Re: 9-STABLE, ZFS, NFS, ggatec - suspected memory leak
On 4/1/12 3:31 PM, Oliver Brandmueller wrote: Philip: Are you using: - another file system (like UFS/FFS for the system or similar?) - ZFS snapshots - ZFS send on the system? Can you also see the NAMEI growth? The system is 100% zfs. zmirror for the os (2 disks) zmysqlL(zmirror) for mysql logs (2disks +1 cache(ssd)) zmysqlD(raidz2) for mysql data (11 disks + 1cache(ssd) +1zil(ssd)) No snapshots No zfs send/recv, but there might be in the future. I have not charted NAMEI growth, but I can try it monday I think. -- 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Philip M. Gollucci (pgollu...@p6m7g8.com) c: 703.336.9354 Member, Apache Software Foundation Committer,FreeBSD Foundation Consultant, P6M7G8 Inc. Director Operations, Ridecharge Inc. Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. ___ 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: 9-STABLE, ZFS, NFS, ggatec - suspected memory leak
http://lists.freebsd.org/pipermail/freebsd-questions/2012-March/239643.html Same issue different thread. Different software. Its not NFS, its ZFS. I don't really have a place to try it on 8.2, but my hunch from things I've done rather similarly which don't cause tell me its a new issue in 9.0, though I won't swear by that. On 03/30/12 08:38, Oliver Brandmueller wrote: > Hi all, > > Setup: > > I'm running 2 machines (amd64, 16GB) with FreeBSD 9-STABLE (Mar 14 so > far) acting as NFS servers. They each serve 3 zpools (holding a single > zfs, hourly snapshots). The zpools each are 3-way mirrors of ggate > devices, each 2 TB, so 2 TB per zpool. Compression is "on" (to save > bandwith to the backend, compressratio around 1.05 to 1.15), atime is > off. > > There is no special tuning in loader.conf (except I tried to limit ZFS > ARC to 8GB lately, which doesn't change a lot). sysctl.conf has: > > kern.ipc.maxsockbuf=33554432 > net.inet.tcp.sendspace=8388608 > net.inet.tcp.recvspace=8388608 > kern.maxfiles=64000 > vfs.nfsd.maxthreads=254 > > Without the first three zfs+ggate goes bad after a short time (checksum > errors, stall), the latter are mainly for NFS and some regular local > cleanup stuff. > > The machines have 4 em and 2 igb network interfaces. 3 of the are > dedicated links (with no switches) to the ggate servers, one is a > dedicated link to a third machine which gets feeded with incremental > snapshots by ZFS send (as backup and fallaback of last resort), one > interface for management tasks and one to an internal network with the > NFS clients. > > The NFS clients are mostly FreeBSD 6, 7 and 9 STABLE machines (migration > to 9 is running), no NFSv4 (by now), all tcp NFS links, merely no > locking. > > Data consists of a lot of files, this is mainly mailboxes (IMAP: > dovecot, incoming mail with exim, some simple web stuff with apache), so > lots of small files, only few bigger ones. Directory structures to a > reasonable depth. > > System is on a SSD (ufs, trim), additionally there are 3 (4 actually, 1 > unused by now) 120GB SSDs serving as cache devices for the zpools. I > first starting using the whole device, but in my hopes to change > something limited cache to partitions of 32GB without change in > behaviour. > > > Problem: > > After about a week of runtime in normal workload the systems starts to > swap (with about 300 to 500 MB of RAM free). Lots of swapping in and > out, but only very few swap space used (30 to 50 MB). ZFS ARC at that > point reaches it's minimum (while using up to it's configured maximum > before). Most of the RAM is wired. L2ARC headers, accourding to > zfs-stats eat about 1GB, ARC is at 1.8GB at this time. No userland > processes using lots of RAM. > > After some time the system becomes unresponsive, the only way to fix > this I had found by now is to reboot the machine (which of course gives > a service interruption). > >>From the start of swapping to unresponsiveness I have about 2 to 4 hours > to check several things (if I just knew what!). > > Workload distribution is not even over the day, from my munin graphs I > can see, that wired grows at time of higher workload. At night with > lower workload (but far from nothing, let's say about 1/3 to 1/2 in > writes, but probably <1/4 in reads from weekday workload) I can barely > see any groth of the wired graph. > > So where is my memory going, any ideas what to change? > > Kernel is stripped down from GENERIC and then everything I need loaded > as modules. > > Kernel config: http://sysadm.in/zprob/ZSTOR > loader.conf : http://sysadm.in/zprob/loader.conf > dmesg.boot : http://sysadm.in/zprob/dmesg.boot > > -- 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Philip M. Gollucci (pgollu...@p6m7g8.com) c: 703.336.9354 Member, Apache Software Foundation Committer,FreeBSD Foundation Consultant, P6M7G8 Inc. Director Operations, Ridecharge Inc. Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. signature.asc Description: OpenPGP digital signature
Re: gptzfsboot dell r510 fails
On 03/02/10 01:56, Philip M. Gollucci wrote: For my next attempt, I'm going to try to move the ssds to slots 6,7 so the boot devices are '0,1' which I know should work. This actually works. That leads me to believe that the vdev probes in zfsload.c are not quite right. Or its finding them incorrectly (too soon). -- 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Philip M. Gollucci (pgollu...@p6m7g8.com) c: 703.336.9354 VP Apache Infrastructure; Member, Apache Software Foundation Committer,FreeBSD Foundation Consultant, P6M7G8 Inc. Sr. System Admin, Ridecharge Inc. Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. ___ 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"
gptzfsboot dell r510 fails
Hi All, Dell r510 24GB RAM 8 disks in the following order 0-1 - 25gb ssd sas 2-7 - 136gb sas http://svn.freebsd.org/base/releng/8...@203057 which does not include http://svn.freebsd.org/viewvc/base?view=revision&revision=199714 so following http://wiki.freebsd.org/RootOnZFS/GPTZFSBoot/RAIDZ2 [/etc/src.conf: ZFS_LOADER_SUPPORT=true] which I've gotten to work on 500+ dell machines on the above fbsd version. [860,1435sc,1950,2950,2970,r710] So I've setup the zpools via the livefs as zroot (mirror) /dev/gpt/disk0 -> mfid2[p3] /dev/gpt/disk1 -> mfid3[p3] zmysql (raidz1) /dev/mfid[4567] cache /dev/mfid[01] I've selected the 3rd device in the perc h700 bios [mfid2] to be the 'bios boot device' which amazingly to me actually worked. During the boot I get to the standard ROOT MOUNT ERROR: set vfs.root.mountfrom.options=rw Loader variables: vfs.root.mountfrom=zfs:zroot vfs.root.mountfrom.options Manual root filesystem specification: . Is this setup even possible, or will I need to relocate the order of the disks ? For my next attempt, I'm going to try to move the ssds to slots 6,7 so the boot devices are '0,1' which I know should work. Failing that, I'll do hardware raid-1 on 0-1 and just a ZFS fs on them on top. -- 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Philip M. Gollucci (pgollu...@p6m7g8.com) c: 703.336.9354 VP Apache Infrastructure; Member, Apache Software Foundation Committer,FreeBSD Foundation Consultant, P6M7G8 Inc. Sr. System Admin, Ridecharge Inc. Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. ___ 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"
dell 2950 + mpt + stable/8 boot hangs
Hi All, [please keep the infra-private list in the replies] We've recently attached a external JBOD, Storform D53J, to a dell pe 2950 via PCI-e cards (using the mpt driver). This works fine on stable/7...@r197719 [1] despite being before some mfc's of mptutil work from scottl. When booting stable/8...@204185 the boot hangs [2] Whats more, is if we disconnect the array physically, we're able to boot [3] the stable/8 kernel and even use the array from a chroot'ed install of the stable/8 userland [sudo camcontrol rescan all, and some zpool stuff] We've already seen this suggestion on google /boot/loader.conf: hw.pci.mcfg=0 which didn't help. Additionally, the following pr might be relevant but we haven't tried it yet. http://people.freebsd.org/~linimon/studies/prs/prs_for_tag_regression.html http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/142263 disabling acpi Thoughts ? [1] - http://people.apache.org/~pgollucci/ERIS/dmesg.boot.7 [2] - http://people.apache.org/~pgollucci/ERIS/eris.bmp [3] - http://people.apache.org/~pgollucci/ERIS/dmesg.boot.8 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Philip M. Gollucci (pgollu...@p6m7g8.com) c: 703.336.9354 VP Apache Infrastructure; Member, Apache Software Foundation Committer,FreeBSD Foundation Consultant, P6M7G8 Inc. Sr. System Admin, Ridecharge Inc. Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. ___ 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: [FreeBSD-Announce] FreeBSD Errata Notice FreeBSD-EN-09:05.null
> Corrected: 2009-10-02 18:09:56 UTC (RELENG_8, 8.0-RC2) > 2009-10-02 18:09:56 UTC (RELENG_7, 7.2-STABLE) > 2009-10-02 18:09:56 UTC (RELENG_7_2, 7.2-RELEASE-p4) > 2009-10-02 18:09:56 UTC (RELENG_7_1, 7.1-RELEASE-p8) > 2009-10-02 18:09:56 UTC (RELENG_6, 6.4-STABLE) > 2009-10-02 18:09:56 UTC (RELENG_6_4, 6.4-RELEASE-p7) > 2009-10-02 18:09:56 UTC (RELENG_6_3, 6.3-RELEASE-p13) > - - > RELENG_6 > RELENG_6_4 > RELENG_6_3 > RELENG_7 > RELENG_7_2 > RELENG_7_1 > RELENG_8 > - - > Branch/path Revision > - - > stable/6/ r197715 > releng/6.4/ r197715 > releng/6.3/ r197715 > stable/7/ r197715 > releng/7.2/ r197715 > releng/7.1/ r197715 > stable/8/ r197714 > - - Don't these usually mention HEAD/CURRENT ? and is the 197714 a typo ? -- -------- 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Philip M. Gollucci (pgollu...@p6m7g8.com) c: 703.336.9354 Consultant - P6M7G8 Inc.http://p6m7g8.net Senior Sys Admin- RideCharge, Inc. http://ridecharge.com ASF Member - Apache Software Foundation http://apache.org FreeBSD Committer - FreeBSD Foundation http://freebsd.org Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. ___ 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: apachectl gracefult causes Signal 11 crash after 6.3 to 7.0 upgrade [SOLVED]
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Jordi Espasa Clofent wrote: | It seems a php-extensions bug. | If you comment the mhash.so in /usr/local/etc/php/extensions.ini as: | | ;entension=mhash.so | | all works fine and you don't get anymore httpd crash (signal 11) if you | use 'apachectl graceful'. | | Maybe will be a good idea to open PR for this? | | I hope it helps someone (I'm very surprised that this isn't a | documented bug in 7.0 yet) It might make more sense to follow up with php. Just b/c it happens in 7.x and not 6.x doesn't mean its a FreeBSD issue. - -- - ------------ Philip M. Gollucci ([EMAIL PROTECTED]) o:703.549.2050x206 Senior System Admin - Riderway, Inc. http://riderway.com / http://ridecharge.com 1024D/DB9B8C1C B90B FBC3 A3A1 C71A 8E70 3F8C 75B8 8FFB DB9B 8C1C Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. -BEGIN PGP SIGNATURE- Version: GnuPG v2.0.8 (FreeBSD) iD8DBQFIUDAgdbiP+9ubjBwRAskiAJ993ELYL3AP5HkVtDSk2JQx9OuJzACfdORO rnTL1Ecdd4MNwlcrNKhwLYM= =lX0o -END PGP SIGNATURE- ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: Can NOT boot FreeBSD on Dell R900
Huang wen hui wrote: > hi, > I boot FreeBSD 7.0R on R900, it stops with an error message: > can't load 'kernel' It might be chipset related, I know the R860 is only like 2-4 months in the field, so I doubt FreeBSD developers have one yet. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: [RFC/P] Port System Re-Engineering (Repost from -ports@)
Aryeh M. Friedman wrote: > [Repost from [EMAIL PROTECTED] > > As has been hashed out in -ports@ over the last few days there is at > least a need to examine weither or not the current ports system should > remain as is or potentially be re-engineered in the future (estimates > if and when needed vary from ASAP to 10-15 years). I have > volunteered to undertake a feasibility/pilot project to examine what > changes (if any) are needed in the system (for the purposes of this > thread I will not venture any of my own suggestions). I have the > following broad questions for people: > > 1. What is more important to your personal use of FreeBSD (the ports > system, the underlaying OS, some other aspect)? Software builds correct and is present. Including a way to make my own custom packages for distribution. > > 2. How frequently do you interact with the ports systems and what is > the most common interaction you have with it? Daily, updating, and maintaining the ports tree itself. > > 3. What is the single best aspect of the current system? Its source based and re-uses and existing language (make) instead of inventing a new one. > > 4. What is the single worst aspect of the current system? Most ports don't deal well with multiple versions. Even apache which is versioned doesn't do it that well. > > 5. If you where a new FreeBSD user how would your answers above > change? If you where brand new to UNIX how whould they change? I'd want a gui and not to compile anything. > > 6. Assuming that there was no additional work on your behalf would you > use a new system if it corrected your answer to number 4? Quite possibly. > > 7. Same as question 6 but for your answer on question 3? (that doesn't make sense -- if you corrected the single best aspect of ports?) > > 8. How long have you used FreeBSD and/or UNIX in general? since 2.2.8 ~1998 > > 9. That is your primary use(s) for your FreeBSD machine(s) (name upto 3)? Desktop Development (SVN, imap, you name it) Production (FAMP stacks) > > 10. Assuming there is no functional difference what is your preferred > installation method for 3rd party software? source compilation -- except for things like Xorg, Firefox and Thunrderbird because they are just so darn big. > > 11. On a scale from 1 to 10 (10 being the best) please rate the > importance of the following aspects of the ports system? > >a. User Interface 7 >b. Consistency of behaviors and interactions 5 >c. Accuracy in dependant port installations 7 >d. Internal record keeping 4 >e. Granularity's of the port management system 6 > > 12. Please rate your personal technical skill level? Very High -- Professional System Admin ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]" -- Philip M. Gollucci ([EMAIL PROTECTED]) o:703.549.2050x206 Senior System Admin - Riderway, Inc. http://riderway.com / http://ridecharge.com 1024D/EC88A0BF 0DE5 C55C 6BF3 B235 2DAB B89E 1324 9B4F EC88 A0BF Work like you don't need the money, love like you'll never get hurt, and dance like nobody's watching. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
