mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* Re: nfs unhappiness with memory pressure
@ 2005-12-06 13:40 Albert Herranz
  0 siblings, 0 replies; 25+ messages in thread
From: Albert Herranz @ 2005-12-06 13:40 UTC (permalink / raw)
  To: trond.myklebust, theonetruekenny; +Cc: linux-kernel

Hi,

The patch linux-2.6.15-fix_sock_allocation.dif seems
to have helped with this issue.

With this patch applied I have been unable to
reproduce the system freezes I was experiencing in
latest 2.6.x kernels when using nfs-root on my
GameCube (24MB RAM).

Thanks,
Albert



	
	
		
______________________________________________ 
Renovamos el Correo Yahoo! 
Nuevos servicios, más seguridad 
http://correo.yahoo.es

^ permalink raw reply	[flat|nested] 25+ messages in thread
* Re: infinite loop? with mmap, nfs, pwrite, O_DIRECT
@ 2005-11-22  0:49 Trond Myklebust
  2005-11-30 20:04 ` nfs unhappiness with memory pressure Kenny Simpson
  0 siblings, 1 reply; 25+ messages in thread
From: Trond Myklebust @ 2005-11-22  0:49 UTC (permalink / raw)
  To: Andrew Morton; +Cc: theonetruekenny, cel, linux-kernel

On Mon, 2005-11-21 at 16:28 -0800, Andrew Morton wrote:
> Trond Myklebust <trond.myklebust@fys.uio.no> wrote:
> >
> > On Mon, 2005-11-21 at 16:09 -0800, Andrew Morton wrote:
> > > Trond Myklebust <trond.myklebust@fys.uio.no> wrote:
> > > >
> > > > The only difference I can see between the two paths is the call to
> > > >  unmap_mapping_range(). What effect would that have?
> > > 
> > > It shoots down any mapped pagecache over the affected file region.  Because
> > > the direct-io write is about to make that pagecache out-of-date.  If the
> > > application tries to use that data again it'll get a major fault and will
> > > re-read the file contents.
> > 
> > I assume then, that this couldn't be the cause of the
> > invalidate_inode_pages() failing to complete?
> 
> It sounds unlikely.  This hang is associated with crossing the 2G boundary
> isn't it?
> 
> I don't think we've seen a sysrq-T trace from the hang?

Kenny sent us this trace. The thing appears to be hanging in
unmap_mapping_range() as called by invalidate_inode_pages2()

Pid: 4271, comm:            writetest
EIP: 0060:[<c029cd2b>] CPU: 0
EIP is at prio_tree_first+0x26/0xb8
 EFLAGS: 00000292    Tainted: P       (2.6.15-rc1)
EAX: 00000000 EBX: f6765d94 ECX: f6765d94 EDX: 00000200
ESI: 00000000 EDI: f5da475c EBP: f6765db4 DS: 007b ES: 007b
CR0: 8005003b CR2: b7590000 CR3: 36b5d000 CR4: 000006d0
 [<c029ce5e>] prio_tree_next+0xa1/0xa3
 [<c014822a>] vma_prio_tree_next+0x27/0x51
 [<c014b1dc>] unmap_mapping_range+0x18b/0x210
 [<c0120d06>] __do_softirq+0x6a/0xd1
 [<c0103a24>] apic_timer_interrupt+0x1c/0x24
 [<c0146577>] invalidate_inode_pages2_range+0x215/0x24c
 [<c01465cd>] invalidate_inode_pages2+0x1f/0x26
 [<c01e4031>] nfs_file_direct_write+0x1e1/0x21a
 [<c0159ea4>] do_sync_write+0xc7/0x10d
 [<c012ff32>] autoremove_wake_function+0x0/0x57
 [<c0159f92>] vfs_write+0xa8/0x177
 [<c015a275>] sys_pwrite64+0x88/0x8c
 [<c0102f51>] syscall_call+0x7/0xb

> > Unless there is some
> > method to prevent applications from faulting in the page while we're
> > inside generic_file_direct_IO(), then the same race would be able to
> > occur there.
> 
> Yes, there are still windows.
> 
> Another thing the unmap_mapping_range() does is to push pte-dirty bits into
> the software-dirty flags, so the modified data does get written.  If we
> didn't do this, a page which was dirtied via mmap before the direct-io
> write would get written back _after_ the direct-io write, arguably causing
> corruption.

As far as we're concerned, anybody using direct-io is responsible for
enforcing their own ordering. The pagecache is one thing, but in NFS,
direct IO is mainly used in situations where several clients are writing
to the same file. There is no way to ensure fully safe mmap() semantics.

Cheers,
  Trond


^ permalink raw reply	[flat|nested] 25+ messages in thread

end of thread, other threads:[~2005-12-06 19:31 UTC | newest]

Thread overview: 25+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2005-12-06 13:40 nfs unhappiness with memory pressure Albert Herranz
  -- strict thread matches above, loose matches on Subject: below --
2005-11-22  0:49 infinite loop? with mmap, nfs, pwrite, O_DIRECT Trond Myklebust
2005-11-30 20:04 ` nfs unhappiness with memory pressure Kenny Simpson
2005-11-30 21:42   ` Keith Mannthey
2005-11-30 22:18     ` Kenny Simpson
2005-12-01 14:49     ` Kenny Simpson
2005-12-05 18:01   ` Kenny Simpson
2005-12-05 19:44     ` Kenny Simpson
2005-12-05 20:14       ` Kenny Simpson
2005-12-05 20:13     ` Trond Myklebust
2005-12-05 20:33       ` Trond Myklebust
2005-12-05 20:52         ` Nick Piggin
2005-12-05 21:18           ` Trond Myklebust
2005-12-05 21:23             ` Trond Myklebust
2005-12-05 23:40               ` Nick Piggin
2005-12-06  0:48                 ` Trond Myklebust
2005-12-05 21:51             ` Kenny Simpson
2005-12-05 21:04         ` Kenny Simpson
2005-12-05 22:39           ` Trond Myklebust
2005-12-06  3:36             ` Andrew Morton
2005-12-06  3:36             ` Andrew Morton
2005-12-06  4:40               ` Trond Myklebust
2005-12-06  5:42                 ` Nick Piggin
2005-12-06 12:18                   ` Trond Myklebust
2005-12-06 19:31               ` Kenny Simpson
2005-12-06 15:51             ` Kenny Simpson

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®