Author: andre
Date: Fri Feb 1 14:16:37 2013
New Revision: 246207
URL: http://svnweb.freebsd.org/changeset/base/246207
Log:
Remove unused VM_MAX_AUTOTUNE_NMBCLUSTERS define.
Modified:
head/sys/i386/include/vmparam.h
Modified: head/sys/i386/include/vmparam.h
Author: andre
Date: Fri Feb 1 14:21:09 2013
New Revision: 246208
URL: http://svnweb.freebsd.org/changeset/base/246208
Log:
uma_zone_set_max() directly returns the rounded effective zone
limit. Use the return value directly instead of doing a second
uma_zone_set_max() step.
MFC after:
On 01.02.2013 18:52, Alan Cox wrote:
On 02/01/2013 04:26, Andre Oppermann wrote:
Author: andre
Date: Fri Feb 1 10:26:31 2013
New Revision: 246204
URL: http://svnweb.freebsd.org/changeset/base/246204
Log:
Add VM_KMEM_SIZE_SCALE parameter set to 2 (50%) for all ARM platforms
On 01.02.2013 21:23, Adrian Chadd wrote:
.. before you make that assumption, please re-visit some the ..
lower-end integrated ethernet MACs in embedded chips.
I don't know whether the Atheros stuff does (I think it does, but I
don't know under what conditions it's possible.)
Maybe have it by
On 01.02.2013 22:16, Juli Mallett wrote:
On Fri, Feb 1, 2013 at 1:01 PM, Andre Oppermann an...@freebsd.org wrote:
On 01.02.2013 21:23, Adrian Chadd wrote:
.. before you make that assumption, please re-visit some the ..
lower-end integrated ethernet MACs in embedded chips.
I don't know
Author: andre
Date: Fri Mar 8 10:14:58 2013
New Revision: 248031
URL: http://svnweb.freebsd.org/changeset/base/248031
Log:
Move the auto-sizing of the callout array from init_param2() to
kern_timeout_callwheel_alloc() where it is actually used.
This is a mechanical move and no tuning
Author: andre
Date: Fri Mar 8 10:37:17 2013
New Revision: 248032
URL: http://svnweb.freebsd.org/changeset/base/248032
Log:
Move the callout subsystem initialization to its own SYSINIT()
from being indirectly called via cpu_startup()+vm_ksubmap_init().
The boot order position remains the
On 09.03.2013 21:03, Davide Italiano wrote:
Author: davide
Date: Sat Mar 9 20:03:10 2013
New Revision: 248113
URL: http://svnweb.freebsd.org/changeset/base/248113
Log:
Fixup r248032:
Change size requested to malloc(9) now that callwheel buckets are
callout_list and not callout_tailq
Author: andre
Date: Sun Mar 10 22:55:35 2013
New Revision: 248141
URL: http://svnweb.freebsd.org/changeset/base/248141
Log:
Bring back the comment on the sizing of the callout array that got
lost in r248031.
Requested by: alc, alfred
Modified:
head/sys/kern/kern_timeout.c
Modified:
On 08.03.2013 19:17, Alan Cox wrote:
On 03/08/2013 04:14, Andre Oppermann wrote:
Author: andre
Date: Fri Mar 8 10:14:58 2013
New Revision: 248031
URL: http://svnweb.freebsd.org/changeset/base/248031
Log:
Move the auto-sizing of the callout array from init_param2
On 12.03.2013 13:19, Gleb Smirnoff wrote:
Author: glebius
Date: Tue Mar 12 12:19:23 2013
New Revision: 248196
URL: http://svnweb.freebsd.org/changeset/base/248196
Log:
Use m_get2() to get mbuf of appropriate size.
The problem with m_get2() is that it will attempt to use jumbo mbufs
larger
On 12.03.2013 20:49, Gleb Smirnoff wrote:
Andre,
On Tue, Mar 12, 2013 at 05:33:04PM +0100, Andre Oppermann wrote:
A We have very common case when we allocate either mbuf or mbuf + cluster,
A depending on size. Everywhere this is made by hand, but can be substituted
A with m_get2(len
On 13.03.2013 16:18, Gleb Smirnoff wrote:
Okay,
I will redo my patch to make default not to allow PAGE_SIZE
clusters.
Thanks.
On Tue, Mar 12, 2013 at 10:19:05PM +0100, Andre Oppermann wrote:
A Jumbos always were physically contiguous. That was the very reason for
A their existence
On 15.03.2013 13:53, Gleb Smirnoff wrote:
Author: glebius
Date: Fri Mar 15 12:53:53 2013
New Revision: 248323
URL: http://svnweb.freebsd.org/changeset/base/248323
Log:
- Use m_getcl() instead of hand allocating.
Sponsored by:Nginx, Inc.
Modified:
head/sys/netinet/tcp_output.c
On 15.03.2013 14:46, Gleb Smirnoff wrote:
On Fri, Mar 15, 2013 at 02:00:57PM +0100, Andre Oppermann wrote:
A On 15.03.2013 13:53, Gleb Smirnoff wrote:
A Author: glebius
A Date: Fri Mar 15 12:53:53 2013
A New Revision: 248323
A URL: http://svnweb.freebsd.org/changeset/base/248323
A
A Log
On 17.03.2013 10:33, Gleb Smirnoff wrote:
On Sun, Mar 17, 2013 at 10:02:09AM +0100, Andre Oppermann wrote:
A On 17.03.2013 08:39, Gleb Smirnoff wrote:
A Author: glebius
A Date: Sun Mar 17 07:39:45 2013
A New Revision: 248417
A URL: http://svnweb.freebsd.org/changeset/base/248417
A
A Log
Author: andre
Date: Tue Apr 9 20:52:26 2013
New Revision: 249317
URL: http://svnweb.freebsd.org/changeset/base/249317
Log:
Fix a race condition on tcp listen socket teardown with pending
connections in the accept queue and contiguous new incoming SYNs.
Compared to the original
Author: andre
Date: Tue Apr 9 21:02:20 2013
New Revision: 249318
URL: http://svnweb.freebsd.org/changeset/base/249318
Log:
Change certain heavily used network related mutexes and rwlocks to
reside on their own cache line to prevent false sharing with other
nearby structures, especially for
Author: andre
Date: Mon Nov 5 09:13:06 2012
New Revision: 242601
URL: http://svnweb.freebsd.org/changeset/base/242601
Log:
Back out r242262. The simplified window change/update logic wasn't
complete and ready for production use.
PR: kern/173309
Modified:
On 08.11.2012 08:46, Peter Wemm wrote:
On Wed, Nov 7, 2012 at 10:24 PM, Alfred Perlstein bri...@mu.org wrote:
[[ + peter ]]
Folks, I spent quite a bit of time trying to figure out how to resolve
maxusers scaling in a happy way for all.
I think I came up with a solution.
This solution should
On 10.11.2012 19:04, Peter Wemm wrote:
On Sat, Nov 10, 2012 at 9:48 AM, Eitan Adler ead...@freebsd.org wrote:
On 10 November 2012 12:45, Peter Wemm pe...@wemm.org wrote:
On Sat, Nov 10, 2012 at 9:33 AM, Eitan Adler ead...@freebsd.org wrote:
On 10 November 2012 12:04, Alfred Perlstein
On 10.11.2012 23:24, Alfred Perlstein wrote:
On 11/10/12 11:18 AM, Andre Oppermann wrote:
On 10.11.2012 19:04, Peter Wemm wrote:
This is complicated but we need a simple user visible view of it. It
really needs to be something like nmbclusters defaults to 6% of
physical ram, with machine
On 13.11.2012 03:50, Alan Cox wrote:
Author: alc
Date: Tue Nov 13 02:50:39 2012
New Revision: 242941
URL: http://svnweb.freebsd.org/changeset/base/242941
Log:
Replace the single, global page queues lock with per-queue locks on the
active and inactive paging queues.
Hear hear! Now if
On 13.11.2012 10:17, Gleb Smirnoff wrote:
On Mon, Nov 12, 2012 at 06:11:40PM -0800, David O'Brien wrote:
D On Fri, Sep 14, 2012 at 11:51:51AM +, Gleb Smirnoff wrote:
D Log:
Do Create directory sys/netpfil, where all packet filters should
D reside, and move there ipfw(4) and pf(4).
On 14.11.2012 09:05, Gleb Smirnoff wrote:
Author: glebius
Date: Wed Nov 14 08:05:21 2012
New Revision: 243019
URL: http://svnweb.freebsd.org/changeset/base/243019
Log:
Remove remnants of classful addressing. These magic transformations
of supplied arguments is not what a modern sysadmin
On 18.11.2012 15:05, Andrey Zonov wrote:
On 11/11/12 3:04 AM, Andre Oppermann wrote:
On 10.11.2012 23:24, Alfred Perlstein wrote:
On 11/10/12 11:18 AM, Andre Oppermann wrote:
On 10.11.2012 19:04, Peter Wemm wrote:
This is complicated but we need a simple user visible view of it. It
really
Author: andre
Date: Tue Nov 27 19:31:49 2012
New Revision: 243624
URL: http://svnweb.freebsd.org/changeset/base/243624
Log:
Remove unused and unnecessary CSUM_IP_FRAGS checksumming capability.
Checksumming the IP header of fragments is no different from doing
normal IP headers.
Author: andre
Date: Tue Nov 27 20:04:52 2012
New Revision: 243627
URL: http://svnweb.freebsd.org/changeset/base/243627
Log:
Fix a race on listen socket teardown where while draining the
accept queues a new socket/connection may be added to the queue
due to a race on the ACCEPT_LOCK.
Author: andre
Date: Tue Nov 27 20:16:01 2012
New Revision: 243628
URL: http://svnweb.freebsd.org/changeset/base/243628
Log:
Update comment to prefer M_NOWAIT over M_DONTWAIT and
M_WAITOK over M_WAIT.
MFC after:1 week
Modified:
head/sys/sys/mbuf.h
Modified: head/sys/sys/mbuf.h
Author: andre
Date: Tue Nov 27 21:19:58 2012
New Revision: 243631
URL: http://svnweb.freebsd.org/changeset/base/243631
Log:
Base the mbuf related limits on the available physical memory or
kernel memory, whichever is lower. The overall mbuf related memory
limit must be set so that mbufs
Author: andre
Date: Tue Nov 27 22:35:48 2012
New Revision: 243638
URL: http://svnweb.freebsd.org/changeset/base/243638
Log:
Fix r243627 by testing against the head socket instead of the socket
just created.
MFC after:1 week
X-MFC-with: r243627
Modified:
at 12:04 PM, Andre Oppermann an...@freebsd.org wrote:
Author: andre
Date: Tue Nov 27 20:04:52 2012
New Revision: 243627
URL: http://svnweb.freebsd.org/changeset/base/243627
Log:
Fix a race on listen socket teardown where while draining the
accept queues a new socket/connection may be added
Author: andre
Date: Tue Nov 27 23:16:56 2012
New Revision: 243639
URL: http://svnweb.freebsd.org/changeset/base/243639
Log:
Complete r243631 by applying the remainder of kern_mbuf.c that got
lost while merging into the commit tree.
MFC after:1 month
X-MFC-with: r243631
Modified:
On 28.11.2012 00:16, Andre Oppermann wrote:
Author: andre
Date: Tue Nov 27 23:16:56 2012
New Revision: 243639
URL: http://svnweb.freebsd.org/changeset/base/243639
Log:
Complete r243631 by applying the remainder of kern_mbuf.c that got
lost while merging into the commit tree.
Please note
On 28.11.2012 00:05, Robert N. M. Watson wrote:
On 27 Nov 2012, at 22:54, Andre Oppermann wrote:
Andre.. this breaks incoming connections. TCP is immediately reset and never
even gets to the
listener process. You need to back out of fix this urgently please.
I just found out and fixed
On 28.11.2012 18:37, Alan Cox wrote:
I'm pretty sure that the realmem calculation is going to overflow on
i386/PAE, where the number of bytes of physical memory is greater than
the type long can represent.
Right. long == int on i386/PAE, not LP64. Is uint64_t the correct type
to use to catch
On 28.11.2012 22:45, Bruce Evans wrote:
On Wed, 28 Nov 2012, Alan Cox wrote:
I'm pretty sure that the realmem calculation is going to overflow on
i386/PAE, where the number of bytes of physical memory is greater than
the type long can represent.
It overflows on i386 even without PAE, where
On 29.11.2012 00:14, Bruce Evans wrote:
On Wed, 28 Nov 2012, Andre Oppermann wrote:
On 28.11.2012 18:37, Alan Cox wrote:
I'm pretty sure that the realmem calculation is going to overflow on
i386/PAE, where the number of bytes of physical memory is greater than
the type long can represent
On 29.11.2012 01:35, Vijay Singh wrote:
a sign of poor prior testing and too much trust into the submitter of
the patch it wasn't an earth shattering event. Doesn't distract from
Andre, I am really quite disappointed to read this from you. The patch
I sent you was fine, and has been well
Author: andre
Date: Thu Nov 29 07:30:42 2012
New Revision: 243668
URL: http://svnweb.freebsd.org/changeset/base/243668
Log:
Using a long is the wrong type to represent the realmem and maxmbufmem
variable as they may overflow on i386/PAE and i386 with 2GB RAM.
Use 64bit quad_t instead.
On 01.12.2012 10:48, Jack Vogel wrote:
On Sat, Dec 1, 2012 at 12:40 AM, Andre Oppermann an...@freebsd.org
mailto:an...@freebsd.org wrote:
On 30.11.2012 23:19, Jack F Vogel wrote:
Author: jfv
Date: Fri Nov 30 22:19:18 2012
New Revision: 243714
URL: http
On 07.12.2012 10:36, Oleksandr Tymoshenko wrote:
On 2012-11-27, at 1:19 PM, Andre Oppermann an...@freebsd.org wrote:
Author: andre
Date: Tue Nov 27 21:19:58 2012
New Revision: 243631
URL: http://svnweb.freebsd.org/changeset/base/243631
Log:
Base the mbuf related limits on the available
On 28.11.2012 04:04, Alfred Perlstein wrote:
On 11/27/12 2:12 PM, Andre Oppermann wrote:
On 27.11.2012 04:04, Alfred Perlstein wrote:
Author: alfred
Date: Tue Nov 27 03:04:24 2012
New Revision: 243594
URL: http://svnweb.freebsd.org/changeset/base/243594
Log:
Auto size the tcbhashsize
(7).
Users are unlikely to even find the right place to look for in the
source code.
--
Andre
Sent from my iPhone
On Dec 7, 2012, at 7:06 AM, Andre Oppermann an...@freebsd.org wrote:
On 28.11.2012 04:04, Alfred Perlstein wrote:
On 11/27/12 2:12 PM, Andre Oppermann wrote:
On 27.11.2012 04:04
On 07.12.2012 22:05, Oleksandr Tymoshenko wrote:
On 12/7/2012 1:53 AM, Andre Oppermann wrote:
On 07.12.2012 10:36, Oleksandr Tymoshenko wrote:
On 2012-11-27, at 1:19 PM, Andre Oppermann an...@freebsd.org wrote:
Author: andre
Date: Tue Nov 27 21:19:58 2012
New Revision: 243631
URL: http
On 07.12.2012 23:17, Oleksandr Tymoshenko wrote:
On 12/7/2012 1:44 PM, Andre Oppermann wrote:
On 07.12.2012 22:05, Oleksandr Tymoshenko wrote:
On 12/7/2012 1:53 AM, Andre Oppermann wrote:
On 07.12.2012 10:36, Oleksandr Tymoshenko wrote:
On 2012-11-27, at 1:19 PM, Andre Oppermann
Author: andre
Date: Sat Dec 8 21:03:14 2012
New Revision: 244039
URL: http://svnweb.freebsd.org/changeset/base/244039
Log:
Remove outdated reference to tcp inflight limiting. It was removed
a long time ago.
MFC after:1 week
Modified:
head/share/man/man7/tuning.7
Modified:
On 08.12.2012 22:26, Eitan Adler wrote:
On 8 December 2012 16:03, Andre Oppermann an...@freebsd.org wrote:
Author: andre
Date: Sat Dec 8 21:03:14 2012
New Revision: 244039
URL: http://svnweb.freebsd.org/changeset/base/244039
Log:
Remove outdated reference to tcp inflight limiting
On 09.12.2012 21:35, Alan Cox wrote:
Andre,
I believe that this change did not actually correct the overflow
problem. See below for an explanation.
On 11/29/2012 01:30, Andre Oppermann wrote:
Author: andre
Date: Thu Nov 29 07:30:42 2012
New Revision: 243668
URL: http://svnweb.freebsd.org
Author: andre
Date: Sun Dec 9 22:54:03 2012
New Revision: 244058
URL: http://svnweb.freebsd.org/changeset/base/244058
Log:
Fix bandwidth reporting when doing a restarted download with -r.
The offset is already accounted for in xs-lastrcvd and doesn't
have to be subtracted again.
Author: andre
Date: Mon Dec 10 12:19:03 2012
New Revision: 244080
URL: http://svnweb.freebsd.org/changeset/base/244080
Log:
Prevent long type overflow of realmem calculation on ILP32 by forcing
calculation to be in quad_t space. Fix style issue with second parameter
to qmin().
On 18.12.2012 06:40, Oleksandr Tymoshenko wrote:
On 2012-12-08, at 1:21 PM, Alan Cox a...@rice.edu wrote:
On 12/08/2012 14:32, Andre Oppermann wrote:
.. skipped ..
The trouble seems to come from NSFBUFS which is (512 + maxusers * 16)
resulting in a kernel map of (512 + 400 * 16
On 18.12.2012 09:24, Gleb Smirnoff wrote:
Andrey,
On Tue, Dec 18, 2012 at 08:14:16AM +, Gleb Smirnoff wrote:
T Author: glebius
T Date: Tue Dec 18 08:14:16 2012
T New Revision: 244387
T URL: http://svnweb.freebsd.org/changeset/base/244387
T
T Log:
T Fix !INET6 build after r244365.
T
T
/2012 14:32, Andre Oppermann wrote:
.. skipped ..
The trouble seems to come from NSFBUFS which is (512 + maxusers *
16)
resulting in a kernel map of (512 + 400 * 16) * PAGE_SIZE =
27MB. This
seem to be pushing it with the smaller ARM kmap layout.
Does it boot and run when you set the tunable
On 13.01.2013 11:10, Alan Cox wrote:
On 01/07/2013 12:47, Oleksandr Tymoshenko wrote:
On 12/27/2012 6:46 PM, Oleksandr Tymoshenko wrote:
On 12/18/2012 1:59 AM, Alan Cox wrote:
On 12/17/2012 23:40, Oleksandr Tymoshenko wrote:
On 2012-12-08, at 1:21 PM, Alan Cox a...@rice.edu wrote:
That
On 13.01.2013 19:06, Alfred Perlstein wrote:
On 1/12/13 10:32 PM, Adrian Chadd wrote:
On 12 January 2013 11:45, Alfred Perlstein bri...@mu.org wrote:
I'm not sure if regressing to the waterfall method of development is a good
idea at this point.
I see a light at the end of the tunnel and we
On 14.01.2013 16:51, Alexander Motin wrote:
On 14.01.2013 17:09, Andre Oppermann wrote:
On 13.01.2013 19:06, Alfred Perlstein wrote:
On 1/12/13 10:32 PM, Adrian Chadd wrote:
On 12 January 2013 11:45, Alfred Perlstein bri...@mu.org wrote:
I'm not sure if regressing to the waterfall method
Author: andre
Date: Thu Jan 17 21:28:31 2013
New Revision: 245575
URL: http://svnweb.freebsd.org/changeset/base/245575
Log:
Move the mbuf memory limit calculations from init_param2() to
tunable_mbinit() where it is next to where it is used later.
Change the sysinit level of
On 14.01.2013 16:00, Andre Oppermann wrote:
On 13.01.2013 11:10, Alan Cox wrote:
3. The function vm_ksubmap_init() has a dependency on the global
variable maxpipekva. vm_ksubmap_init() is executed under SI_SUB_CPU,
which comes after SI_SUB_KMEM.
Am I missing anything?
I'm attaching a patch
201 - 259 of 259 matches
Mail list logo