feedback on how to implement launchtime in
> >> the kernel.
> >>
> >> I.E: You define WHEN you want to send a packet, and the driver will
> >> store the packet in a buffer and will send it out on the net when
> the
> >> internal timestamp counter in the network controller reaches the
> >> specified "launch time".
> >>
> >> Some Ethernet controllers like the new Intel i210 support "launch
> >> time",
> >>
> >> Support for launch time is desirable for any isochronous connection,
> >> but I am currently interested in the NTP protocol to improve the
> >> timing.
> >>
> >> Proposed Changes to the Kernel
> >> ===========================================================
> >> The launchtime support will be dependent on CONFIG_NET_LAUNCHTIME If
> >> this is not set, then the kernel functionality is not changed.
> >>
> >> My current idea is to add a new bit to the "flags" field of
> >> "socket.c:sendto"
> >> #define MSG_LAUNCHTIME 0x?????
> >>
> >> struct msghdr gets an additional launchtime field.
> >>
> >> sendto will check if the flags parameter contains MSG_LAUNCHTIME.
> >> If it does, then the first 64 bit longword of the packet (buff)
> >> contains the launchtime.
> >> The launchtime from the buffer is copied to the msghdr.launchtime
> >> field, and the first 64 bits of the packet is then shaved off,
> before
> >> the address is written to the msghdr.
> >>
> >> Each network controller supporting launchtime needs to have an
> >> alternative call to "send packet with launchtime" . This call adds
> >> the launchtime parameter.
> >> If launchtime is supported the exported "ops" includes the new call.
> >>
> >> The UDP/IP packet send will check the MSG_LAUNCHTIME and if set, it
> >> will check if the "send packet with launchtime" call is available
> for
> >> the driver and if so call it, otherwise it will call the normal send
> >> packet and thus ignore the launchtime.
> >>
> >> Before launchtime is used, the application should send an ioctl to
> >> the driver, making sure that launchtime is configured, and only if
> >> the driver ACKs , the application will use launchtime.
> >>
> >> (Possibly the "ops" field for "send packet with launchtime" should
> be
> >> NULL until that ioctl is complete. Comments?)
> >>
> >> To me, this seems to be transparent for all other network stacks so
> >> protocols and drivers not supporting launchtime should still work.
> >>
> >> As far as I know, drivers do not support launch time today.
> >> The Intel igb driver does not in the latest version on the intel web
> >> site, There are some defines headers in the latest version  defining
> >> the registers but so far, the code is not using it.
> >>
> >> There is the linux_igb_avb project on sourceforge which  allows use
> >> of launch time for user space applications, but not as part of the
> kernel.
> >>
> >> Maybe there is more work done somewhere else, but i am not aware of
> >> this, so any links to such work is appreciated.
> >>
> >> There are some FPGA based PCIe boards that support launchtime
> (Endace
> >> DAG) using proprietary APIs.
> >> Talked to some vendors providing TCP/IP offload engines for FPGA and
> >> they do not support launchtime and liuke Endace use proprietary APIs
> >> so they are only useable by custom programs. Normal networking
> >> interfaces are not supported.
> >>
> >> Comment on above is appreciated.
> >>
> >> BACKGROUND
> >> For those that do not know how the NTP protocol works:
> >> ===================================================
> >> The client sends an UDP packet to the NTP server using port 123 The
> >> NTP client reads the current systime and puts that in the outgoing
> packet.
> >> There is a delay between the time the systime is read, and the time
> >> the packet actually leaves the Ethernet controller adding jitter to
> >> the NTP algorithm.
> >>
> >> When the server receives the packet, it can be timestamped in H/W
> and
> >> a CMSG is then created by the network stack containing that
> timestamp
> >> for use by the server NTP daemon.
> >>
> >> The server generates a reply, which needs to include the client
> >> transmit time, the servers receive time, and the servers transmit
> time.
> >> Again, the transmit time needs to be written into the NTP packet,
> and
> >> then it needs to be processed through the network stack before it is
> >> leaving the ethernet controller causing more jitter.
> >>
> >> If launch time is supported, then the client NTP daemon would simply
> >> read the systime, add a constant delay to create the transmit
> >> timestamp.
> >> The delay needs to be sufficiently large to ensure that all
> >> processing is done,
> >>
> >> The server will do something similar adding a constant to the server
> >> receive timestamp to create the server transmit timestamp.
> >> If both the client and the server uses H/W timestamping and launch
> >> time, then the the jitter ideally is reduced to zero.
> >>
> >> TRANSMIT TIMESTAMPING
> >> ========================
> >> Support for TX timestamps in H/W is not really useful, since you
> need
> >> to provide the TX timestamp in the packet you measure on, so when
> you
> >> know the timestamp it is too late. Server to server  NTP connections
> >> support sending that timestamp in a new packet, but there is no such
> >> support in client server communication.
> >>
> >> The i210 supports putting the timestamp inside the packet as it
> >> leaves the Ethernet controller, but that means that you screw up the
> >> UDP checksum, so the packet will be rejected by the receiving NTP
> daemon.
> >> In addition, the i210 timestamp measures seconds and nanoseconds
> >> which is incompatible with the NTP timestamp which uses seconds and
> a
> >> 32 bit fraction of a second so that does not work either.
> >>
> >> Best Regards
> >> Ulf Samuelsson
> >> eMagii.
> >
> > Ulf,
> >
> > I have been looking into adding launch time support as part of
> enabling some of the I210 functionality you have described (such as in
> linux_igb_avb on SourceForge) upstream--less focused on NTP and more
> focused on AVB, but launch time will be necessary for both. If you
> would like, please feel free to contact me and I would love to work
> with you on this.
> >
> > Reading your proposal, I'm a little confused by which systime you're
> referring to. Do you mean on the host or on the NIC? In the case of
> hardware timestamping today, in igb we set the SYSTIM registers to the
> current system time, but that doesn't mean that the host clock and the
> NIC clock stay synced. You would either need a mechanism such as PPS
> (which igb does not implement today) to sync the host clock to the NIC
> clock or have the NTP daemon account for the discrepancy. Off the top
> of my head, I want to say modern PTP daemons (such as ptp4l) account
> for the discrepancy in the daemon.
> >
> > Cheers,
> > Matthew
> 
> We live in luxury, having access to a Cesium Clock ;-) and we define
> the time, beeing a top-level (Stratum 1) server.
> 
> There are some I/Os on the i210 that can be used to interface to the
> PPS.
> 
> As for reading systime, it is done indirectly as you get the systime as
> part of the NTP incoming packet. (It is timestamped at reception) and
> add the constant to that value.
> 
> Best Regards
> Ulf Samuelsson

So your proposal is to use a PPS interface (from some Stratum 1 server) to drive the clock on an I210 so you can use the I210's launch time mechanism to send packets at a certain time--is this correct? Or are you talking more about a software launch time solution?

Forgive my ignorance, but what constant are you referring to in the receive path? Based on your first e-mail, you mention the constant should be added to the transmit path.

Also, how will you account for hardware discrepancies? For example, how far in the future you can schedule a packet will differ from hardware to hardware.

Cheers,
Matthew
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists