Re: kern.sched.quantum: Creepy, sadistic scheduler
On 04/17/18 17:20, EBFE via freebsd-stable wrote: > On Tue, 17 Apr 2018 09:05:48 -0700 > Freddie Cashwrote: > >> # Tune for desktop usage >> kern.sched.preempt_thresh=224 >> >> Works quite nicely on a 4-core AMD Phenom-II X4 960T Processor >> (3010.09-MHz K8-class CPU) running KDE4 using an Nvidia 210 GPU. > > For interactive tasks, there is a "special" tunable: > % sysctl kern.sched.interact > kern.sched.interact: 10 # default is 30 > % sysctl -d kern.sched.interact > kern.sched.interact: Interactivity score threshold > > reducing the value from 30 to 10-15 keeps your gui/system responsive, > even under high load. > [...] I suspect my case (make buildworld while running misc/dnetc) doesn't qualify. However, I just completed a SCHED_ULE run with preempt_thresh set to 5, and "time make buildworld" reports: 7336.748u 677.085s 9:25:19.86 23.6% 27482+473k 42147+431581io 38010pf+0w Much closer to SCHED_4BSD! I'll try preempt_thresh=0 next, and I guess I'll at least try preempt_thresh=224 to see how that works for me. -- George signature.asc Description: OpenPGP digital signature
Re: kern.sched.quantum: Creepy, sadistic scheduler
On Tue, 17 Apr 2018 09:05:48 -0700 Freddie Cashwrote: > # Tune for desktop usage > kern.sched.preempt_thresh=224 > > Works quite nicely on a 4-core AMD Phenom-II X4 960T Processor > (3010.09-MHz K8-class CPU) running KDE4 using an Nvidia 210 GPU. For interactive tasks, there is a "special" tunable: % sysctl kern.sched.interact kern.sched.interact: 10 # default is 30 % sysctl -d kern.sched.interact kern.sched.interact: Interactivity score threshold reducing the value from 30 to 10-15 keeps your gui/system responsive, even under high load. ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: kern.sched.quantum: Creepy, sadistic scheduler
On Tue, Apr 17, 2018 at 8:49 AM, Kevin Obermanwrote: > On Mon, Apr 16, 2018 at 11:56 PM, Eivind Nicolay Evensen < > eivi...@terraplane.org> wrote: > > > On Wed, Apr 04, 2018 at 09:32:58AM -0400, George Mitchell wrote: > > > On 04/04/18 06:39, Alban Hertroys wrote: > > > > [...] > > > > That said, SCHED_ULE (the default scheduler for quite a while now) > was > > designed with multi-CPU configurations in mind and there are claims that > > SCHED_4BSD works better for single-CPU configurations. You may give that > a > > try, if you're not already on SCHED_4BSD. > > > > [...] > > > > > > A small, disgruntled community of FreeBSD users who have never seen > > > proof that SCHED_ULE is better than SCHED_4BSD in any environment > > > continue to regularly recompile with SCHED_4BSD. I dread the day when > > > that becomes impossible, but at least it isn't here yet. -- George > > > > Indeed 4bsd is better in my case aswell. While for some unknown to me > > reason ule performed a bit better in the 10.x series than before, in 11.x > > it again is in my case not usable. > > > > Mouse freezes for around half a second with even frequency by just moving > > it around in x11. Using 4bsd instead makes the problem go away. > > I'm actually very happy that ule became worse again because going > > back to 4bsd yet again also gave improved performance from other > > dreadfully slow but (to me) still useful programs, like darktable. > > > > With 4bsd, when adjusting shadows and highlights it is possible to see > > what I do when moving sliders. With ule it has never been better than > waiting > > 10-20-30 seconds to see where it was able to read a slider position > > and update display, when working on images around 10500x10500 greyscale. > > > > It's not single cpu/single core either: > > CPU: AMD FX(tm)-6300 Six-Core Processor (3817.45-MHz > K8-class > > CPU) > > My experience has long been that 4BSD works far better for interactive, X > based systems than ULE. Even on 10 I saw long, annoying pauses with ULE and > I don't se those with 4BSD. I'd really like to see it better known that > this is often the case. BTW, my system is 2 core/4 thread Sandybridge. > > The following has been suggested multiple times over the years on various mailing lists as the "solution" to making ULE work well for interactive tasks like running X-based desktops (in /etc/sysctl.conf): # Tune for desktop usage kern.sched.preempt_thresh=224 Works quite nicely on a 4-core AMD Phenom-II X4 960T Processor (3010.09-MHz K8-class CPU) running KDE4 using an Nvidia 210 GPU. -- Freddie Cash fjwc...@gmail.com ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: amd64 kernel crash introduced between 20180329 & 20180408
> On 17 Apr 2018, at 9:24 AM, Kyle Evanswrote: > > Can you set vm.pmap.pti=0 at the loader prompt and see if > this affects your situation at all, just to rule that out? I redid everything from the start, did set vm.pmap.pti=0, and it behaves exactly the same: kernel panic. Thanks for your help! Do I have any other takers? ;-) Dan ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: kern.sched.quantum: Creepy, sadistic scheduler
On Mon, Apr 16, 2018 at 11:56 PM, Eivind Nicolay Evensen < eivi...@terraplane.org> wrote: > On Wed, Apr 04, 2018 at 09:32:58AM -0400, George Mitchell wrote: > > On 04/04/18 06:39, Alban Hertroys wrote: > > > [...] > > > That said, SCHED_ULE (the default scheduler for quite a while now) was > designed with multi-CPU configurations in mind and there are claims that > SCHED_4BSD works better for single-CPU configurations. You may give that a > try, if you're not already on SCHED_4BSD. > > > [...] > > > > A small, disgruntled community of FreeBSD users who have never seen > > proof that SCHED_ULE is better than SCHED_4BSD in any environment > > continue to regularly recompile with SCHED_4BSD. I dread the day when > > that becomes impossible, but at least it isn't here yet. -- George > > Indeed 4bsd is better in my case aswell. While for some unknown to me > reason > ule performed a bit better in the 10.x series than before, in 11.x > it again is in my case not usable. > > Mouse freezes for around half a second with even frequency by just moving > it around in x11. Using 4bsd instead makes the problem go away. > I'm actually very happy that ule became worse again because going > back to 4bsd yet again also gave improved performance from other > dreadfully slow but (to me) still useful programs, like darktable. > > With 4bsd, when adjusting shadows and highlights it is possible to see > what I > do when moving sliders. With ule it has never been better than waiting > 10-20-30 seconds to see where it was able to read a slider position > and update display, when working on images around 10500x10500 greyscale. > > It's not single cpu/single core either: > CPU: AMD FX(tm)-6300 Six-Core Processor (3817.45-MHz K8-class > CPU) > > > > > -- > Eivind > My experience has long been that 4BSD works far better for interactive, X based systems than ULE. Even on 10 I saw long, annoying pauses with ULE and I don't se those with 4BSD. I'd really like to see it better known that this is often the case. BTW, my system is 2 core/4 thread Sandybridge. -- Kevin Oberman, Part time kid herder and retired Network Engineer E-mail: rkober...@gmail.com PGP Fingerprint: D03FB98AFA78E3B78C1694B318AB39EF1B055683 ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: amd64 kernel crash introduced between 20180329 & 20180408
On Tue, Apr 17, 2018 at 10:18 AM, Dan Allenwrote: > > >> On 17 Apr 2018, at 8:49 AM, Kyle Evans wrote: >> >> As "the guy most likely to have broken boot code in stable," may I ask >> what leads you specifically to amd64 boot code? Mostly curious if >> there's something beyond "i386 works well" that lead you to this >> conclusion. > > It is partly just a hunch. > > I installed 11.0 for use with qemu a while ago. I did binary upgrades for > patches using > freebsd-update. When 11.1 came out, it would not work correctly, again with > the same > kind of behavior. Then, I got some later snapshots that worked again, > notably the 20180329 > build. When the next snapshot came out, things broke. I also tried my own > builds, same story. > > I even got both source trees together - 20180329 and 20180408 - and did a > diff on the entire > trees, and I noticed activity in the boot & kernel code. It could just as > likely be something in the > kernel as well, but none of this happens with the i386 build. > >> When you say it crashes and does a kernel dump- you're landing at a >> ddb prompt, yeah? What does executing bt at that prompt look like? > > No, I am not ever given a prompt. I get to watch a mini-dump happen and then > an automatic > reboot. It is a kernel panic. Here is what I see: > Ahh, fun. =) I'm inclined to think it's probably not a boot code problem, but it is suspicious. Can you set vm.pmap.pti=0 at the loader prompt and see if this affects your situation at all, just to rule that out? ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: amd64 kernel crash introduced between 20180329 & 20180408
> On 17 Apr 2018, at 8:49 AM, Kyle Evanswrote: > > As "the guy most likely to have broken boot code in stable," may I ask > what leads you specifically to amd64 boot code? Mostly curious if > there's something beyond "i386 works well" that lead you to this > conclusion. It is partly just a hunch. I installed 11.0 for use with qemu a while ago. I did binary upgrades for patches using freebsd-update. When 11.1 came out, it would not work correctly, again with the same kind of behavior. Then, I got some later snapshots that worked again, notably the 20180329 build. When the next snapshot came out, things broke. I also tried my own builds, same story. I even got both source trees together - 20180329 and 20180408 - and did a diff on the entire trees, and I noticed activity in the boot & kernel code. It could just as likely be something in the kernel as well, but none of this happens with the i386 build. > When you say it crashes and does a kernel dump- you're landing at a > ddb prompt, yeah? What does executing bt at that prompt look like? No, I am not ever given a prompt. I get to watch a mini-dump happen and then an automatic reboot. It is a kernel panic. Here is what I see: ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: amd64 kernel crash introduced between 20180329 & 20180408
On Tue, Apr 17, 2018 at 9:44 AM, Dan Allenwrote: > I run FreeBSD 11-STABLE on actual machines, and I build the system every few > days. Things have been fine. > > However, I also run FreeBSD 11 via the qemu emulator on my Mac. I run lots > of different BSD & Linux OSes here to test them out. I have been running the > same binary of qemu-system-x86_64 v1.2 for six years. It runs great. > > Then recently this happened: > > This snapshot dated 20180329, after doing a fresh install, runs fine: > > > https://download.freebsd.org/ftp/snapshots/ISO-IMAGES/11.1/FreeBSD-11.1-STABLE-amd64-20180329-r331742-disc1.iso > > I can run pkg install and begin adding stuff to the system and life is good. > > BUT > > This snapshot dated 20180408, after doing a fresh install, will crash when > running pkg install: > > > https://download.freebsd.org/ftp/snapshots/ISO-IMAGES/11.1/FreeBSD-11.1-STABLE-amd64-20180408-r332308-disc1.iso > > It crashes about 90% of the way through updating the pkg snapshot. It does > not matter what pkg you try and install. > > However, the latest release in the i386 flavor works fine on qemu: > > > https://download.freebsd.org/ftp/snapshots/ISO-IMAGES/11.1/FreeBSD-11.1-STABLE-i386-20180412-r332428-disc1.iso > > So sometime between March 29th & April 8th, in amd64 boot code, I believe the > problem was introduced. As "the guy most likely to have broken boot code in stable," may I ask what leads you specifically to amd64 boot code? Mostly curious if there's something beyond "i386 works well" that lead you to this conclusion. > I cannot debug the crash, because it does a kernel dump, and then when the > system reboots, almost anything again triggers a kernel crash and it reboots > again and again: no chance to inspect a mini dump or whatever. When you say it crashes and does a kernel dump- you're landing at a ddb prompt, yeah? What does executing bt at that prompt look like>? > I wish I had more to go on, but I am happy to off list work with anyone that > wants to pursue this, by testing out stuff or answering more questions. > ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
amd64 kernel crash introduced between 20180329 & 20180408
I run FreeBSD 11-STABLE on actual machines, and I build the system every few days. Things have been fine. However, I also run FreeBSD 11 via the qemu emulator on my Mac. I run lots of different BSD & Linux OSes here to test them out. I have been running the same binary of qemu-system-x86_64 v1.2 for six years. It runs great. Then recently this happened: This snapshot dated 20180329, after doing a fresh install, runs fine: https://download.freebsd.org/ftp/snapshots/ISO-IMAGES/11.1/FreeBSD-11.1-STABLE-amd64-20180329-r331742-disc1.iso I can run pkg install and begin adding stuff to the system and life is good. BUT This snapshot dated 20180408, after doing a fresh install, will crash when running pkg install: https://download.freebsd.org/ftp/snapshots/ISO-IMAGES/11.1/FreeBSD-11.1-STABLE-amd64-20180408-r332308-disc1.iso It crashes about 90% of the way through updating the pkg snapshot. It does not matter what pkg you try and install. However, the latest release in the i386 flavor works fine on qemu: https://download.freebsd.org/ftp/snapshots/ISO-IMAGES/11.1/FreeBSD-11.1-STABLE-i386-20180412-r332428-disc1.iso So sometime between March 29th & April 8th, in amd64 boot code, I believe the problem was introduced. I cannot debug the crash, because it does a kernel dump, and then when the system reboots, almost anything again triggers a kernel crash and it reboots again and again: no chance to inspect a mini dump or whatever. I wish I had more to go on, but I am happy to off list work with anyone that wants to pursue this, by testing out stuff or answering more questions. Dan Allen Running FreeBSD since 2.2.8 ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
CentOs Competitors Users Contact List.
style="color:rgb(31,78,121)">Hello, Would you be interested in CentOS (Linux) Users List? We are a Global Technology User’s List Provider’s with 90 Million Plus data and counting. You may also acquire the alternatives such as: Windows Server users List, Oracle Linux users List, style="color:rgb(31,78,121)">Ubuntu Linux users List, Suse Linux users List, Oracle Solaris users List and many more. List Contains: Name, Companys Name, Phone Number, Fax Number, Job Title, Email address, Complete Mailing Address, SIC code, Company revenue, size, Web address etc. All Technology / Companies Partners and Users List, IT decision Makers from Fortune 500 Companies, IT Decision Makers from SME as well. style="margin-bottom:0.0001pt;line-height:normal">style="color:rgb(31,78,121)">We provide data across the globe - North America, EMEA, Asia Pacific and LATAM. Please let us know your targeted criteria and geography to provide you with detailed information for your review. Let me know your thoughts! style="color:rgb(31,78,121)">Thanks, Gemma White Senior Database Executive style="color:rgb(31,78,121)"> To “opt out” response not interestedstyle="color:rgb(31,78,121)"> powered by GSM. Free mail merge and email marketing software for Gmail. ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
more data: SCHED_ULE+PREEMPTION is the problem
On 04/07/18 10:18, Peter wrote: > Hi all, > [...] Thanks for all the investigation! > 3. kern.sched.preempt_thresh > > I could make the problem disappear by changing kern.sched.preempt_thresh > from the default 80 to either 11 (i5-3570T) or 7 (p3) or smaller. This > seems to correspond to the disk interrupt threads, which run at intr:12 > (i5-3570T) or intr:8 (p3). > [...] More data. With SCHED_4BSD at FreeBSD 10.4-RELEASE-p8 #0 r331984: kern.sched.runq_fuzz: 1 kern.sched.ipiwakeup.useloop: 0 kern.sched.ipiwakeup.usemask: 1 kern.sched.ipiwakeup.delivered: 376139898 kern.sched.ipiwakeup.requested: 376137875 kern.sched.ipiwakeup.enabled: 1 kern.sched.slice: 12 kern.sched.quantum: 94488 kern.sched.name: 4BSD kern.sched.preemption: 1 kern.sched.cpusetsize: 8 With dnetc running on a 6-core AMD CPU from a few years back, "time make buildworld" yields: 6640.224u 828.874s 2:14:37.73 92.4% 28525+494k 31633+431554io 33192pf+0w I shifted to a GENERIC kernel, FreeBSD 10.4-RELEASE-p8 #0 r332560: kern.sched.topology_spec: 0, 1, 2, 3, 4, 5 0, 1, 2, 3, 4, 5 kern.sched.steal_thresh: 2 kern.sched.steal_idle: 1 kern.sched.balance_interval: 127 kern.sched.balance: 1 kern.sched.affinity: 1 kern.sched.idlespinthresh: 157 kern.sched.idlespins: 1 kern.sched.static_boost: 152 kern.sched.preempt_thresh: 80 kern.sched.interact: 30 kern.sched.slice: 12 kern.sched.quantum: 94488 kern.sched.name: ULE kern.sched.preemption: 1 kern.sched.cpusetsize: 8 I stupidly typed "make buildworld" without the "time" command, but the build log started at Mon Apr 16 13:49:12 EDT 2018 and completed at Tue Apr 17 00:22:23 EDT 2018. You read that right: 2+ hours vs 10 1/2! So I set "sysctl kern.sched.preempt_thresh=5" (a wild guess on my part) and started another "time make buildworld". It's still going now, but subjectively it's still running like molasses. I'll post more results later after trying sysctl kern.sched.preempt_thresh=0. By the way, over the years that this discussion has been going on, I've *never* had a response to my question: "What is the workload for which SCHED_ULE outperforms SCHED_4BSD?"-- George signature.asc Description: OpenPGP digital signature
11.1 stable r321309 loader.efi boot faile
>> freebsd 11.1 stable r321309 boot failed >> loader.efi recognize efipart as new disk on MacBook pro mid 2015 >> >> >> >> > ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: stable/11 r332356 started panicing in bpf_dtor/__mtx_lock_sleep
On 17.04.2018 16:30, Eugene Grosbein wrote: CCing mjoras@ as author of suspicious change https://svnweb.freebsd.org/base?view=revision=323477 > I have a server that was running stable/11 rock-stable for many months. It was running stable/11 r314043 before last update. > A week ago I've updates it to 11.1-STABLE r332356 and today it paniced and I > have crashdump. > Any thoughts? > > Unread portion of the kernel message buffer: > Sleeping thread (tid 100444, pid 28400) owns a non-sleepable lock > KDB: stack backtrace of thread 100444: > sched_switch() at sched_switch+0x626/frame 0xfe03550f9740 > mi_switch() at mi_switch+0xc5/frame 0xfe03550f9770 > sleepq_wait() at sleepq_wait+0x2c/frame 0xfe03550f97a0 > _sx_xlock_hard() at _sx_xlock_hard+0x2f0/frame 0xfe03550f9830 > vlan_ioctl() at vlan_ioctl+0x53f/frame 0xfe03550f98b0 > ifpromisc() at ifpromisc+0x106/frame 0xfe03550f9910 > bpf_detachd_locked() at bpf_detachd_locked+0x1b4/frame 0xfe03550f9960 > bpf_dtor() at bpf_dtor+0x9a/frame 0xfe03550f9990 > devfs_fpdrop() at devfs_fpdrop+0x9c/frame 0xfe03550f99b0 > devfs_close_f() at devfs_close_f+0x45/frame 0xfe03550f99e0 > closef() at closef+0x209/frame 0xfe03550f9a70 > closefp() at closefp+0x8b/frame 0xfe03550f9ab0 > amd64_syscall() at amd64_syscall+0x25c/frame 0xfe03550f9bf0 > fast_syscall_common() at fast_syscall_common+0x101/frame 0xfe03550f9bf0 > --- syscall (6, FreeBSD ELF64, sys_close), rip = 0x4a317a, rsp = > 0x7fffe3d8, rbp = 0x7fffe3f0 --- > panic: sleeping thread > cpuid = 1 > KDB: stack backtrace: > db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfe0354c6d7c0 > vpanic() at vpanic+0x177/frame 0xfe0354c6d820 > panic() at panic+0x43/frame 0xfe0354c6d880 > propagate_priority() at propagate_priority+0x183/frame 0xfe0354c6d8b0 > turnstile_wait() at turnstile_wait+0x2bc/frame 0xfe0354c6d900 > __mtx_lock_sleep() at __mtx_lock_sleep+0x151/frame 0xfe0354c6d960 > bpf_dtor() at bpf_dtor+0x191/frame 0xfe0354c6d990 > devfs_fpdrop() at devfs_fpdrop+0x9c/frame 0xfe0354c6d9b0 > devfs_close_f() at devfs_close_f+0x45/frame 0xfe0354c6d9e0 > closef() at closef+0x209/frame 0xfe0354c6da70 > closefp() at closefp+0x8b/frame 0xfe0354c6dab0 > amd64_syscall() at amd64_syscall+0x25c/frame 0xfe0354c6dbf0 > fast_syscall_common() at fast_syscall_common+0x101/frame 0xfe0354c6dbf0 > --- syscall (6, FreeBSD ELF64, sys_close), rip = 0x4a317a, rsp = > 0x7fffe3d8, rbp = 0x7fffe3f0 --- > Uptime: 6d2h0m17s > Dumping 1414 out of 12265 MB:..2%..11%..21%..31%..41%..51%..62%..71%..81%..91% > > > (kgdb) bt > #0 doadump (textdump=1) at pcpu.h:229 > #1 0x804f3b9a in kern_reboot (howto=260) at > /usr/local/src/sys/kern/kern_shutdown.c:383 > #2 0x804f3f81 in vpanic (fmt=, ap= optimized out>) > at /usr/local/src/sys/kern/kern_shutdown.c:776 > #3 0x804f3dc3 in panic (fmt=) at > /usr/local/src/sys/kern/kern_shutdown.c:707 > #4 0x80546b33 in propagate_priority (td=) at > /usr/local/src/sys/kern/subr_turnstile.c:226 > #5 0x8054720c in turnstile_wait (ts=0xf80151ac4180, owner= optimized out>, queue=) > at /usr/local/src/sys/kern/subr_turnstile.c:742 > #6 0x804dda81 in __mtx_lock_sleep (c=0x80c9c910, v= optimized out>) > at /usr/local/src/sys/kern/kern_mutex.c:627 > #7 0x805cd061 in bpf_dtor (data=0xf801512df800) at > /usr/local/src/sys/net/bpf.c:778 > #8 0x80455e5c in devfs_fpdrop (fp=) at > /usr/local/src/sys/fs/devfs/devfs_vnops.c:193 > #9 0x804595d5 in devfs_close_f (fp=0xf802af2fe6e0, td= optimized out>) > at /usr/local/src/sys/fs/devfs/devfs_vnops.c:675 > #10 0x804b1549 in closef (fp=0xf802af2fe6e0, > td=0xf8000cf75000) at file.h:346 > #11 0x804af00b in closefp (fdp=0xf80083b48000, fd= optimized out>, fp=0xf802af2fe6e0, > td=0xf8000cf75000, holdleaders=0) at > /usr/local/src/sys/kern/kern_descrip.c:1191 > #12 0x807afb6c in amd64_syscall (td=0xf8000cf75000, traced=0) at > subr_syscall.c:132 > #13 0x80791c3d in fast_syscall_common () at > /usr/local/src/sys/amd64/amd64/exception.S:480 > #14 0x004a317a in ?? () > Previous frame inner to this frame (corrupt stack?) Some more details: this monitoring server has many vlans over em1. It runs some custom perl code utilizing Net::Pcap over bpf. Many times per minute it opens/closes bpf to send/receive custom PPPoE frames using vlans (sends over multiple if_vlan and receives using their parent em1). This server also multiple times per minute starts and stops receiving IPTV multicast traffic using another em0 interface as part of another monitoring job. Again, r314043 was pretty stable. ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to
stable/11 r332356 started panicing in bpf_dtor/__mtx_lock_sleep
Hi! I have a server that was running stable/11 rock-stable for many months. A week ago I've updates it to 11.1-STABLE r332356 and today it paniced and I have crashdump. Any thoughts? Unread portion of the kernel message buffer: Sleeping thread (tid 100444, pid 28400) owns a non-sleepable lock KDB: stack backtrace of thread 100444: sched_switch() at sched_switch+0x626/frame 0xfe03550f9740 mi_switch() at mi_switch+0xc5/frame 0xfe03550f9770 sleepq_wait() at sleepq_wait+0x2c/frame 0xfe03550f97a0 _sx_xlock_hard() at _sx_xlock_hard+0x2f0/frame 0xfe03550f9830 vlan_ioctl() at vlan_ioctl+0x53f/frame 0xfe03550f98b0 ifpromisc() at ifpromisc+0x106/frame 0xfe03550f9910 bpf_detachd_locked() at bpf_detachd_locked+0x1b4/frame 0xfe03550f9960 bpf_dtor() at bpf_dtor+0x9a/frame 0xfe03550f9990 devfs_fpdrop() at devfs_fpdrop+0x9c/frame 0xfe03550f99b0 devfs_close_f() at devfs_close_f+0x45/frame 0xfe03550f99e0 closef() at closef+0x209/frame 0xfe03550f9a70 closefp() at closefp+0x8b/frame 0xfe03550f9ab0 amd64_syscall() at amd64_syscall+0x25c/frame 0xfe03550f9bf0 fast_syscall_common() at fast_syscall_common+0x101/frame 0xfe03550f9bf0 --- syscall (6, FreeBSD ELF64, sys_close), rip = 0x4a317a, rsp = 0x7fffe3d8, rbp = 0x7fffe3f0 --- panic: sleeping thread cpuid = 1 KDB: stack backtrace: db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfe0354c6d7c0 vpanic() at vpanic+0x177/frame 0xfe0354c6d820 panic() at panic+0x43/frame 0xfe0354c6d880 propagate_priority() at propagate_priority+0x183/frame 0xfe0354c6d8b0 turnstile_wait() at turnstile_wait+0x2bc/frame 0xfe0354c6d900 __mtx_lock_sleep() at __mtx_lock_sleep+0x151/frame 0xfe0354c6d960 bpf_dtor() at bpf_dtor+0x191/frame 0xfe0354c6d990 devfs_fpdrop() at devfs_fpdrop+0x9c/frame 0xfe0354c6d9b0 devfs_close_f() at devfs_close_f+0x45/frame 0xfe0354c6d9e0 closef() at closef+0x209/frame 0xfe0354c6da70 closefp() at closefp+0x8b/frame 0xfe0354c6dab0 amd64_syscall() at amd64_syscall+0x25c/frame 0xfe0354c6dbf0 fast_syscall_common() at fast_syscall_common+0x101/frame 0xfe0354c6dbf0 --- syscall (6, FreeBSD ELF64, sys_close), rip = 0x4a317a, rsp = 0x7fffe3d8, rbp = 0x7fffe3f0 --- Uptime: 6d2h0m17s Dumping 1414 out of 12265 MB:..2%..11%..21%..31%..41%..51%..62%..71%..81%..91% (kgdb) bt #0 doadump (textdump=1) at pcpu.h:229 #1 0x804f3b9a in kern_reboot (howto=260) at /usr/local/src/sys/kern/kern_shutdown.c:383 #2 0x804f3f81 in vpanic (fmt=, ap=) at /usr/local/src/sys/kern/kern_shutdown.c:776 #3 0x804f3dc3 in panic (fmt=) at /usr/local/src/sys/kern/kern_shutdown.c:707 #4 0x80546b33 in propagate_priority (td=) at /usr/local/src/sys/kern/subr_turnstile.c:226 #5 0x8054720c in turnstile_wait (ts=0xf80151ac4180, owner=, queue=) at /usr/local/src/sys/kern/subr_turnstile.c:742 #6 0x804dda81 in __mtx_lock_sleep (c=0x80c9c910, v=) at /usr/local/src/sys/kern/kern_mutex.c:627 #7 0x805cd061 in bpf_dtor (data=0xf801512df800) at /usr/local/src/sys/net/bpf.c:778 #8 0x80455e5c in devfs_fpdrop (fp=) at /usr/local/src/sys/fs/devfs/devfs_vnops.c:193 #9 0x804595d5 in devfs_close_f (fp=0xf802af2fe6e0, td=) at /usr/local/src/sys/fs/devfs/devfs_vnops.c:675 #10 0x804b1549 in closef (fp=0xf802af2fe6e0, td=0xf8000cf75000) at file.h:346 #11 0x804af00b in closefp (fdp=0xf80083b48000, fd=, fp=0xf802af2fe6e0, td=0xf8000cf75000, holdleaders=0) at /usr/local/src/sys/kern/kern_descrip.c:1191 #12 0x807afb6c in amd64_syscall (td=0xf8000cf75000, traced=0) at subr_syscall.c:132 #13 0x80791c3d in fast_syscall_common () at /usr/local/src/sys/amd64/amd64/exception.S:480 #14 0x004a317a in ?? () Previous frame inner to this frame (corrupt stack?) ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
Re: kern.sched.quantum: Creepy, sadistic scheduler
On Wed, Apr 04, 2018 at 09:32:58AM -0400, George Mitchell wrote: > On 04/04/18 06:39, Alban Hertroys wrote: > > [...] > > That said, SCHED_ULE (the default scheduler for quite a while now) was > > designed with multi-CPU configurations in mind and there are claims that > > SCHED_4BSD works better for single-CPU configurations. You may give that a > > try, if you're not already on SCHED_4BSD. > > [...] > > A small, disgruntled community of FreeBSD users who have never seen > proof that SCHED_ULE is better than SCHED_4BSD in any environment > continue to regularly recompile with SCHED_4BSD. I dread the day when > that becomes impossible, but at least it isn't here yet. -- George Indeed 4bsd is better in my case aswell. While for some unknown to me reason ule performed a bit better in the 10.x series than before, in 11.x it again is in my case not usable. Mouse freezes for around half a second with even frequency by just moving it around in x11. Using 4bsd instead makes the problem go away. I'm actually very happy that ule became worse again because going back to 4bsd yet again also gave improved performance from other dreadfully slow but (to me) still useful programs, like darktable. With 4bsd, when adjusting shadows and highlights it is possible to see what I do when moving sliders. With ule it has never been better than waiting 10-20-30 seconds to see where it was able to read a slider position and update display, when working on images around 10500x10500 greyscale. It's not single cpu/single core either: CPU: AMD FX(tm)-6300 Six-Core Processor (3817.45-MHz K8-class CPU) -- Eivind ___ freebsd-stable@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"