Robert,
thanks for longer reply!
On Sun, Nov 30, 2014 at 09:33:50PM +, Robert Watson wrote:
R> I do have a substantial worry about 'compatibility' -- which is to say, the
R> risk of not only running into trouble with more obscure bits of the network
R> stack, but also third-party extens
Hi Gleb:
Randall had mentioned these in-flight changes to me, and I can see how these
might substantially reduce latency in usefully filling the TCP pipe when the
window is opening rapidly (among other things). As with others, I'm a bit
cautious about further increases in asynchrony within m
Author: kib
Date: Sun Nov 30 20:20:55 2014
New Revision: 275347
URL: https://svnweb.freebsd.org/changeset/base/275347
Log:
Provide mutual exclusion between zone allocation/destruction and
uma_reclaim(). Reclamation code must not see half-constructed or
destructed zones. Do this by bracing
Author: jilles
Date: Sun Nov 30 20:12:47 2014
New Revision: 275346
URL: https://svnweb.freebsd.org/changeset/base/275346
Log:
sh: Remove special case for '=' in set -x; always quote it in outqstr().
I plan to make set -x output always printable using $'...'; avoiding quoting
words contain
Author: gibbs
Date: Sun Nov 30 19:32:00 2014
New Revision: 275345
URL: https://svnweb.freebsd.org/changeset/base/275345
Log:
Remove trailing whitespace.
Modified:
head/sys/kern/subr_taskqueue.c
Modified: head/sys/kern/subr_taskqueue.c
=
On 11/30/14, 10:38 AM, Gleb Smirnoff wrote:
Adrian & Alfred,
On Sun, Nov 30, 2014 at 09:55:05AM -0800, Adrian Chadd wrote:
A> I really wished that these commits got individual reviews before they went
in.
On Sun, Nov 30, 2014 at 10:10:57AM -0800, Alfred Perlstein wrote:
A> Agree, this was
Adrian,
On Sun, Nov 30, 2014 at 09:55:05AM -0800, Adrian Chadd wrote:
A> The whole idea of an mbuf whose data isn't quite there yet makes
A> debugging issues rather amusing, as now you may have VM issues to
A> debug at the same time as you're debugging network related stuff.
I don't see how VM
Alfred,
On Sun, Nov 30, 2014 at 10:10:57AM -0800, Alfred Perlstein wrote:
A> Splitting this into the mbuf layer adds a huge level of complexity where
A> again, there are already completion paths in the socket layer to do
A> this. I am completely confused as to why this couldn't just be done
Adrian & Alfred,
On Sun, Nov 30, 2014 at 09:55:05AM -0800, Adrian Chadd wrote:
A> I really wished that these commits got individual reviews before they went
in.
On Sun, Nov 30, 2014 at 10:10:57AM -0800, Alfred Perlstein wrote:
A> Agree, this was already discussed as quite possibly an incorrect
Agree, this was already discussed as quite possibly an incorrect way
forward some months ago.
Where is the actual review for this huge change to the networking stack?
Splitting this into the mbuf layer adds a huge level of complexity where
again, there are already completion paths in the socke
Hi,
I really wished that these commits got individual reviews before they went in.
The whole idea of an mbuf whose data isn't quite there yet makes
debugging issues rather amusing, as now you may have VM issues to
debug at the same time as you're debugging network related stuff.
I really think t
Author: andrew
Date: Sun Nov 30 17:29:49 2014
New Revision: 275337
URL: https://svnweb.freebsd.org/changeset/base/275337
Log:
There is no need to use FUNC_END with aeabi_ldiv0 or aeabi_idiv0 as they
are aliases.
Sponsored by: ABT Systems Ltd
Modified:
head/contrib/gcc/config/arm/lib1fu
Author: andrew
Date: Sun Nov 30 17:27:24 2014
New Revision: 275336
URL: https://svnweb.freebsd.org/changeset/base/275336
Log:
Use llabs when getting the absolute value of a long long.
Sponsored by: ABT Ststems Ltd
Modified:
head/contrib/binutils/bfd/elf32-arm.c
Modified: head/contrib/bi
Author: bryanv
Date: Sun Nov 30 16:36:26 2014
New Revision: 275335
URL: https://svnweb.freebsd.org/changeset/base/275335
Log:
Cleanup and performance improvement of the virtio_blk driver
- Add support for GEOM direct completion. Depending on the benchmark,
this tends to give a ~30%
Author: glebius
Date: Sun Nov 30 13:43:52 2014
New Revision: 275333
URL: https://svnweb.freebsd.org/changeset/base/275333
Log:
Merge from projects/sendfile:
- Provide pru_ready function for TCP.
- Don't call tcp_output() from tcp_usr_send() if no ready data was put
into the socket buf
Author: glebius
Date: Sun Nov 30 13:40:58 2014
New Revision: 275332
URL: https://svnweb.freebsd.org/changeset/base/275332
Log:
Merge from projects/sendfile:
Provide pru_ready for AF_LOCAL sockets. Local sockets sendsdata directly
to the receive buffer of the peer, thus pru_ready also wor
Author: hselasky
Date: Sun Nov 30 13:27:58 2014
New Revision: 275330
URL: https://svnweb.freebsd.org/changeset/base/275330
Log:
Fix building of some infiniband utilities by updating some header file
locations and compiler include directives.
MFC after:3 days
Sponsored by: Mellanox T
Author: glebius
Date: Sun Nov 30 13:24:21 2014
New Revision: 275329
URL: https://svnweb.freebsd.org/changeset/base/275329
Log:
Merge from projects/sendfile: extend protocols API to support
sending not ready data:
o Add new flag to pru_send() flags - PRUS_NOTREADY.
o Add new protocol method
Author: hselasky
Date: Sun Nov 30 13:13:46 2014
New Revision: 275328
URL: https://svnweb.freebsd.org/changeset/base/275328
Log:
Add missing libraries when linking.
MFC after:3 days
Sponsored by: Mellanox Technologies
Modified:
head/contrib/ofed/librdmacm/examples/build/cmatose/Make
Author: glebius
Date: Sun Nov 30 12:52:33 2014
New Revision: 275326
URL: https://svnweb.freebsd.org/changeset/base/275326
Log:
Merge from projects/sendfile:
o Introduce a notion of "not ready" mbufs in socket buffers. These
mbufs are now being populated by some I/O in background and are
Author: ngie
Date: Sun Nov 30 12:34:48 2014
New Revision: 275324
URL: https://svnweb.freebsd.org/changeset/base/275324
Log:
Remove duplicate FILESYSTEMS REQUIRE from etc/rc.d/ipmon and etc/rc.d/pflog
Modified:
head/etc/rc.d/ipmon
head/etc/rc.d/pflog
Directory Properties:
head/ (props ch
Author: ngie
Date: Sun Nov 30 12:32:16 2014
New Revision: 275323
URL: https://svnweb.freebsd.org/changeset/base/275323
Log:
Add mergeinfo for r275302
Modified:
Directory Properties:
head/ (props changed)
___
svn-src-head@freebsd.org mailing list
h
Author: andrew
Date: Sun Nov 30 12:25:04 2014
New Revision: 275322
URL: https://svnweb.freebsd.org/changeset/base/275322
Log:
Correctly a few incorrect uses of ENTRY/EENTRY and END/EEND
Sponsored by: ABT Systems Ltd
Modified:
head/sys/arm/arm/fusu.S
head/sys/arm/arm/support.S
Modified
Author: andrew
Date: Sun Nov 30 12:20:24 2014
New Revision: 275321
URL: https://svnweb.freebsd.org/changeset/base/275321
Log:
Remove extra labels, ENTRY_NP already provides them.
Sponsored by: ABT Systems Ltd
Modified:
head/sys/arm/arm/cpufunc_asm_armv5.S
head/sys/arm/arm/cpufunc_asm_x
Author: glebius
Date: Sun Nov 30 12:11:01 2014
New Revision: 275320
URL: https://svnweb.freebsd.org/changeset/base/275320
Log:
Missed in r274421: use sbavail() instead of bare access to sb_cc.
Modified:
head/sys/netinet/tcp_usrreq.c
Modified: head/sys/netinet/tcp_usrreq.c
===
Author: glebius
Date: Sun Nov 30 11:22:39 2014
New Revision: 275315
URL: https://svnweb.freebsd.org/changeset/base/275315
Log:
- Move sbcheck() declaration under SOCKBUF_DEBUG.
- Improve SOCKBUF_DEBUG macros.
- Improve sbcheck().
Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Modifi
Author: glebius
Date: Sun Nov 30 11:02:07 2014
New Revision: 275312
URL: https://svnweb.freebsd.org/changeset/base/275312
Log:
Make sballoc() and sbfree() functions. Ideally, they could be marked
as static, but unfortunately Infiniband (ab)uses them.
Sponsored by: Nginx, Inc.
Modified:
Author: rdivacky
Date: Sun Nov 30 08:43:55 2014
New Revision: 275305
URL: https://svnweb.freebsd.org/changeset/base/275305
Log:
Unbreak the code for non-digits below '0' by casting the expression
to unsigned int.
Pointed out by: bde
Modified:
head/sys/boot/i386/boot2/boot2.c
Modified:
28 matches
Mail list logo
