NFS attr cache performance
Im looking for deep hacks into what I could do to make the 6.x NFS client hold a larger (or much larger) file/directory attribute cache. In very large make everything environments with Fbsd, we are about 1/3rd the speed of local disk coming from a very large Netapp box. The same make from a heavily patched/modified Linux NFS client is miles faster than local disk. I have no insight to the Linux modifications, but looking at the nfsstats, attribute calls are the bulk of the traffic to the NFS mounted file system. Any and all ideas are OK..maybe something simple I overlooked. I need to reserve another build server early this week, and go over my options again on whats not been working, and get the list numbers as well. Thanks in advance. ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: NFS attr cache performance
I will do that, thanks! On Mon, 30 Oct 2006, Eric Anderson wrote: On 10/29/06 22:31, Geoff Mohler wrote: Im looking for deep hacks into what I could do to make the 6.x NFS client hold a larger (or much larger) file/directory attribute cache. In very large make everything environments with Fbsd, we are about 1/3rd the speed of local disk coming from a very large Netapp box. The same make from a heavily patched/modified Linux NFS client is miles faster than local disk. I have no insight to the Linux modifications, but looking at the nfsstats, attribute calls are the bulk of the traffic to the NFS mounted file system. Any and all ideas are OK..maybe something simple I overlooked. I need to reserve another build server early this week, and go over my options again on whats not been working, and get the list numbers as well. Thanks in advance. See Bruce Evans very recent work on this on freebsd-fs@ mailing list. Eric -- Eric AndersonSr. Systems AdministratorCentaur Technology Anything that works is better than anything that doesn't. ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to [EMAIL PROTECTED]
Cannot upgrade 4.11-RELEASE #0
I am trying to upgrade via buildworld my 4.11-RELEASE #0 system, and I am running into a few key errors. First, I am updated in my cvsup, here is my config file: *default host=cvsup3.freebsd.org compress *default base=/usr *default prefix=/usr *default release=cvs *default delete use-rel-suffix *default tag=. src-all When I do a buiuldworld, I get a pile of these: /usr/src/usr.bin/make/globals.h:49: stdint.h: No such file or directory My /etc/make.conf includes COMPAT3X and 4X as found in a number of google searches related to this. Just not sure where to go next.. Im trying to update this machine remotely, and my KEY issue is that Imagemagik wont install, oddly with the same stdint.h error(s). Ideas? --- Sixty-six per cent of people currently do not approve of the way that Bush is handling the war. The other 34 per cent believe that Adam and Eve rode around naked on Dinosaurs. -Tina Fey, SNL ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Cannot upgrade 4.11-RELEASE #0
Ok..thanks for the proper kick. :) On Sun, 27 Nov 2005, Kris Kennaway wrote: On Sun, Nov 27, 2005 at 04:47:26PM -0600, Geoff Mohler wrote: I am trying to upgrade via buildworld my 4.11-RELEASE #0 system, and I am running into a few key errors. First, I am updated in my cvsup, here is my config file: *default host=cvsup3.freebsd.org compress *default base=/usr *default prefix=/usr *default release=cvs *default delete use-rel-suffix *default tag=. src-all When I do a buiuldworld, I get a pile of these: /usr/src/usr.bin/make/globals.h:49: stdint.h: No such file or directory You can't update from 4.11 to 7.0 in that way. You have to at least go through 5.x first. If you wanted to do something else like update to 4.11-STABLE, your cvsupfile is wrong. Kris --- Sixty-six per cent of people currently do not approve of the way that Bush is handling the war. The other 34 per cent believe that Adam and Eve rode around naked on Dinosaurs. -Tina Fey, SNL ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to [EMAIL PROTECTED]
Enopugh..Re: You've Been Added!
Open mailing lists..regardless of how informative they are, are just too annoying to belong to anymore. To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Odd ftp.freebsd.org question..
Whats the current limint on how many concurrent connections the main ftp site can chew on? Trying to size up some hardware..and Id like to use what ya you use there as a guide. To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: 4.5-RELEASE upgrade..didnt??
No, I didnt. Thanks! Will do that and report back. On Tue, 5 Mar 2002, Kenneth Culver wrote: did u do a config -r on your kernel config file? if not it might not pick up some of the new stuff. Ken On Mon, 4 Mar 2002, Geoff Mohler wrote: Ok..dumb question alert. (fair warning) I just did a 4.3 to 4.5 upgrade, and made sure the sys source was upgraded as well. Went in, and did a make on my config file from 4.3..and rebooted (made sure the new kernel was in / as well). Uname reports a 4.3 system..etc..etc..etc. What'd I miss? To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: 4.5-RELEASE upgrade..didnt??
No, still have this from uname -a: 4.3-RELEASE FreeBSD 4.3-RELEASE #3: On Tue, 5 Mar 2002, Kenneth Culver wrote: did u do a config -r on your kernel config file? if not it might not pick up some of the new stuff. Ken On Mon, 4 Mar 2002, Geoff Mohler wrote: Ok..dumb question alert. (fair warning) I just did a 4.3 to 4.5 upgrade, and made sure the sys source was upgraded as well. Went in, and did a make on my config file from 4.3..and rebooted (made sure the new kernel was in / as well). Uname reports a 4.3 system..etc..etc..etc. What'd I miss? To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
4.5-RELEASE upgrade..didnt??
Ok..dumb question alert. (fair warning) I just did a 4.3 to 4.5 upgrade, and made sure the sys source was upgraded as well. Went in, and did a make on my config file from 4.3..and rebooted (made sure the new kernel was in / as well). Uname reports a 4.3 system..etc..etc..etc. What'd I miss? To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Next 4.x release timeframe?
What is the next 4.x release schedule looking like? Cant wait to employ the large # of NFS related patches once theyre ready for prime time. Thanks! --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Next 4.x release timeframe?
Yes, exactly..thanks Bruce. ;^) On Wed, 23 Jan 2002, Bruce A. Mah wrote: If memory serves me right, Geoff Mohler wrote: What is the next 4.x release schedule looking like? You mean 4.5-RELEASE, which, barring some unforeseen problems, will be released later this week? :-) http://www.freebsd.org/internal/releng45.html (Typically, releases happen about every four months, so you can extrapolate from that.) Bruce. --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: NFS: How to make FreeBSD fall on its face in one easy step
Matt didnt feel the fixes were primarily performance related, just bug fixes. On Thu, 13 Dec 2001, Mike Silbersack wrote: On Wed, 12 Dec 2001, Matthew Dillon wrote: :I suppose while were on the topic.. : :Are there any hidden secrets to eeking out more performance from the BSD :NFS client (other than version types and the normal fstab tweaks). : :Im the CS Labs manager at NetApp..and Im always trying to store away a :secret here or there when someone comes to me with a problem in the field. : :FreeBSD since v2..rock on! For extreme performance there are some zero-copy patches floating around which have not been integrated into the main tree. Generally, though, your NFS performance is going to be ultimately limited by your server's disk performance. -Matt Matthew Dillon And if you hadn't heard, Matt just fixed a couple of bugs in the tcp stack which improves NFS greatly. It sounds like after this round of NFS fixes, the first answer to NFS questions should be: Upgrade to 4.5! Mike Silby Silbersack --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: NFS: How to make FreeBSD fall on its face in one easy step
For some people, the overhead is an acceptible tradeoff to redundancy. Ever since Cisco released thier 6500 10/100 blades that to crappy buffering between a Gigabit NFS server (could be anything, just an example) and an 100Mbit client, people have somewhat been adding that overhead to thier CPU and data-rate budgets as acceptable losses. On Thu, 13 Dec 2001, Dan Nelson wrote: In the last episode (Dec 13), Mike Silbersack said: On Wed, 12 Dec 2001, Matthew Dillon wrote: Geoff Mohler wrote: :Are there any hidden secrets to eeking out more performance from :the BSD NFS client (other than version types and the normal fstab :tweaks). And if you hadn't heard, Matt just fixed a couple of bugs in the tcp stack which improves NFS greatly. It sounds like after this round of NFS fixes, the first answer to NFS questions should be: Upgrade to 4.5! I don't even bother with TCP mounts; my default amd rule says proto=udp. Is there any reason to add the overhead of the TCP stack if you're not leaving your own ethernet? You should be able to easily saturate a 100mbit link with FreeBSD 4.* machines, and I can do 15-20MB/sec with Netgear GA620 gigabit nics (SMP 2 x pIII/600). -- Dan Nelson [EMAIL PROTECTED] --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Found NFS data corruption bug... (was Re: NFS: How to makeFreeBSD fall on its face in one easy step )
); /* + * XXX work around SMP data integrity race + * by unmapping the page from user processes. + * The garbage we just cleared may be mapped + * to a user process running on another cpu + * and this code is not running through normal + * I/O channels which handle SMP issues for + * us, so unmap page to synchronize all cpus. + * + * XXX should vm_pager_unmap_page() have + * dealt with this? + */ + vm_page_protect(m, VM_PROT_NONE); + + /* * Clear out partial-page dirty bits. This * has the side effect of setting the valid * bits, but that is ok. There are a bunch To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: NFS: How to make FreeBSD fall on its face in one easy step
I suppose while were on the topic.. Are there any hidden secrets to eeking out more performance from the BSD NFS client (other than version types and the normal fstab tweaks). Im the CS Labs manager at NetApp..and Im always trying to store away a secret here or there when someone comes to me with a problem in the field. FreeBSD since v2..rock on! To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: FreeBSD performing worse than Linux?
Dont forget the latencies introduced by routing hardware..Id not expect the average DSL modem to be to snappy about its internal packet forwarding performance. http://rescomp.stanford.edu/~cheshire/rants/Latency.html Thats a good read On Thu, 29 Nov 2001, Leo Bicknell wrote: On Fri, Nov 30, 2001 at 03:23:45AM +0100, Pierre Beyssac wrote: I can't reproduce this result, 16K fills a T1 for 11 ms, which is 22000 km (at 2/3 of light speed), enough to get halfway round the earth... Your math is a little funny. 4000 km New York to LA c = 300,000 km/sec Speed of light in fiber, approximately .66 c, or 198,000 km/sec. Approximate sum of buffering + serialization delay in the network, is a 15% penalty, or 168,300 kph. total speed. 4000 km one way == 8000 km two way, 8000 / 168300 = 47ms in my book, theoretial optimum. With an RTT of 47ms, you can move 16k per RTT, or or about 340k/sec. * If you find a cross country RTT of 47 ms I'll personally send you $20. around 60-65 is normal for good circuits, and 70-90 is not wholely unusual. * The 340k/sec assumes perfect network conditions, that is no dropped or delayed packets. Please search the archives. There are reams of information about this. -- Leo Bicknell - [EMAIL PROTECTED] - CCIE 3440 PGP keys at http://www.ufp.org/~bicknell/ Read TMBG List - [EMAIL PROTECTED], www.tmbg.org To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: multi-disk file systems on FreeBSD?
vinum..duh..sorry guys. My brain kicked out ccd before I could look it up. On Wed, 28 Nov 2001, Michael Lucas wrote: man 8 vinum On Wed, Nov 28, 2001 at 12:48:48PM -0500, Dan Ellard wrote: Are there a way under FreeBSD to build a file system using more than one special file? For example, I have a machine with three 9G SCSI disks, and I'd like to build a 27G file system by combining them. Thanks, -Dan To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message -- Michael Lucas [EMAIL PROTECTED] http://www.blackhelicopters.org/~mwlucas/ Big Scary Daemons: http://www.oreillynet.com/pub/q/Big_Scary_Daemons To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Intel gigabit driver
Yay..stable jumbo frames! :^) On Wed, 28 Nov 2001, Prafulla Deuskar wrote: All, Intel Corporation has released a gigabit driver for PRO/1000 series of adapters. The driver is available for download from the following url: http://appsr.intel.com/scripts-df/Product_Filter.asp?ProductID=415 The driver will be committed to -CURRENT first and MFC'ed to -STABLE later. Thanks, Prafulla To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: help
Uhh..with what? On Tue, 27 Nov 2001, Andrey Pugachev wrote: help To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Unix Philosophers Please!
On Wed, 31 Oct 2001, Brian Reichert wrote: On Wed, Oct 31, 2001 at 03:02:59PM -0600, Nicpon, John wrote: Please specifically define where data goes that is sent to /dev/null How 'specific' are you trying to get? /dev/null is a pseudo-device to which writes never fail. What question are you _really_ trying to ask? -- Brian 'you Bastard' Reichert [EMAIL PROTECTED] 37 Crystal Ave. #303 Daytime number: (603) 434-6842 Derry NH 03038-1713 USA Intel architecture: the left-hand path To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- Geoff Mohler To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
-Stable installation...
Whats a good reference guide on how to install a -STABLE release? Thanks. --- *** *New Improved: http://www.speedtoys.com * *** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: wx0 jumbo frame support explosions..
FreeBSD speedracer.speedtoys.com 4.3-RELEASE FreeBSD 4.3-RELEASE #3: On Thu, 19 Jul 2001, Matthew Jacob wrote: Finally following up on this... was this with -current or -stable? On Mon, 9 Jul 2001, Geoff Mohler wrote: When I enable jumbo frames in /usr/src/sys/pci.if_wx.c, and then set it via 'ifconfig wx0 mtu 9000' once the new kernel is booted..my system immediately goes zonkers...not even healthy enough to log. Just kernel panic and reboot. Idears? --- ** *New Improved: http://www.speedtoys.com* ** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- *** *New Improved: http://www.speedtoys.com * *** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: wx0 jumbo frame support explosions..
It would crash when I forced the large MTU size when already running at the default MTU size. I would reconfig the Netapp box to jumbo, then ifconfig up the wx0 interface..bang crash. On Thu, 19 Jul 2001, Matthew Jacob wrote: Ah. Well, it doesn't crash in FreeBSD-current. It doesn't work well *either*, but I'm curious- was wx0 resident or was it kldload'ed by the ifconfig? -matt On Thu, 19 Jul 2001, Geoff Mohler wrote: FreeBSD speedracer.speedtoys.com 4.3-RELEASE FreeBSD 4.3-RELEASE #3: On Thu, 19 Jul 2001, Matthew Jacob wrote: Finally following up on this... was this with -current or -stable? On Mon, 9 Jul 2001, Geoff Mohler wrote: When I enable jumbo frames in /usr/src/sys/pci.if_wx.c, and then set it via 'ifconfig wx0 mtu 9000' once the new kernel is booted..my system immediately goes zonkers...not even healthy enough to log. Just kernel panic and reboot. Idears? --- ** *New Improved: http://www.speedtoys.com* ** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- *** *New Improved: http://www.speedtoys.com * *** --- *** *New Improved: http://www.speedtoys.com * *** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
wx0 jumbo frame support explosions..
When I enable jumbo frames in /usr/src/sys/pci.if_wx.c, and then set it via 'ifconfig wx0 mtu 9000' once the new kernel is booted..my system immediately goes zonkers...not even healthy enough to log. Just kernel panic and reboot. Idears? --- ** *New Improved: http://www.speedtoys.com* ** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: wx0 jumbo frame support explosions..
Yay. :^) Timeframe? On Tue, 10 Jul 2001, Matthew Jacob wrote: Not debugged yet. On Mon, 9 Jul 2001, Geoff Mohler wrote: When I enable jumbo frames in /usr/src/sys/pci.if_wx.c, and then set it via 'ifconfig wx0 mtu 9000' once the new kernel is booted..my system immediately goes zonkers...not even healthy enough to log. Just kernel panic and reboot. Idears? --- ** *New Improved: http://www.speedtoys.com* ** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message --- ** *New Improved: http://www.speedtoys.com* ** To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message