Date: Fri, 6 Jan 2006 10:55:02 +0000 From: Scott Mitchell <scott+lists.freebsd@fishballoon.org> To: Michael Vince <mv@roq.com> Cc: freebsd-stable@freebsd.org Subject: Re: 6.0 on Dell 1850 with PERC4e/DC RAID? Message-ID: <20060106105501.GA19690@llama.fishballoon.org> In-Reply-To: <43BDD444.80509@roq.com> References: <20060105224150.GA991@tuatara.fishballoon.org> <43BDD444.80509@roq.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Jan 06, 2006 at 01:21:56PM +1100, Michael Vince wrote: > FYI there also has been a big update to the amr driver which claims to > dramatically increase performance among other things, interestingly > enought it was augmented by Yahoo, I can only assume they are moving to > Dell, yahoo for me (and now you :). > The updates are still in -current but it will be MFC'ed into stable > sooner or later. > > http://lists.freebsd.org/pipermail/cvs-src/2005-December/056814.html Yeah, I saw that, and it sounds most excellent. Good to see some real support from the likes of Dell and LSI, too. I might be able to get away with running -stable on this machine, but -current will be right out. Hopefully these changes can be MFCed in time for 6.1. Scott > Log: > Mega update to the LSI MegaRAID driver: > > 1. Implement a large set of ioctl shims so that the Linux management apps > from LSI will work. This includes infrastructure to support adding, > deleting > and rescanning arrays at runtime. This is based on work from Doug > Ambrosko, > heavily augmented by LSI and Yahoo. > > 2. Implement full 64-bit DMA support. Systems with more than 4GB of RAM > can now operate without the cost of bounce buffers. Cards that cannot do > 64-bit DMA will automatically revert to using bounce buffers. This option > can be forced off by setting the 'hw.amr.force_sg32" tunable in the loader. > It should only be turned off for debugging purposes. This work was > sponsored > by Yahoo. > > 3. Streamline the command delivery and interrupt handler paths after > much discussion with Dell and LSI. The logic now closely matches the > intended design, making it both more robust and much faster. Certain > i/o failures under heavy load should be fixed with this. > > 4. Optimize the locking. In the interrupt handler, the card can be > checked > for completed commands without any locks held, due to the handler being > implicitely serialized and there being no need to look at any shared data. > Only grab the lock to return the command structure to the free pool. A > small optimization can still be made to collect all of the completions > together and then free them together under a single lock. > > Items 3 and 4 significantly increase the performance of the driver. On an > LSI 320-2X card, transactions per second went from 13,000 to 31,000 in my > testing with these changes. However, these changes are still fairly > experimental and shouldn't be merged to 6.x until there is more testing. > > Thanks to Doug Ambrosko, LSI, Dell, and Yahoo for contributing towards > this. > > > > > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org" > -- =========================================================================== Scott Mitchell | PGP Key ID | "Eagles may soar, but weasels Cambridge, England | 0x54B171B9 | don't get sucked into jet engines" scott at fishballoon.org | 0xAA775B8B | -- Anon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060106105501.GA19690>