My LTO tape drive is slow and “shoe-shines†on FreeBSD
Clash Royale CLAN TAG#URR8PPP
up vote
3
down vote
favorite
Regardless of what data I write to my LTO-4 tape drive /dev/nsa0, writing is very slow (less than 1 MB/s) and the tape is constantly being wound back and forth in a shoe-shine pattern. No speed problem occurs when reading or erasing (with mt erase) tapes. It appears that this problem occurs since I tried to enable SMART monitoring on the tape drive using smartctl.
freebsd scsi tape
asked Oct 15 '17 at 0:18
FUZxxl
3321212
add a comment |Â
up vote
3
down vote
favorite
Regardless of what data I write to my LTO-4 tape drive /dev/nsa0, writing is very slow (less than 1 MB/s) and the tape is constantly being wound back and forth in a shoe-shine pattern. No speed problem occurs when reading or erasing (with mt erase) tapes. It appears that this problem occurs since I tried to enable SMART monitoring on the tape drive using smartctl.
freebsd scsi tape
asked Oct 15 '17 at 0:18
FUZxxl
3321212
What block size are you using when writing?
– Mark Plotnick
Oct 15 '17 at 0:25
@MarkPlotnick 1 MB using a kernel with patchedMAXPHYS. The effect is independent of block size.
– FUZxxl
Oct 15 '17 at 0:26
add a comment |Â
up vote
3
down vote
favorite
up vote
3
down vote
favorite
Regardless of what data I write to my LTO-4 tape drive /dev/nsa0, writing is very slow (less than 1 MB/s) and the tape is constantly being wound back and forth in a shoe-shine pattern. No speed problem occurs when reading or erasing (with mt erase) tapes. It appears that this problem occurs since I tried to enable SMART monitoring on the tape drive using smartctl.
freebsd scsi tape
asked Oct 15 '17 at 0:18
FUZxxl
3321212
Regardless of what data I write to my LTO-4 tape drive /dev/nsa0, writing is very slow (less than 1 MB/s) and the tape is constantly being wound back and forth in a shoe-shine pattern. No speed problem occurs when reading or erasing (with mt erase) tapes. It appears that this problem occurs since I tried to enable SMART monitoring on the tape drive using smartctl.
freebsd scsi tape
asked Oct 15 '17 at 0:18
FUZxxl
3321212
edited Jul 3 at 11:05
asked Oct 15 '17 at 0:18
FUZxxl
3321212
asked Oct 15 '17 at 0:18
FUZxxl
3321212
asked Oct 15 '17 at 0:18
FUZxxl
3321212
3321212
What block size are you using when writing?
– Mark Plotnick
Oct 15 '17 at 0:25
@MarkPlotnick 1 MB using a kernel with patchedMAXPHYS. The effect is independent of block size.
– FUZxxl
Oct 15 '17 at 0:26
add a comment |Â
What block size are you using when writing?
– Mark Plotnick
Oct 15 '17 at 0:25
@MarkPlotnick 1 MB using a kernel with patchedMAXPHYS. The effect is independent of block size.
– FUZxxl
Oct 15 '17 at 0:26
What block size are you using when writing?
– Mark Plotnick
Oct 15 '17 at 0:25
What block size are you using when writing?
– Mark Plotnick
Oct 15 '17 at 0:25
@MarkPlotnick 1 MB using a kernel with patched
MAXPHYS. The effect is independent of block size.– FUZxxl
Oct 15 '17 at 0:26
@MarkPlotnick 1 MB using a kernel with patched
MAXPHYS. The effect is independent of block size.– FUZxxl
Oct 15 '17 at 0:26
add a comment |Â
1 Answer
1
active
oldest
votes
up vote
4
down vote
accepted
It is possible that the buffering mode has been set to “unbuffered.†This is a special feature of LTO tape drives, forcing them to return from a WRITE command only after the data has been written to the tape. This stops any streaming from happening and causes the observed effects.
Unfortunately FreeBSD does not provide the mt drvbuffer 1 command from Linux to turn buffering back on, but it is possible to manually send an appropriately crafted MODE SELECT command to the drive to turn buffering back on:
camcontrol cmd /dev/nsa0 -c '15 10 00 00 04 00' -o 4 '0 0 10 0'
If you have more than one tape drive, replace /dev/nsa0 with an appropriate device file.
answered Oct 15 '17 at 0:18
FUZxxl
3321212
add a comment |Â
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
up vote
4
down vote
accepted
It is possible that the buffering mode has been set to “unbuffered.†This is a special feature of LTO tape drives, forcing them to return from a WRITE command only after the data has been written to the tape. This stops any streaming from happening and causes the observed effects.
Unfortunately FreeBSD does not provide the mt drvbuffer 1 command from Linux to turn buffering back on, but it is possible to manually send an appropriately crafted MODE SELECT command to the drive to turn buffering back on:
camcontrol cmd /dev/nsa0 -c '15 10 00 00 04 00' -o 4 '0 0 10 0'
If you have more than one tape drive, replace /dev/nsa0 with an appropriate device file.
answered Oct 15 '17 at 0:18
FUZxxl
3321212
add a comment |Â
up vote
4
down vote
accepted
It is possible that the buffering mode has been set to “unbuffered.†This is a special feature of LTO tape drives, forcing them to return from a WRITE command only after the data has been written to the tape. This stops any streaming from happening and causes the observed effects.
Unfortunately FreeBSD does not provide the mt drvbuffer 1 command from Linux to turn buffering back on, but it is possible to manually send an appropriately crafted MODE SELECT command to the drive to turn buffering back on:
camcontrol cmd /dev/nsa0 -c '15 10 00 00 04 00' -o 4 '0 0 10 0'
If you have more than one tape drive, replace /dev/nsa0 with an appropriate device file.
answered Oct 15 '17 at 0:18
FUZxxl
3321212
add a comment |Â
up vote
4
down vote
accepted
up vote
4
down vote
accepted
It is possible that the buffering mode has been set to “unbuffered.†This is a special feature of LTO tape drives, forcing them to return from a WRITE command only after the data has been written to the tape. This stops any streaming from happening and causes the observed effects.
Unfortunately FreeBSD does not provide the mt drvbuffer 1 command from Linux to turn buffering back on, but it is possible to manually send an appropriately crafted MODE SELECT command to the drive to turn buffering back on:
camcontrol cmd /dev/nsa0 -c '15 10 00 00 04 00' -o 4 '0 0 10 0'
If you have more than one tape drive, replace /dev/nsa0 with an appropriate device file.
answered Oct 15 '17 at 0:18
FUZxxl
3321212
It is possible that the buffering mode has been set to “unbuffered.†This is a special feature of LTO tape drives, forcing them to return from a WRITE command only after the data has been written to the tape. This stops any streaming from happening and causes the observed effects.
Unfortunately FreeBSD does not provide the mt drvbuffer 1 command from Linux to turn buffering back on, but it is possible to manually send an appropriately crafted MODE SELECT command to the drive to turn buffering back on:
camcontrol cmd /dev/nsa0 -c '15 10 00 00 04 00' -o 4 '0 0 10 0'
If you have more than one tape drive, replace /dev/nsa0 with an appropriate device file.
answered Oct 15 '17 at 0:18
FUZxxl
3321212
answered Oct 15 '17 at 0:18
FUZxxl
3321212
answered Oct 15 '17 at 0:18
FUZxxl
3321212
answered Oct 15 '17 at 0:18
FUZxxl
3321212
3321212
add a comment |Â
add a comment |Â
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2funix.stackexchange.com%2fquestions%2f398179%2fmy-lto-tape-drive-is-slow-and-shoe-shines-on-freebsd%23new-answer', 'question_page');
);
Post as a guest
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
What block size are you using when writing?
– Mark Plotnick
Oct 15 '17 at 0:25
@MarkPlotnick 1 MB using a kernel with patched
MAXPHYS. The effect is independent of block size.– FUZxxl
Oct 15 '17 at 0:26