lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date:	Mon, 17 Dec 2012 23:57:40 +0100
From:	Ulf samuelsson <netdev@...gii.com>
To:	"Vick, Matthew" <matthew.vick@...el.com>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: Launch Time Support



17 dec 2012 kl. 22:44 skrev "Vick, Matthew" <matthew.vick@...el.com>:

>> -----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?

There are 4 I/O pins, and you can capture the timestamp when they change value.
This can be used to calibrate the timestamp vs the 1 PPS clock.
It is far from ideal, but it might just work.

If you can clock the part from a 5 MHz clock from the Cesium clock, that would be even better.




> 
> 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.

It is an arbitrary time constant you select in the range of 10s of milliseconds.
The only requirement is that the time from receiving the incoming packet,
to the time when the reply leaves the machine is always shorter than the time constant.
We have seen that this has been implemented on a 10 GbE FPGA card using 50 ms.
There is no requirement for short latency in NTP, only predictable latency.

> 
> 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.

We don't have the problem, since it is for internal use, and we will use the same H/W
In all nodes.  Possibly you want to be able to query the driver for your use.


Best Regards
Ulf Samuelsson
ulf@...gii.com


> 
> 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
--
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