Hello,
Solaris 10 GA + latest recommended patches:
while runing dtrace:
bash-3.00# dtrace -n ''io:::start {@[execname, args[2]->fi_pathname]
= count();}''
...
vim
/zones/obsdb3/root/opt/sfw/bin/vim 296
tnslsnr <none>
2373
fsflush <none>
2952
sched <none>
9949
ar60run <none>
13590
RACUST <none>
39252
RAXTRX <none>
39789
RAXMTR <none>
40671
FNDLIBR <none>
64956
oracle <none>
2096052
How can I interpret ''<none>'' ? Is it possible to get
full path (like in vim) ?
Regards
przemol
Hello przemolicc,
Tuesday, August 8, 2006, 3:54:26 PM, you wrote:
ppf> Hello,
ppf> Solaris 10 GA + latest recommended patches:
ppf> while runing dtrace:
ppf> bash-3.00# dtrace -n ''io:::start {@[execname,
ppf> args[2]->fi_pathname] = count();}''
ppf> ...
ppf> vim
ppf> /zones/obsdb3/root/opt/sfw/bin/vim 296
ppf> tnslsnr <none>
2373
ppf> fsflush <none>
2952
ppf> sched <none>
9949
ppf> ar60run <none>
13590
ppf> RACUST <none>
39252
ppf> RAXTRX <none>
39789
ppf> RAXMTR <none>
40671
ppf> FNDLIBR <none>
64956
ppf> oracle <none>
2096052
ppf> How can I interpret ''<none>'' ? Is it possible to
get full path (like in vim) ?
I guess Oracle is on ZFS.
Well right now IO provider won''t work properly with ZFS.
I guess it would be hard to implement IO provider in ZFS - but maybe
not?
However you can use syscall provider and monitor pread, pwrite, etc.
syscalls.
--
Best regards,
Robert mailto:rmilkowski at task.gda.pl
http://milek.blogspot.com
On 8/8/06, przemolicc at poczta.fm <przemolicc at poczta.fm> wrote:> > Hello, > > Solaris 10 GA + latest recommended patches: > > while runing dtrace: > > bash-3.00# dtrace -n ''io:::start {@[execname, args[2]->fi_pathname] > count();}'' > ... > > oracle <none> 2096052 > > How can I interpret ''<none>'' ? Is it possible to get full path (like in > vim) ? > >Section "27.2.3 fileinfo_t" of DTrace Guide explains in detail why you see ''<none>'' in many cases. http://www.sun.com/bigadmin/content/dtrace/d10_latest.pdf or http://docs.sun.com/app/docs/doc/817-6223/6mlkidllf?a=view The "execname" part can also be misleading, as many I/O activities are "asynchronous" (including but not limited to Asynchronous I/O), so whatever thread running on CPU may have nothing to do with the I/O that''s occuring. This is working as designed and not a "problem" that limited to ZFS, IMO. Tao -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20060808/cf52e75a/attachment.html>
On Tue, Aug 08, 2006 at 04:47:51PM +0200, Robert Milkowski wrote:> Hello przemolicc, > > Tuesday, August 8, 2006, 3:54:26 PM, you wrote: > > ppf> Hello, > > ppf> Solaris 10 GA + latest recommended patches: > > ppf> while runing dtrace: > > ppf> bash-3.00# dtrace -n ''io:::start {@[execname, > ppf> args[2]->fi_pathname] = count();}'' > ppf> ... > ppf> vim > ppf> /zones/obsdb3/root/opt/sfw/bin/vim 296 > ppf> tnslsnr <none> 2373 > ppf> fsflush <none> 2952 > ppf> sched <none> 9949 > ppf> ar60run <none> 13590 > ppf> RACUST <none> 39252 > ppf> RAXTRX <none> 39789 > ppf> RAXMTR <none> 40671 > ppf> FNDLIBR <none> 64956 > ppf> oracle <none> 2096052 > > ppf> How can I interpret ''<none>'' ? Is it possible to get full path (like in vim) ? > > I guess Oracle is on ZFS.Ooops ! After your e-mail I realised I should sent it to dtrace-discuss not zfs-discuss ! No ! Oracle is not on zfs. Sorry !> Well right now IO provider won''t work properly with ZFS. > I guess it would be hard to implement IO provider in ZFS - but maybe > not? > > However you can use syscall provider and monitor pread, pwrite, etc. > syscalls. > > -- > Best regards, > Robert mailto:rmilkowski at task.gda.pl > http://milek.blogspot.com >
On Tue, Aug 08, 2006 at 11:33:28AM -0500, Tao Chen wrote:> On 8/8/06, przemolicc at poczta.fm <przemolicc at poczta.fm> wrote: > > > >Hello, > > > >Solaris 10 GA + latest recommended patches: > > > >while runing dtrace: > > > >bash-3.00# dtrace -n ''io:::start {@[execname, args[2]->fi_pathname] > >count();}'' > >... > > > > oracle <none> > > 2096052 > > > >How can I interpret ''<none>'' ? Is it possible to get full path (like in > >vim) ? > > > > > Section "27.2.3 fileinfo_t" of DTrace Guide > explains in detail why you see ''<none>'' in many cases. > http://www.sun.com/bigadmin/content/dtrace/d10_latest.pdf > or > http://docs.sun.com/app/docs/doc/817-6223/6mlkidllf?a=view > > The "execname" part can also be misleading, as many I/O activities are > "asynchronous" (including but not limited to Asynchronous I/O), so whatever > thread running on CPU may have nothing to do with the I/O that''s occuring. > > This is working as designed and not a "problem" that limited to ZFS, IMO.Thanks Tao for the doc pointers. I haven''t noticed them. przemol
On Tue, Aug 08, 2006 at 11:33:28AM -0500, Tao Chen wrote:> On 8/8/06, przemolicc at poczta.fm <przemolicc at poczta.fm> wrote: > > > >Hello, > > > >Solaris 10 GA + latest recommended patches: > > > >while runing dtrace: > > > >bash-3.00# dtrace -n ''io:::start {@[execname, args[2]->fi_pathname] > >count();}'' > >... > > > > oracle <none> > > 2096052 > > > >How can I interpret ''<none>'' ? Is it possible to get full path (like in > >vim) ? > > > > > Section "27.2.3 fileinfo_t" of DTrace Guide > explains in detail why you see ''<none>'' in many cases. > http://www.sun.com/bigadmin/content/dtrace/d10_latest.pdf > or > http://docs.sun.com/app/docs/doc/817-6223/6mlkidllf?a=view > > The "execname" part can also be misleading, as many I/O activities are > "asynchronous" (including but not limited to Asynchronous I/O), so whatever > thread running on CPU may have nothing to do with the I/O that''s occuring. > > This is working as designed and not a "problem" that limited to ZFS, IMO.Thanks Tao for the doc pointers. I haven''t noticed them. przemol _______________________________________________ zfs-discuss mailing list zfs-discuss at opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss -- This message posted from opensolaris.org