libata - anomaly performance with NCQ

libata - anomaly performance with NCQ

[Bartosz SKOWRON]

Hi,

here is a problem:
http://ata.wiki.kernel.org/index.php/Known_issues#Seagate_harddrive_performance_anomaly_with_hdparm

and my disk is affected by this one as well.
it's ST9320421AS and you can add it to the list

And 2 questions:
1) cause the title contains "with hdparm"...does it mean that
physically the performance is OK and only hdparm shows something
wrong?
2) there is an information about upgrading firmware. as far as i know
Seagate doesn't publish firmwares. So the only way is to contact
seagate support, send the hdd and wait for the new one?

bart.

Re: libata - anomaly performance with NCQ

[Robert Hancock]

Bartosz SKOWRON wrote:
> Hi,
> 
> here is a problem:
> http://ata.wiki.kernel.org/index.php/Known_issues#Seagate_harddrive_performance_anomaly_with_hdparm
> 
> and my disk is affected by this one as well.
> it's ST9320421AS and you can add it to the list
> 
> And 2 questions:
> 1) cause the title contains "with hdparm"...does it mean that
> physically the performance is OK and only hdparm shows something
> wrong?

Well, hdparm is a fairly crude benchmark but there's likely at least 
some impact in other usage.

> 2) there is an information about upgrading firmware. as far as i know
> Seagate doesn't publish firmwares. So the only way is to contact
> seagate support, send the hdd and wait for the new one?

I think Seagate can provide firmware updaters for the user to use, but 
normally only if you contact support I think.

Re: libata - anomaly performance with NCQ

[Bartosz SKOWRON]

On Sat, Jan 31, 2009 at 2:07 AM, Robert Hancock <hancockr@shaw.ca> wrote:

>> 1) cause the title contains "with hdparm"...does it mean that
>> physically the performance is OK and only hdparm shows something
>> wrong?
> Well, hdparm is a fairly crude benchmark but there's likely at least some
> impact in other usage.

It's not an answer for my question. So, should I check with other
benchmarks? I thought that this's issue is investigated and the answer
is common. Do you recommend any "not crude" benchmarks? :)


>> 2) there is an information about upgrading firmware. as far as i know
>> Seagate doesn't publish firmwares. So the only way is to contact
>> seagate support, send the hdd and wait for the new one?
> I think Seagate can provide firmware updaters for the user to use, but
> normally only if you contact support I think.

I will send the email cause there is no phone line for my country.
BTW. upgrade firmware == damage data?

Re: libata - anomaly performance with NCQ

[Robert Hancock]

Bartosz SKOWRON wrote:
> On Sat, Jan 31, 2009 at 2:07 AM, Robert Hancock <hancockr@shaw.ca> wrote:
> 
>>> 1) cause the title contains "with hdparm"...does it mean that
>>> physically the performance is OK and only hdparm shows something
>>> wrong?
>> Well, hdparm is a fairly crude benchmark but there's likely at least some
>> impact in other usage.
> 
> It's not an answer for my question. So, should I check with other
> benchmarks? I thought that this's issue is investigated and the answer
> is common. Do you recommend any "not crude" benchmarks? :)

bonnie++ is one I've used, I'm sure there are others.. Of course, what 
do you compare the results to..

> 
> 
>>> 2) there is an information about upgrading firmware. as far as i know
>>> Seagate doesn't publish firmwares. So the only way is to contact
>>> seagate support, send the hdd and wait for the new one?
>> I think Seagate can provide firmware updaters for the user to use, but
>> normally only if you contact support I think.
> 
> I will send the email cause there is no phone line for my country.
> BTW. upgrade firmware == damage data?

It shouldn't, but some people with the recent 7200.11 drives that did 
firmware upgrades reported it bricked the drive, so backing up the data 
first would definitely be a good idea..

Re: libata - anomaly performance with NCQ

[Bartosz SKOWRON]

On Sat, Jan 31, 2009 at 6:18 AM, Robert Hancock <hancockrwd@gmail.com> wrote:

> bonnie++ is one I've used, I'm sure there are others.. Of course, what do
> you compare the results to..

Hmmm more tests == more confusions ;-)

NCQ ENABLED:

Version 1.03b       ------Sequential Output------ --Sequential Input- --Random-
                    -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP
banan            6G 32681  99 81220  35 37915  31 32675  99 88157  28 286.0   0
                    ------Sequential Create------ --------Random Create--------
                    -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
              files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
                 16  3115  32 +++++ +++  3774  38  3321  38 +++++ +++  1004  10

NCQ DISABLED:
Version 1.03b       ------Sequential Output------ --Sequential Input- --Random-
                    -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP
banan            6G 32617  99 84305  36 36022  16 32889  99 88199  28 233.9   0
                    ------Sequential Create------ --------Random Create--------
                    -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
              files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
                 16  3866  40 +++++ +++  5538  48  3668  38 +++++ +++  1093  11


So it looks very similar but without ncq looks a bit better, doesn't it?

something practical test: copy a movie file (~750MB) into /tmp (tmpfs):
ncq: ~70-75MB/s
noncq: ~65-70MB/s

and hdparm once again:

ncq:
 Timing buffered disk reads:  108 MB in  3.06 seconds =  35.33 MB/sec
noncq:
 Timing buffered disk reads:  258 MB in  3.01 seconds =  85.63 MB/sec


Can you or anyone else analyze those results? They confuse me a lot
cause they are sometimes in a conflict.
And what results of bonnie++ should i compare to other tests?
sequintal output:block ? or per?

and here is my hdd:
 Model=ST9320421AS                             , FwRev=SD13    ,
SerialNo=            5TJ0DGSP
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
 RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=4
 BuffType=unknown, BuffSize=16384kB, MaxMultSect=16, MultSect=?16?
 CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=625142448
 IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
 PIO modes:  pio0 pio1 pio2 pio3 pio4
 DMA modes:  mdma0 mdma1 mdma2
 UDMA modes: udma0 udma1 udma2 udma3 udma4 udma5 *udma6
 AdvancedPM=yes: unknown setting WriteCache=enabled
 Drive conforms to: unknown:  ATA/ATAPI-4,5,6,7


regards,
bart