On Sat, 6 Mar 2010, Daniel Braniss wrote:
it works ok in 7.2, so it would be interesting to compare changes ...
The sys/rpc in FreeBSD8 is completely different code than what is used in
FreeBSD7, so I'm afraid thay're apples vs oranges.
rick
___
On Tue, 2 Mar 2010, Daniel Braniss wrote:
just keep sending insights/pointers and enjoy life
You could try this patch for sys/rpc/replay.c. Completely untested and
just typed into email (so don't give it to patch, just edit the file).
- try adding these 2 lines just before
On Fri, 5 Mar 2010, Daniel Braniss wrote:
On Tue, 2 Mar 2010, Daniel Braniss wrote:
just keep sending insights/pointers and enjoy life
You could try this patch for sys/rpc/replay.c. Completely untested and
just typed into email (so don't give it to patch, just edit the file).
- try
[...]
but it didn't help, it's not triggered
Hmm, well that's the only place I could see in replay.c that could leak
(and it's a pretty straightforward piece of code). This is getting
interesting. Just to confirm where we currently are...
- replay cache disabled -- no leak
- replay
On Thu, 4 Mar 2010, Daniel Braniss wrote:
correct. The interesting side effect, is that I can't see any negative
issues when disabling the cash.
If the client retries a non-idempotent RPC, the server will do it
again, which can result in data corruption. This is likely to happen
On Tue, 2 Mar 2010, Daniel Braniss wrote:
just keep sending insights/pointers and enjoy life
You could try this patch for sys/rpc/replay.c. Completely untested and
just typed into email (so don't give it to patch, just edit the file).
- try adding these 2 lines just before the end of
On Tue, 2 Mar 2010, Daniel Braniss wrote:
just keep sending insights/pointers and enjoy life
You could try this patch for sys/rpc/replay.c. Completely untested and
just typed into email (so don't give it to patch, just edit the file).
- try adding these 2 lines just before
On Tue, 2 Mar 2010, Daniel Braniss wrote:
runing with the experimental nfs server all is ok!
(at least I can't see any mbuf leakage :-)
so now that we can assume that the problem is in NFS/UDP writes via
classic nfsserver, where to look?
It might also be the krpc reply
On Wed, 3 Mar 2010, Daniel Braniss wrote:
disabling the krpc reply cache does it, no visible damage. Somehow
this reminds me of my old 1970 beetle, parts would fall off but it would
continue working :-)
where to go from here?
Ok, so it sounds like the leak is in the krpc reply cache code,
On Wed, 3 Mar 2010, Daniel Braniss wrote:
disabling the krpc reply cache does it, no visible damage. Somehow
this reminds me of my old 1970 beetle, parts would fall off but it would
continue working :-)
where to go from here?
Ok, so it sounds like the leak is in the krpc reply
On Sat, 27 Feb 2010, Jeremy Chadwick wrote:
I concur.
Everything in my network is now on TCP, and there is no mbuf leakage.
I just don't get over the 5500 mark, no matter what I throw at it.
I do feel that TCP is not as well performing on a local net with Linux,
hence the choice
On Tue, 2 Mar 2010, Daniel Braniss wrote:
runing with the experimental nfs server all is ok!
(at least I can't see any mbuf leakage :-)
so now that we can assume that the problem is in NFS/UDP writes via
classic nfsserver, where to look?
It might also be the krpc reply cache, since the
On Sat, 27 Feb 2010, Jeremy Chadwick wrote:
I concur.
Everything in my network is now on TCP, and there is no mbuf leakage.
I just don't get over the 5500 mark, no matter what I throw at it.
I do feel that TCP is not as well performing on a local net with Linux,
hence the choice for UDP. But
On Sat, Feb 27, 2010 at 10:53:00PM +0100, Willem Jan Withagen wrote:
On 27-2-2010 21:32, Eirik Øverby wrote:
I've had a discussion with some folks on this for a while. I can easil=y
reproduce this situation by mounting a FreeBSD ZFS filesystem via
NFS-UDP from an OpenBSD machine. Telling
On Feb 28, 2010, at 12:11 PM, Daniel Braniss wrote:
I'm pulling in Robert Watson, who has some familiarity with the UDP
stack/code in FreeBSD. I'm not sure he'll be a sufficient source of
knowledge for this specific issue since it appears (?) to be specific to
NFS; Rick Macklem would be a
On Feb 28, 2010, at 12:11 PM, Daniel Braniss wrote:
I'm pulling in Robert Watson, who has some familiarity with the UDP
stack/code in FreeBSD. I'm not sure he'll be a sufficient source of
knowledge for this specific issue since it appears (?) to be specific =to
NFS; Rick Macklem would
On Feb 28, 2010, at 2:52 PM, Daniel Braniss wrote:
well, I have further reduced the problem, it happens with NFS/UDP writes.
i'll try the wireshark road, but i'm very rusty with RPC, the other road is to
check the changes, my oldest is from late october (RC2) where it's happening,
while
On Sun, 28 Feb 2010 16:52:44 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/udp (was: mbuf leakage with nfs/zfs):
DB well, I have further reduced the problem, it happens with NFS/UDP
DB writes. i'll try the wireshark road, but i'm very rusty with RPC, the
DB other
On Sat, 27 Feb 2010 09:24:10 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB I doubt it, but here is another shot:
DB are we all running samba? I'm asking because the lock manager keeps
DB dying and ...
Nope, no samba on my side. I am running lockd
On Sat, 27 Feb 2010 09:24:10 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB I doubt it, but here is another shot:
DB are we all running samba? I'm asking because the lock manager keeps
DB dying and ...
Nope, no samba on my side. I am running
On Sat, 27 Feb 2010 11:14:56 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB anyways, I am running tests on an 'unused' server, only me using it to
DB 'make world'
DB and it's leaking.
Hm, I've got a server with 8-PRE from somewhen in Nov09
On Sat, 27 Feb 2010 11:14:56 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB anyways, I am running tests on an 'unused' server, only me using it to
DB 'make world'
DB and it's leaking.
Hm, I've got a server with 8-PRE from somewhen in Nov09
On Sat, 27 Feb 2010 12:26:02 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB Hm, I've got a server with 8-PRE from somewhen in Nov09 that is
DB serving nfs from zfs fine and shows no leakage...
DB the binary search has started!
DB sorry, have to go
On 27-2-2010 8:02, Gerrit Kühn wrote:
On Fri, 26 Feb 2010 23:12:39 +0100 Willem Jan Withagenw...@digiware.nl
wrote about Re: mbuf leakage with nfs/zfs?:
WJW Mine are now:
WJW 41533/2402/43935 mbufs in use (current/cache/total)
WJW 41454/1572/43026/262144 mbuf clusters in use (current/cache
On Sat, 27 Feb 2010 15:15:52 +0100 Willem Jan Withagen w...@digiware.nl
wrote about Re: mbuf leakage with nfs/zfs?:
WJW 81492/2613/84105 mbufs in use (current/cache/total)
WJW 80467/2235/82702/128000 mbuf clusters in use
WJW (current/cache/total/max) 80458/822 mbuf+clusters out of packet
WJW
On Sat, 27 Feb 2010 12:26:02 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB Hm, I've got a server with 8-PRE from somewhen in Nov09 that is
DB serving nfs from zfs fine and shows no leakage...
DB the binary search has started!
After considering
On Sat, 27 Feb 2010 12:26:02 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB Hm, I've got a server with 8-PRE from somewhen in Nov09 that is
DB serving nfs from zfs fine and shows no leakage...
DB the binary search has started!
After
On Sat, Feb 27, 2010 at 08:21:05PM +0100, Gerrit Kühn wrote:
On Sat, 27 Feb 2010 15:15:52 +0100 Willem Jan Withagen w...@digiware.nl
wrote about Re: mbuf leakage with nfs/zfs?:
WJW 81492/2613/84105 mbufs in use (current/cache/total)
WJW 80467/2235/82702/128000 mbuf clusters in use
WJW
On 27. feb. 2010, at 20.38, Jeremy Chadwick wrote:
On Sat, Feb 27, 2010 at 08:21:05PM +0100, Gerrit Kühn wrote:
On Sat, 27 Feb 2010 15:15:52 +0100 Willem Jan Withagen w...@digiware.nl
wrote about Re: mbuf leakage with nfs/zfs?:
WJW 81492/2613/84105 mbufs in use (current/cache/total)
WJW
On Sat, 27 Feb 2010 21:32:39 +0100 Eirik Øverby ltn...@anduin.net wrote
about Re: mbuf leakage with nfs/zfs?:
E I've had a discussion with some folks on this for a while. I can easily
E reproduce this situation by mounting a FreeBSD ZFS filesystem via
E NFS-UDP from an OpenBSD machine. Telling
On Sat, 27 Feb 2010 21:36:47 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? :
DB I have been running for the last few hours, 8-rel, and the only client
DB is another
DB 8-stable, furthermore, no ZFS, just plain UFS, and the leak is there!
Mounted via udp
On 27. feb. 2010, at 22.38, Gerrit Kühn wrote:
On Sat, 27 Feb 2010 21:32:39 +0100 Eirik Øverby ltn...@anduin.net wrote
about Re: mbuf leakage with nfs/zfs?:
E I've had a discussion with some folks on this for a while. I can easily
E reproduce this situation by mounting a FreeBSD ZFS
On Sat, 27 Feb 2010 11:38:19 -0800 Jeremy Chadwick
free...@jdc.parodius.com wrote about Re: mbuf leakage with nfs/zfs?:
JC I should point out that the NFS+ZFS-based filer doesn't actually do its
JC backups using NFS; it uses rsnapshot (rsync) over SSH. There is
JC intense network I/O during
On Sat, 27 Feb 2010 22:40:43 +0100 Eirik Øverby ltn...@anduin.net wrote
about Re: mbuf leakage with nfs/zfs?:
E So we see this problem with udp clients from OpenBSD and Linux.
E I have not had the opportunity to test with Linux or anything else.
I guess all others who reported so far
On 27-2-2010 21:32, Eirik Øverby wrote:
I've had a discussion with some folks on this for a while. I can easily
reproduce this situation by mounting a FreeBSD ZFS filesystem via
NFS-UDP from an OpenBSD machine. Telling the OpenBSD machine to use TCP
instead of UDP makes the problem go away.
On Sat, Feb 27, 2010 at 10:53:00PM +0100, Willem Jan Withagen wrote:
On 27-2-2010 21:32, Eirik Øverby wrote:
I've had a discussion with some folks on this for a while. I can easily
reproduce this situation by mounting a FreeBSD ZFS filesystem via
NFS-UDP from an OpenBSD machine. Telling the
On Fri, 26 Feb 2010 17:41:02 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: em0 freezes on ZFS server :
DB check:
DB ftp://ftp.cs.huji.ac.il/users/danny/freebsd/plot.ps
DB x is seconds, y is mbus current.
Looks not as bad as mine. I had 37k when I rebooted the machine some
minutes
On Fri, 26 Feb 2010 17:41:02 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: em0 freezes on ZFS server :
DB check:
DB ftp://ftp.cs.huji.ac.il/users/danny/freebsd/plot.ps
DB x is seconds, y is mbus current.
Looks not as bad as mine. I had 37k when I rebooted the machine some
On Fri, 26 Feb 2010 22:09:32 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? (was: em0 freezes on ZFS
server) :
DB Furthermore I found this via Google:
DB
http://lists.freebsd.org/pipermail/freebsd-current/2009-December/014062.html.
This did not help, I
On Fri, 26 Feb 2010 22:09:32 +0200 Daniel Braniss da...@cs.huji.ac.il
wrote about Re: mbuf leakage with nfs/zfs? (was: em0 freezes on ZFS
server) :
DB at the moment there is not much activity, but if you check the latest
DB plot.ps you will see that the bottom is slowly increasing, so my bet
DB
On 26-2-2010 22:43, Gerrit Kühn wrote:
DB I'll have to do some packet snooping to check if it's TCP or UDP nfs
DB traffic, since some of the clients are Linux ...
I have Linux clients, too. Some use tcp, some udp.
I have Linux and FreeBSD clients running. The build system runs on
Linux.
On Fri, 26 Feb 2010 23:12:39 +0100 Willem Jan Withagen w...@digiware.nl
wrote about Re: mbuf leakage with nfs/zfs?:
WJW Mine are now:
WJW 41533/2402/43935 mbufs in use (current/cache/total)
WJW 41454/1572/43026/262144 mbuf clusters in use (current/cache/total/max)
WJW 39241/823 mbuf+clusters out
On Fri, 26 Feb 2010 23:12:39 +0100 Willem Jan Withagen w...@digiware.nl
wrote about Re: mbuf leakage with nfs/zfs?:
WJW DB I'll have to do some packet snooping to check if it's TCP or
WJW DB UDP nfs traffic, since some of the clients are Linux ...
WJW I have Linux clients, too. Some
43 matches
Mail list logo
