Date: Sat, 14 Nov 1998 00:25:23 +0100 From: Bernd Walter <ticso@cicely.de> To: Mike Smith <mike@smith.net.au>, Peter Jeremy <peter.jeremy@auss2.alcatel.com.au> Cc: hackers@FreeBSD.ORG Subject: Re: [Vinum] Stupid benchmark: newfsstone Message-ID: <19981114002523.39363@cicely.de> In-Reply-To: <199811132150.NAA00549@dingo.cdrom.com>; from Mike Smith on Fri, Nov 13, 1998 at 01:50:40PM -0800 References: <98Nov13.140613est.40335@border.alcanet.com.au> <199811132150.NAA00549@dingo.cdrom.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Nov 13, 1998 at 01:50:40PM -0800, Mike Smith wrote:
> > Greg Lehey <grog@lemis.com> wrote:
> > > And it's almost impossible to find
> > >spindle synchronized disks nowadays.
> >
> > Seagate Barracuda's support it, I assumed that the newer Seagates did
> > as well. The impression I got was that all you had to do was wire the
> > `spindle sync' lines from all the disks together and then designate
> > all except one as a sync'd slave. Admittedly, I've never tried
> > actually using it.
>
> Most modern "server class" SCSI disks support it. It's not useful
> unless you turn off tagged queueing, caching and most other drive
> performance features.
Where's the problem with these options on when using Spindle Sync?
>
> > > Finally, aggregating involves a
> > >scatter/gather approach which, unless I've missed something, is not
> > >supported at a hardware level. Each request to the driver specifies
> > >one buffer for the transfer, so the scatter gather would have to be
> > >done by allocating more memory and performing the transfer there (for
> > >a read) and then copying to the correct place.
> >
> > Since the actual data transfer occurs to physical memory, whilst the
> > kernel buffers are in VM, this should just require some imaginative
> > juggling of the PTE's so the physical pages (or actual scatter/gather
> > requests) are de-interleaved (to match the data on each spindle).
>
> You'd have to cons a new map and have it present the scattered target
> area as a linear region. This is expensive, and the performance boost
> is likely to be low to nonexistent for optimal stripe sizes.
> Concatenation of multiple stripe reads is only a benefit if the stripe
> is small (so that concatenation significantly lowers overhead).
That's right - but you can't expect a high linear performance increase
when using great stripes.
By the way: Is FFS limited to 64k Blocksize?
At least newfs can't handle it it my case:
root@cicely5# newfs -f 65536 -b 131072 rda14e
Warning: 640 sector(s) in last cylinder unallocated
/dev/rda14e: 2116992 sectors in 517 cylinders of 1 tracks, 4096 sectors
1033.7MB in 33 cyl groups (16 c/g, 32.00MB/g, 1024 i/g)
super-block backups (for fsck -b #) at:
256, 65792, 131328, 196864, 262400, 327936, 393472, 459008, 524544, 590080, 655616, 721152, 786688, 852224, 917760, 983296,
1048832, 1114368, 1179904, 1245440, 1310976, 1376512, 1442048, 1507584, 1573120, 1638656, 1704192, 1769728, 1835264, 1900800,
1966336, 2031872, 2097408,
read error: 768
newfs: rdfs: Bad address
root@cicely5# newfs -f 65536 -b 65536 rda14e
Warning: 640 sector(s) in last cylinder unallocated
/dev/rda14e: 2116992 sectors in 517 cylinders of 1 tracks, 4096 sectors
1033.7MB in 33 cyl groups (16 c/g, 32.00MB/g, 512 i/g)
super-block backups (for fsck -b #) at:
128, 65664, 131200, 196736, 262272, 327808, 393344, 458880, 524416, 589952, 655488, 721024, 786560, 852096, 917632, 983168,
1048704, 1114240, 1179776, 1245312, 1310848, 1376384, 1441920, 1507456, 1572992, 1638528, 1704064, 1769600, 1835136, 1900672,
1966208, 2031744, 2097280,
>
> > What would be useful is some help (from vinum or ccd) to ensure that
> > the cylinder group blocks (superblock + inode maps etc) don't cross
> > stripes.
>
> That's something that the user should take care of. Any power-of-2
> stripe size is likely to work out OK, as CG's are currently 32MB.
>
> --
> \\ Sometimes you're ahead, \\ Mike Smith
> \\ sometimes you're behind. \\ mike@smith.net.au
> \\ The race is long, and in the \\ msmith@freebsd.org
> \\ end it's only with yourself. \\ msmith@cdrom.com
>
>
>
> To Unsubscribe: send mail to majordomo@FreeBSD.org
> with "unsubscribe freebsd-hackers" in the body of the message
--
B.Walter
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19981114002523.39363>