I recently converted my home directory to zfs on an external disk drive.
Approximately every three seconds I can hear the disk being accessed,
even if I'm doing nothing. The noise is driving me crazy!
I tried using dtrace to find out what process might be accessing the
disk. I used the iosnoop program from the dtrace toolkit. No matter
what I do, iosnoop doesn't report any accesses to the disk. Is it
broken? Is it a limitation of zfs? Am I doing something wrong?
Running just plain "iosnoop" shows accesses to lots of files, but none
on my zfs disk. Using "iosnoop -d c1t1d0" or "iosnoop -m /export/home/shannon"
shows nothing at all. I tried /usr/demo/dtrace/iosnoop.d too, still nothing.
Meanwhile, "zpool iostat 5" shows the disk being accessed. Glenn Skinner
told me about the parameter zfs:spa_max_replication_override. Setting it
to 1 is supposed to disable ditto blocks in zfs. Here's what I get when
I set it to 1:
$ zpool iostat 5
capacity operations bandwidth
pool used avail read write read write
---------- ----- ----- ----- ----- ----- -----
home 12.4G 4.55G 0 2 11.7K 41.1K
home 12.4G 4.55G 0 6 0 133K
home 12.4G 4.55G 0 6 0 162K
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 7 0 144K
home 12.4G 4.55G 0 6 0 153K
home 12.4G 4.55G 0 6 0 139K
home 12.4G 4.55G 0 6 0 132K
home 12.4G 4.55G 0 6 0 144K
home 12.4G 4.55G 0 6 0 135K
home 12.4G 4.55G 0 12 0 186K
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 13 0 265K
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
Setting it back to its original value of 3 while still running gives:
home 12.4G 4.55G 0 12 0 185K
home 12.4G 4.55G 0 12 0 258K
home 12.4G 4.55G 0 11 0 188K
home 12.4G 4.55G 0 11 0 175K
home 12.4G 4.55G 0 11 0 184K
home 12.4G 4.55G 0 12 0 180K
That seems to be related to my problem, but it doesn't seem to be the
whole problem.
Curiously, when I came in to my office this morning, I didn't hear my
disk making noise. It wasn't until after I unlocked the screen that
the noise started, which makes my think it must be something related
to my desktop.
If I check the I/O activity now, logged in remotely with my screen
locked, I get:
$ zpool iostat 5
capacity operations bandwidth
pool used avail read write read write
---------- ----- ----- ----- ----- ----- -----
home 12.4G 4.55G 0 2 10.9K 39.6K
home 12.4G 4.55G 0 11 0 171K
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 10 0 149K
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 0 0 0
home 12.4G 4.55G 0 11 0 146K
home 12.4G 4.55G 0 12 0 186K
Much less activity, but still not zero.
Anyway, anyone have any ideas of how I can use dtrace or some other tool
to track this down? Any chance that there's something about zfs that is
causing this problem? Is there something about zfs that prevents dtrace
from working properly?
Oh ya, I'm running snv_79b on SPARC.
Thanks.
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
