On 2/10/2010 12:02 AM, Dan Langille wrote:
Trying to make sense of stuff I don't know about...
Matthew Dillon wrote:
AHCI on-motherboard with equivalent capabilities do not appear to be
in wide distribution yet. Most AHCI chips can do NCQ to a single
target (even a single target behind a PM), but not concurrently to
multiple targets behind a port multiplier. Even though SATA
bandwidth
constraints might seem to make this a reasonable alternative it
actually isn't because any seek heavy activity to multiple drives
will be serialized and perform EXTREMELY poorly. Linear performance
will be fine. Random performance will be horrible.
Don't use a port multiplier and this goes away. I was hoping to avoid
a PM and using something like the Syba PCI Express SATA II 4 x Ports
RAID Controller seems to be the best solution so far.
http://www.amazon.com/Syba-Express-Ports-Controller-SY-PEX40008/dp/B002R0DZWQ/ref=sr_1_22?ie=UTF8&s=electronics&qid=1258452902&sr=1-22
Dan, I can personally vouch for these cards under FreeBSD. We have 3 of
them in one system, with almost every port connected to a port
multiplier (SiI5xxx PMs). Using the siis(4) driver on 8.0-RELEASE
provides very good performance, and supports both NCQ and FIS-based
switching (an essential for decent port-multiplier performance).
One thing to consider, however, is that the card is only single-lane
PCI-Express. The bandwidth available is only 2.5Gb/s (~312MB/sec,
slightly less than that of the SATA-2 link spec), so if you have 4
high-performance drives connected, you may hit a bottleneck at the
bus. I'd be particularly interested if anyone can find any similar
Silicon Image SATA controllers with a PCI-E 4x or 8x interface ;)
It should be noted that while hotswap is supported with silicon
image
chipsets and port multiplier enclosures (which also use Sili
chips in
the enclosure), the hot-swap capability is not anywhere near as
robust
as you would find with a more costly commercial SAS setup. SI chips
are very poorly made (this is the same company that went bust under
another name a few years back due to shoddy chipsets), and have a
lot
of on-chip hardware bugs, but fortunately OSS driver writers (linux
guys) have been able to work around most of them. So even though
the
chipset is a bit shoddy actual operation is quite good. However,
this does mean you generally want to idle all activity on the
enclosure
to safely hot swap anything, not just the drive you are pulling out.
I've done a lot of testing and hot-swapping an idle disk while other
drives in the same enclosure are hot is not reliable (for a cheap
port
multiplier enclosure using a Sili chip inside, which nearly all do).
I haven't had such bad experience as the above, but it is certainly a
concern. Using ZFS we simply 'offline' the device, pull, replace with a
new one, glabel, and zfs replace. It seems to work fine as long as
nothing is accessing the device you are replacing (otherwise you will
get a kernel panic a few minutes down the line). [email protected] has
also committed a large patch set to 9-CURRENT which implements "proper"
SATA/AHCI hot-plug support and error-recovery through CAM.
-Steve Polyack
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[email protected]"
