On Thu, May 23, 2019 at 7:44 AM <mad.scientist.at.la...@tutanota.com> wrote:

> I just put an SSD into my hp dl585g7.  I used the provided sata SSD drive
> connector, it's on the same sata driver that runs the optical drive.  It's
> terribly slow to boot etc.  Is this just a slow controller designed to keep
> up with an optical drive and swamped by an SSD?  would pulling the optical
> drive help?   I may wind up hooking it to the internal SAS controller with
> a suitable cable (there are 2 cables to the plugable hard drive area, i
> could swap one for another cable as I'm only using 2 hard drives.  I'd just
> need to extend the power from the built in ssd connector.  Advice?
> Suggestions??  At this point it's slow to boot like a thumb drive on USB 2
> or an optical drive.  I have an identical SSD in my desktop and it runs
> near the rated 500MB/s so I'm confident the SSD is good.
>

Have you compared hdparm <device> and hdparm -tT <device> outputs between
the hp and laptop?

On my system with an SATA SSD, its only;
# hdparm -tT /dev/sda

/dev/sda:
 Timing cached reads:   7820 MB in  2.00 seconds = 3912.89 MB/sec
 Timing buffered disk reads: 172 MB in  3.13 seconds =  55.02 MB/sec

So 3x slower than the spinning disks on the same box for the buffered disk
reads....
# hdparm /dev/sda

/dev/sda:
 multcount     =  0 (off)
 IO_support    =  1 (32-bit)
 readonly      =  0 (off)
 readahead     = 256 (on)
 geometry      = 30401/255/63, sectors = 488397168, start = 0

multicount off is weird, lets see what it reports;
hdparm -i /dev/sda | grep MaxMultSect
 BuffType=unknown, BuffSize=unknown, MaxMultSect=16, MultSect=off

So it should be possible to set it to 16,
# hdparm -m 16  /dev/sda

/dev/sda:
 setting multcount to 16
Use of -m is VERY DANGEROUS.
Only the old IDE drivers work correctly with -m with kernels up to at least
2.6.29.
libata drives may fail and get hung if you set this flag.
Please supply the --yes-i-know-what-i-am-doing flag if you really want this.
Program aborted.

Ok i'm not concerned about speed on this box, so i wont bother.
Interestingly the spinning disks are multicount off on this box too, so
that setting doesn't explain the SSD's slowness.

Reply via email to