Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
I am struggling with my AR9285 for more than a year now. Sometimes it is better, sometimes worse, but never without disconnections. I have also noticed it dies more frequently on heavy usage. I read somewhere that raising value of kern.ipc.nmbclusters (in my case to 51200) could be of help, so I am trying it at the moment. -- Marko Cupać ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
On Mon, Aug 19, 2013 at 09:59:19AM +0200, Marko Cupać wrote: I am struggling with my AR9285 for more than a year now. Sometimes it is better, sometimes worse, but never without disconnections. I have also noticed it dies more frequently on heavy usage. I read somewhere that raising value of kern.ipc.nmbclusters (in my case to 51200) could be of help, so I am trying it at the moment. -- Marko Cupać Hmm, let me know how that goes, I'll probably try it too. How did you find the number '51200', and what does that value do? Also: Yea, I had used FreeBSD on this laptop a while back (back when current was version 9), back then it was basically unusable. Looks like you're right, it gets a little better and a little worse. -- Tj Hariharan Email: t...@archlinux.us pgpmgj2kuxXtQ.pgp Description: PGP signature
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
On Mon, 19 Aug 2013 14:46:01 +0530 Tj Hariharan t...@archlinux.us wrote: Hmm, let me know how that goes, I'll probably try it too. How did you find the number '51200', and what does that value do? I searched error message I was getting and found this thread: http://lists.freebsd.org/pipermail/freebsd-net/2009-August/022784.html I did not want to put the value blindly so i checked tuning: http://www.freebsd.org/doc/en_US.ISO8859-1/books/handbook/configtuning-kernel-limits.html It says Values between 4096 and 32768 are recommended for machines with greater amounts of memory. I had 25600 so I guessed I could double it and see how it goes. I am total layman, and am just sharing my experimentations. I am not sure if they will get us any improvements. What else can I do when there are 175 PRs currently open: http://lists.freebsd.org/pipermail/freebsd-wireless/2013-August/003769.html ...and 90% of those are related to ath. -- Marko Cupać ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. -- Andre ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
On 19.08.2013 05:40, Thomas Mueller wrote: cd devices: disk devices: disk0 BIOS drive A: disk0s1: Unknown disk1: BIOS drive C: disk2: BIOS drive D: disk2p1: FreeBSD boot disk2p2: FreeBSD UFS disk2p3: FreeBSD swap disk3: BIOS drive E: disk3p1: FreeBSD boot disk3p2: FreeBSD UFS disk3p3: FreeBSD swap pxe devices: OK Hello, can you try to install this loader? http://people.freebsd.org/~ae/loader -- WBR, Andrey V. Elsukov signature.asc Description: OpenPGP digital signature
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
On Mon, Aug 19, 2013 at 11:40:44AM +0200, Marko Cupać wrote: I am total layman, and am just sharing my experimentations. I am not sure if they will get us any improvements. What else can I do when there are 175 PRs currently open: http://lists.freebsd.org/pipermail/freebsd-wireless/2013-August/003769.html ...and 90% of those are related to ath. LOL...damn, I guess I should avoid ATH card for future laptop purchases. -- Tj Hariharan Email: t...@archlinux.us pgpQTK50STmBu.pgp Description: PGP signature
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
On Mon, Aug 19, 2013 at 11:15:32AM +0530, Tj Hariharan wrote: O never mind, it still happens, though obviously more intermittently, since I didn't notice anything odd for almost an entire day. A few more things this time though: a. It IS intermittent, there seems to be very little pattern to this, except that it seems to be more likely to happen when/if I am using the internet more and actively (e.g. youtube etc rather than just let a few small internet using things run). b. There seems to be an extra line in the error logs: Aug 19 10:53:47 tahoe dhclient[79063]: ioctl(SIOCGIFFLAGS) on wlan0: Operation not permitted On Sun, Aug 18, 2013 at 09:02:41AM -0700, Adrian Chadd wrote: good to know! -adrian On 18 August 2013 05:19, Tj Hariharan t...@archlinux.us wrote: Ok so, at the time I was using r254246. Just this afternoon, I realised there were quite a few commits after that. I am now on r25 and everything seems to be working fine, i.e. no more wlan0 dying randomly. I have no idea what is causing this, though. (the r254246 was from installing from a download of 9.2 dvd). On Sat, Aug 17, 2013 at 09:49:49PM -0700, Adrian Chadd wrote: Hi! I'm not sure what could've caused this! Not much has changed in the wireless stack and ath driver between 9.1 and 9.2. Would you be able to work through different svn versions of stable/9 between 9.1 and 9.2 to narrow down when things broke? It may be something other than the wifi driver/stack. Thanks! -adrian On 17 August 2013 05:12, Tj t...@archlinux.us wrote: (Sorry emailed from wrong address, re emailing) Hi, I just upgraded to 9.2-PRERELEASE from 9.1-RELEASE, I have not had this problem before with any version of freebsd however. I have an ATHEROS card (AR928X according to pciconf), things go fine except every few minutes/hours (randomly) I get the following http://bpaste.net/show/123755/ type of error, and the network is no longer connected, however, beyond the fact that I can't even reach my router there's no obvious other sign, I.e ifconfig still shows a valid output with ip address etc as if it were still connected. Restarting the netif service fixes it, until it happens again - which it does in a short while (though sometimes I have to restart netif twice). As I said, this happened just as I upgraded from 9.1 to 9.2. Anyone have any idea what's causing this? -Tj Hariharan ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org -- Tejas (Tj) Hariharan Email: t...@archlinux.us Okay it's gotten MUCH worse now. netif can no longer be stopped without a reboot when wlan0 craps out. (As I mentioned a restart usually fixes things). While trying to stop netif attempts to destroy the wlan0 interface, which fails - which, as it turns out is where the ioctl: operation not permitted error error comes from I think. -- Tj Hariharan Email: t...@archlinux.us pgpk73RtDBNjq.pgp Description: PGP signature
Re: status of autotuning freebsd for 9.2
On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. -- Andre ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
On Mon, Aug 19, 2013 at 10:26 AM, Alfred Perlstein alf...@ixsystems.comwrote: On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. So your saying, 9.2-RELEASE performance suffers degradation against say 9.1 ?? are you referring to with this patch enabled? or just in general 9.2-RELEASE -- Andre ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
Are you running the AR9285 on -HEAD? If not, upgrade. It should behave much, much better. -adrian On 19 August 2013 00:59, Marko Cupać marko.cu...@mimar.rs wrote: I am struggling with my AR9285 for more than a year now. Sometimes it is better, sometimes worse, but never without disconnections. I have also noticed it dies more frequently on heavy usage. I read somewhere that raising value of kern.ipc.nmbclusters (in my case to 51200) could be of help, so I am trying it at the moment. -- Marko Cupać ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
A lot of the ath PRs filed by me can be closed. They're reminders that things needed fixing, which I've done. A lot of them are for older cards on older machines with odd behaviour due to PCI/cardbus issues, power save bugs, ACPI hilarity, etc. I've tried to port over some fixes to address these but it's hard to verify them without a (much larger) lab and (a lot more) free time to test it all. Just remember - there's mostly just me working on this stuff.. -adrian On 19 August 2013 04:37, Tj Hariharan t...@archlinux.us wrote: On Mon, Aug 19, 2013 at 11:40:44AM +0200, Marko Cupać wrote: I am total layman, and am just sharing my experimentations. I am not sure if they will get us any improvements. What else can I do when there are 175 PRs currently open: http://lists.freebsd.org/pipermail/freebsd-wireless/2013-August/003769.html ...and 90% of those are related to ath. LOL...damn, I guess I should avoid ATH card for future laptop purchases. -- Tj Hariharan Email: t...@archlinux.us ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
Hi, Please just do it manually for now. # ifconfig wlan0 # ifconfig wlan0 create wlandev ath0 # wpa_supplicant -i wlan0 -c /etc/wpa_supplicant.conf # dhclient wlan0 .. see what happens. -adrian On 19 August 2013 06:30, Tj Hariharan t...@archlinux.us wrote: On Mon, Aug 19, 2013 at 11:15:32AM +0530, Tj Hariharan wrote: O never mind, it still happens, though obviously more intermittently, since I didn't notice anything odd for almost an entire day. A few more things this time though: a. It IS intermittent, there seems to be very little pattern to this, except that it seems to be more likely to happen when/if I am using the internet more and actively (e.g. youtube etc rather than just let a few small internet using things run). b. There seems to be an extra line in the error logs: Aug 19 10:53:47 tahoe dhclient[79063]: ioctl(SIOCGIFFLAGS) on wlan0: Operation not permitted On Sun, Aug 18, 2013 at 09:02:41AM -0700, Adrian Chadd wrote: good to know! -adrian On 18 August 2013 05:19, Tj Hariharan t...@archlinux.us wrote: Ok so, at the time I was using r254246. Just this afternoon, I realised there were quite a few commits after that. I am now on r25 and everything seems to be working fine, i.e. no more wlan0 dying randomly. I have no idea what is causing this, though. (the r254246 was from installing from a download of 9.2 dvd). On Sat, Aug 17, 2013 at 09:49:49PM -0700, Adrian Chadd wrote: Hi! I'm not sure what could've caused this! Not much has changed in the wireless stack and ath driver between 9.1 and 9.2. Would you be able to work through different svn versions of stable/9 between 9.1 and 9.2 to narrow down when things broke? It may be something other than the wifi driver/stack. Thanks! -adrian On 17 August 2013 05:12, Tj t...@archlinux.us wrote: (Sorry emailed from wrong address, re emailing) Hi, I just upgraded to 9.2-PRERELEASE from 9.1-RELEASE, I have not had this problem before with any version of freebsd however. I have an ATHEROS card (AR928X according to pciconf), things go fine except every few minutes/hours (randomly) I get the following http://bpaste.net/show/123755/ type of error, and the network is no longer connected, however, beyond the fact that I can't even reach my router there's no obvious other sign, I.e ifconfig still shows a valid output with ip address etc as if it were still connected. Restarting the netif service fixes it, until it happens again - which it does in a short while (though sometimes I have to restart netif twice). As I said, this happened just as I upgraded from 9.1 to 9.2. Anyone have any idea what's causing this? -Tj Hariharan ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org -- Tejas (Tj) Hariharan Email: t...@archlinux.us Okay it's gotten MUCH worse now. netif can no longer be stopped without a reboot when wlan0 craps out. (As I mentioned a restart usually fixes things). While trying to stop netif attempts to destroy the wlan0 interface, which fails - which, as it turns out is where the ioctl: operation not permitted error error comes from I think. -- Tj Hariharan Email: t...@archlinux.us ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: [ATH] 9.2-PRERELEASE and wlan0 device disconnection
Ok it's gotten worse now. I can no longer restart netif, it just hangs there in uninterruptible wait forever (trying to delete the wlan0 interface using ifconfig) On Mon, Aug 19, 2013 at 09:59:19AM +0200, Marko Cupać wrote: I am struggling with my AR9285 for more than a year now. Sometimes it is better, sometimes worse, but never without disconnections. I have also noticed it dies more frequently on heavy usage. I read somewhere that raising value of kern.ipc.nmbclusters (in my case to 51200) could be of help, so I am trying it at the moment. -- Marko Cupać Hmm, let me know how that goes, I'll probably try it too. How did you find the number '51200', and what does that value do? Also: Yea, I had used FreeBSD on this laptop a while back (back when current was version 9), back then it was basically unusable. Looks like you're right, it gets a little better and a little worse. -- Tj Hariharan Email: t...@archlinux.us ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
Performance is bad for large memory requirements period. Vnodes and mbufs on a machine with 24gb ram is limited to the same amount as a machine with less than 4GB ram. This was fixed in head but not merged back in time. This results in poor out of the box performance on 10gige and servers with high vnode requirements. Sent from my iPhone On Aug 19, 2013, at 7:30 AM, Outback Dingo outbackdi...@gmail.com wrote: On Mon, Aug 19, 2013 at 10:26 AM, Alfred Perlstein alf...@ixsystems.com wrote: On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. So your saying, 9.2-RELEASE performance suffers degradation against say 9.1 ?? are you referring to with this patch enabled? or just in general 9.2-RELEASE -- Andre ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
On Mon, Aug 19, 2013 at 12:05 PM, Alfred Perlstein alf...@ixsystems.comwrote: Performance is bad for large memory requirements period. Vnodes and mbufs on a machine with 24gb ram is limited to the same amount as a machine with less than 4GB ram. This was fixed in head but not merged back in time. is there a patch set i can backport on my own, do we know what revision(s) are required? Ive got boxes with 128GB and 10Gbe Intel... so im willing to do some work.. This results in poor out of the box performance on 10gige and servers with high vnode requirements. Sent from my iPhone On Aug 19, 2013, at 7:30 AM, Outback Dingo outbackdi...@gmail.com wrote: On Mon, Aug 19, 2013 at 10:26 AM, Alfred Perlstein alf...@ixsystems.comwrote: On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. So your saying, 9.2-RELEASE performance suffers degradation against say 9.1 ?? are you referring to with this patch enabled? or just in general 9.2-RELEASE -- Andre ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
On 19.08.2013 18:09, Outback Dingo wrote: On Mon, Aug 19, 2013 at 12:05 PM, Alfred Perlstein alf...@ixsystems.com mailto:alf...@ixsystems.com wrote: Performance is bad for large memory requirements period. Vnodes and mbufs on a machine with 24gb ram is limited to the same amount as a machine with less than 4GB ram. This was fixed in head but not merged back in time. is there a patch set i can backport on my own, do we know what revision(s) are required? Ive got boxes with 128GB and 10Gbe Intel... so im willing to do some work.. I have committed it to 9-stable this morning with r254515. No backporting necessary. -- Andre This results in poor out of the box performance on 10gige and servers with high vnode requirements. Sent from my iPhone On Aug 19, 2013, at 7:30 AM, Outback Dingo outbackdi...@gmail.com mailto:outbackdi...@gmail.com wrote: On Mon, Aug 19, 2013 at 10:26 AM, Alfred Perlstein alf...@ixsystems.com mailto:alf...@ixsystems.com wrote: On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org mailto:an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. So your saying, 9.2-RELEASE performance suffers degradation against say 9.1 ?? are you referring to with this patch enabled? or just in general 9.2-RELEASE -- Andre ___ freebsd-stable@freebsd.org mailto:freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org mailto:freebsd-stable-unsubscr...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
On Mon, Aug 19, 2013 at 12:17 PM, Andre Oppermann an...@freebsd.org wrote: On 19.08.2013 18:09, Outback Dingo wrote: On Mon, Aug 19, 2013 at 12:05 PM, Alfred Perlstein alf...@ixsystems.com mailto:alf...@ixsystems.com wrote: Performance is bad for large memory requirements period. Vnodes and mbufs on a machine with 24gb ram is limited to the same amount as a machine with less than 4GB ram. This was fixed in head but not merged back in time. is there a patch set i can backport on my own, do we know what revision(s) are required? Ive got boxes with 128GB and 10Gbe Intel... so im willing to do some work.. I have committed it to 9-stable this morning with r254515. No backporting necessary. Okay so wait, your saying the autotune commit this morning resolves Alfreds claims of abysmal performance in general, or is there other additional fixes in head aside from the autotune hes mentioning -- Andre This results in poor out of the box performance on 10gige and servers with high vnode requirements. Sent from my iPhone On Aug 19, 2013, at 7:30 AM, Outback Dingo outbackdi...@gmail.com mailto:outbackdi...@gmail.com** wrote: On Mon, Aug 19, 2013 at 10:26 AM, Alfred Perlstein alf...@ixsystems.com mailto:alf...@ixsystems.com wrote: On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org mailto:an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. So your saying, 9.2-RELEASE performance suffers degradation against say 9.1 ?? are you referring to with this patch enabled? or just in general 9.2-RELEASE -- Andre __**_ freebsd-stable@freebsd.org mailto:freebsd-stable@**freebsd.orgfreebsd-stable@freebsd.org mailing list http://lists.freebsd.org/**mailman/listinfo/freebsd-**stablehttp://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscribe@** freebsd.org freebsd-stable-unsubscr...@freebsd.org mailto:freebsd-stable-**unsubscr...@freebsd.orgfreebsd-stable-unsubscr...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
RE: status of autotuning freebsd for 9.2
-Original Message- From: owner-freebsd-sta...@freebsd.org [mailto:owner-freebsd-sta...@freebsd.org] On Behalf Of Alfred Perlstein Sent: Tuesday, 20 August 2013 2:05 AM To: Outback Dingo Cc: r...@freebsd.org; sta...@freebsd.org; Andre Oppermann; nones...@longcount.org Subject: Re: status of autotuning freebsd for 9.2 Performance is bad for large memory requirements period. Vnodes and mbufs on a machine with 24gb ram is limited to the same amount as a machine with less than 4GB ram. This was fixed in head but not merged back in time. This results in poor out of the box performance on 10gige and servers with high vnode requirements. Sent from my iPhone On Aug 19, 2013, at 7:30 AM, Outback Dingo outbackdi...@gmail.com wrote: On Mon, Aug 19, 2013 at 10:26 AM, Alfred Perlstein alf...@ixsystems.com wrote: On Aug 19, 2013, at 2:52 AM, Andre Oppermann an...@freebsd.org wrote: On 16.08.2013 10:29, Andre Oppermann wrote: On 16.08.2013 08:32, Alfred Perlstein wrote: Andre, I'm kind of bummed out this didn't make it into 9.2, I'm wondering can I commit this to 9-stable now? (or is it already in?) It didn't make it because there was only sparse feedback after the call for testers. There were a couple of replies that it is being tested but no statements either way if it was good or not. Hence I erred on the side of caution and refrained from committing it. Revisiting the history of this after vacation absence actually shows that we straddled the release code freeze deadline and you had provided good testing feedback. However the MFC got rejected by RE on the fear of introducing unknown regressions into the release process. Would you do the honors? Yes, will do later today. Committed to stable/9 as r254515. Let me know if there are any issues. Thanks Andre. Maybe we can do a point release/patch release with this in a few weeks for 9.2.1 or 9.2p1 because 9.2 out of the box performance is abysmal not only in networking but also disk as maxvnodes is clipped way too small even with plenty of ram. So your saying, 9.2-RELEASE performance suffers degradation against say 9.1 ?? are you referring to with this patch enabled? or just in general 9.2-RELEASE -- Andre ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org It might be relevant that there were performance changes to nullfs (caching) code back in January and updated in May by Kib. Because I use jails and nullfs extensively, the nullfs enhancement demanded an increase in maxvodes, otherwise performance degraded, quite badly. Tripling the default suited my needs on 4GB systems, but I don't have an algorithmic recommendation; as for me it depends on the role/purpose of the server. If vnodes is an issue *and* you use mount_nullfs, another approach is to disable caching via mount_nullfs -o nocache as this may help to narrow the cause. Ref: http://svnweb.freebsd.org/base/stable/9/sys/fs/nullfs/null_subr.c?view=log http://lists.freebsd.org/pipermail/svn-src-stable-9/2013-May/004531.html And thank-you for your work on http://lists.freebsd.org/pipermail/svn-src-stable-9/2013-August/005307.html Regards, Dewayne. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: status of autotuning freebsd for 9.2
On 8/19/13 9:19 AM, Outback Dingo wrote: On Mon, Aug 19, 2013 at 12:17 PM, Andre Oppermann an...@freebsd.org mailto:an...@freebsd.org wrote: On 19.08.2013 18:09, Outback Dingo wrote: On Mon, Aug 19, 2013 at 12:05 PM, Alfred Perlstein alf...@ixsystems.com mailto:alf...@ixsystems.com mailto:alf...@ixsystems.com mailto:alf...@ixsystems.com wrote: Performance is bad for large memory requirements period. Vnodes and mbufs on a machine with 24gb ram is limited to the same amount as a machine with less than 4GB ram. This was fixed in head but not merged back in time. is there a patch set i can backport on my own, do we know what revision(s) are required? Ive got boxes with 128GB and 10Gbe Intel... so im willing to do some work.. I have committed it to 9-stable this morning with r254515. No backporting necessary. Okay so wait, your saying the autotune commit this morning resolves Alfreds claims of abysmal performance in general, Yes. or is there other additional fixes in head aside from the autotune hes mentioning Well of course head has cool code, but this was a big problem. -Alfred ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
I can repeat (again) what uname -a shows: FreeBSD amelia2 9.2-PRERELEASE FreeBSD 9.2-PRERELEASE #17 r254196: Sun Aug 11 00:36:49 UTC 2013 root@amelia2:/usr/obj/usr/src/sys/SANDY amd64 Hello, can you try to install this loader? http://people.freebsd.org/~ae/loader WBR, Andrey V. Elsukov I just downloaded it, saving as loaderae, using your email username and initials as a suffix. I assume loader works under a different name? I can use kfreebsd/loaderae instead of kfreebsd /boot/loader, and loaderae will be preserved over the next update from source. Then I will want to test the new /boot/loader which might possibly work right with kfreebsd. Or maybe I will have a newer kfreebsd. Tom ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
[sending this from hub since bellsouth.net doesn't seem to like my `normal' mailserver...] On Mon, Aug 19, 2013 at 07:30:16PM +, Thomas Mueller wrote: I can repeat (again) what uname -a shows: FreeBSD amelia2 9.2-PRERELEASE FreeBSD 9.2-PRERELEASE #17 r254196: Sun Aug 11 00:36:49 UTC 2013 root@amelia2:/usr/obj/usr/src/sys/SANDY amd64 Hello, can you try to install this loader? http://people.freebsd.org/~ae/loader WBR, Andrey V. Elsukov I just downloaded it, saving as loaderae, using your email username and initials as a suffix. I assume loader works under a different name? I can use kfreebsd/loaderae instead of kfreebsd /boot/loader, and loaderae will be preserved over the next update from source. Then I will want to test the new /boot/loader which might possibly work right with kfreebsd. Or maybe I will have a newer kfreebsd. ..so you probably never saw my post about the updated super grub disk iso: http://lists.freebsd.org/pipermail/freebsd-stable/2013-August/074711.html I.e. they fixed the kfreebsd misspelling and the grub 2.00 bug that prevented it from booting a 9.1+ kernel directly, so the autodetection now has better chances of working. (They even added loader to the autodetection so you can also `e'dit that entry and change loader to loaderae to test this.) HTH, :) Juergen ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
..so you probably never saw my post about the updated super grub disk iso: http://lists.freebsd.org/pipermail/freebsd-stable/2013-August/074711.html I.e. they fixed the kfreebsd misspelling and the grub 2.00 bug that prevented it from booting a 9.1+ kernel directly, so the autodetection now has better chances of working. (They even added loader to the autodetection so you can also `e'dit that entry and change loader to loaderae to test this.) HTH, :) Juergen I remember that message you refer to but thought the bug was not fixed yet in Super Grub Disk. How would I make it into something like a giant floppy image that can be booted from syslinux or isolinux like the Super Grub Disk on the System Rescue CD? I could also try something by building grub2 from FreeBSD ports, don't know just what booting images I can create. Tom ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
I can repeat (again) what uname -a shows: FreeBSD amelia2 9.2-PRERELEASE FreeBSD 9.2-PRERELEASE #17 r254196: Sun Aug 11 00:36:49 UTC 2013 root@amelia2:/usr/obj/usr/src/sys/SANDY amd64 Hello, can you try to install this loader? http://people.freebsd.org/~ae/loader WBR, Andrey V. Elsukov I just downloaded it, saving as loaderae, using your email username and initials as a suffix. I assume loader works under a different name? I can use kfreebsd/loaderae instead of kfreebsd /boot/loader, and loaderae will be preserved over the next update from source. Then I will want to test the new /boot/loader which might possibly work right with kfreebsd. Or maybe I will have a newer kfreebsd. Update: Actually there was a typo above: I meant kfreebsd /boot/loaderae and not kfreebsd/loaderae. Anyway, I tried kfreebsd /boot/loaderae and got the same thing as with kfreebsd /boot/loader was taken to a loader prompt where I could not access any files on the hard disk. So again I had to reboot, this time from the USB stick and at the loader prompt typed set boot_askname Tom ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
On 20.08.2013 06:58, Thomas Mueller wrote: was taken to a loader prompt where I could not access any files on the hard disk. Was the output of lsdev command the same or something changed? So again I had to reboot, this time from the USB stick and at the loader prompt typed set boot_askname -- WBR, Andrey V. Elsukov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Change in loader or kernel: won't boot with kfreebsd in grub2
On 20.08.2013 06:58, Thomas Mueller wrote: was taken to a loader prompt where I could not access any files on the hard disk. Was the output of lsdev command the same or something changed? So again I had to reboot, this time from the USB stick and at the loader prompt typed set boot_askname WBR, Andrey V. Elsukov Only difference in lsdev output was that the USB sticks didn't show, but that was because I had removed them. I reinserted the USB sticks, but they still didn't show, probably because the loader presumably does not recognize newly inserted USB sticks. I then typed reboot and successfully rebooted from the appropriate USB stick. Tom ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Update to 9.2-PRERELEASE, what is this?
On Sun, Aug 18, 2013 at 3:43 PM, Warren Block wbl...@wonkity.com wrote: On Sun, 18 Aug 2013, David Demelier wrote: http://files.malikania.fr/DSC_0223.jpg What's that? Is this a joke? Yes, sort of. This is fantastic. Kudos and thanks for the laugh to whoever snuck it in there. After you're tired of it, override it in /boot/loader.conf: loader_logo=orb A PR should probably be entered to correct /boot/defaults/loader.conf. What do we set as loader_logo to change it back once this has been fixed? This probably isn't really orbbw, but it needs to stick around as an easter egg for the life of 9.2. Thanks! ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: NFS deadlock on 9.2-Beta1
On Thu, Aug 15, 2013 at 5:39 PM, Rick Macklem rmack...@uoguelph.ca wrote: Have you been able to pass the debugging info on to Kostik? It would be really nice to get this fixed for FreeBSD9.2. You're probably not talking to me, but headway here is slow. At our location, we have been continuing to test releng/9.2 extensively, but with r250907 reverted. Since reverting it solves the issue, and since there haven't been any further changes to releng/9.2 that might also resolve this issue, re-applying r250907 is perceived here as un-fixing a problem. Enthusiasm for doing so is correspondingly low, even if the purpose is to gather debugging info. :( However, after finally having clearance to test releng/9.2 r254540 with r250907 included and with DDB on five nodes. The problem cropped up in about an hour. Two threads in one process deadlocked, was perfect. Got it into DDB and saw the stack trace was scrolling off so there was no way to copy it by hand. Also, the machine's disk is smaller than physical RAM, so no dump file. :( Here's what is available so far: db show proc 33362 Process 33362 (httpd) at 0xcd225b50: state: NORMAL uid: 25000 gids: 25000 parent: pid 25104 at 0xc95f92d4 ABI: FreeBSD ELF32 arguments: /usr/local/libexec/httpd threads: 3 100405 D newnfs 0xc9b875e4 httpd 100393 D pgrbwt 0xc43a30c0 httpd 100755 S uwait 0xc84b7c80 httpd Not much to go on. :( Maybe these five can be configured with serial consoles. So, inquiries are continuing, but the answer to does this still happen on 9.2-RC2? is definitely yes. Thanks! ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org