Re: ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
On Mon, Oct 28, 2013 at 02:56:17PM -0700, Xin Li wrote: > >>> Semi-indirect. dtrace -n 'fbt:kernel:vm_object_terminate:entry > >>> { @traces[stack()] = count(); }' > >>> > >>> After some (2-3) seconds > >>> > >>> kernel`vnode_destroy_vobject+0xb9 > >>> zfs.ko`zfs_freebsd_reclaim+0x2e kernel`VOP_

Re: ZFS txg implementation flaw

2013-10-28 Thread Jordan Hubbard
On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: > As I see ZFS cretate seperate thread for earch txg writing. > Also for writing to L2ARC. > As result -- up to several thousands threads created and destoyed per > second. And hundreds thousands page allocations, zeroing, maping > unmaping

Re: ZFS txg implementation flaw

2013-10-28 Thread Xin Li
-BEGIN PGP SIGNED MESSAGE- Hash: SHA512 On 10/28/13 14:45, Slawa Olhovchenkov wrote: > On Mon, Oct 28, 2013 at 02:38:30PM -0700, Xin Li wrote: > >> -BEGIN PGP SIGNED MESSAGE- Hash: SHA512 >> >> On 10/28/13 14:32, Slawa Olhovchenkov wrote: >>> On Mon, Oct 28, 2013 at 02:22:16PM -0

Re: ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
On Mon, Oct 28, 2013 at 02:38:30PM -0700, Xin Li wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA512 > > On 10/28/13 14:32, Slawa Olhovchenkov wrote: > > On Mon, Oct 28, 2013 at 02:22:16PM -0700, Jordan Hubbard wrote: > > > >> > >> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov > >> wr

Re: ZFS txg implementation flaw

2013-10-28 Thread Xin Li
-BEGIN PGP SIGNED MESSAGE- Hash: SHA512 On 10/28/13 14:32, Slawa Olhovchenkov wrote: > On Mon, Oct 28, 2013 at 02:22:16PM -0700, Jordan Hubbard wrote: > >> >> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov >> wrote: >> >>> As I see ZFS cretate seperate thread for earch txg writing. >

Re: ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
On Mon, Oct 28, 2013 at 02:22:16PM -0700, Jordan Hubbard wrote: > > On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: > > > As I see ZFS cretate seperate thread for earch txg writing. > > Also for writing to L2ARC. > > As result -- up to several thousands threads created and destoyed per >

Re: ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
On Mon, Oct 28, 2013 at 04:51:02PM -0400, Allan Jude wrote: > On 2013-10-28 16:48, Slawa Olhovchenkov wrote: > > On Mon, Oct 28, 2013 at 02:28:04PM -0400, Allan Jude wrote: > > > >> On 2013-10-28 14:16, Slawa Olhovchenkov wrote: > >>> On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: > >>

Re: ZFS txg implementation flaw

2013-10-28 Thread Allan Jude
On 2013-10-28 16:48, Slawa Olhovchenkov wrote: > On Mon, Oct 28, 2013 at 02:28:04PM -0400, Allan Jude wrote: > >> On 2013-10-28 14:16, Slawa Olhovchenkov wrote: >>> On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: >>> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: >

Re: ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
On Mon, Oct 28, 2013 at 02:28:04PM -0400, Allan Jude wrote: > On 2013-10-28 14:16, Slawa Olhovchenkov wrote: > > On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: > > > >> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: > >> > >>> I can be wrong. > >>> As I see ZFS cretate seperate

Re: ZFS txg implementation flaw

2013-10-28 Thread Allan Jude
On 2013-10-28 14:25, aurfalien wrote: > On Oct 28, 2013, at 11:16 AM, Slawa Olhovchenkov wrote: > >> On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: >> >>> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: >>> I can be wrong. As I see ZFS cretate seperate thread for earch

Re: ZFS txg implementation flaw

2013-10-28 Thread aurfalien
On Oct 28, 2013, at 11:16 AM, Slawa Olhovchenkov wrote: > On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: > >> >> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: >> >>> I can be wrong. >>> As I see ZFS cretate seperate thread for earch txg writing. >>> Also for writing to L2A

Re: ZFS txg implementation flaw

2013-10-28 Thread Allan Jude
On 2013-10-28 14:16, Slawa Olhovchenkov wrote: > On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: > >> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: >> >>> I can be wrong. >>> As I see ZFS cretate seperate thread for earch txg writing. >>> Also for writing to L2ARC. >>> As result

Re: ZFS txg implementation flaw

2013-10-28 Thread aurfalien
On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: > I can be wrong. > As I see ZFS cretate seperate thread for earch txg writing. > Also for writing to L2ARC. > As result -- up to several thousands threads created and destoyed per > second. And hundreds thousands page allocations, zeroing, m

Re: ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote: > > On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote: > > > I can be wrong. > > As I see ZFS cretate seperate thread for earch txg writing. > > Also for writing to L2ARC. > > As result -- up to several thousands threads created and

ZFS txg implementation flaw

2013-10-28 Thread Slawa Olhovchenkov
I can be wrong. As I see ZFS cretate seperate thread for earch txg writing. Also for writing to L2ARC. As result -- up to several thousands threads created and destoyed per second. And hundreds thousands page allocations, zeroing, maping unmaping and freeing per seconds. Very high overhead. In sys