Official thread: "zen-sources" - Part 7

Message

rahulthewall · Post by **rahulthewall** » Tue Sep 29, 2009 11:22 am

The shutdown lockup is gone now. Maybe bfs-240 fixed it. Thanks.

aTan · Post by **aTan** » Tue Sep 29, 2009 1:36 pm

But suspend to ram is still broken.

btw: 240 in Zen?

ponciarello · Post by **ponciarello** » Tue Sep 29, 2009 2:17 pm

yupz

http://git.zen-sources.org/?p=zen-stable.git;a=summary

http://git.zen-sources.org/?p=zen-stabl ... ter-2.6.30

aTan · Post by **aTan** » Tue Sep 29, 2009 3:03 pm

ponciarello wrote:yupz

http://git.zen-sources.org/?p=zen-stable.git;a=summary

http://git.zen-sources.org/?p=zen-stabl ... ter-2.6.30

hmm. zen-stable...

now I see

Guys,
GIT CHANGES
- zen-stable.git and zen.git have diverged, now you are on zen.git

DigitalCorpus · Post by **DigitalCorpus** » Tue Sep 29, 2009 5:57 pm

So I see that some people were using an Interbench to test how effective BFS really was. Reading through the BFS FAQ, Con suggested to not use that benchmark. What should we be using instead?

Aside from CFS, there are other features in Zen worht testing but I don't know how. One example is the SLAB allocators. I already know to avoid SLOB, but how to SLAB, SLUB, SLQB stack and how so you test it? I encoded HD TV on almost a daily basis and with 8GB of RAM, I tend to use /dev/shm as a scratch ram disk.

Also, what is CPU_BFS_AUTOISO. It's description

Code: Select all

 Enable this to automatically enable SCHED_ISO for X

doesn't help me much except for the fact that it pertains to X environments.

Edit: Also, what would be the suggestion of using BFS on a Q6700 server/desktop config? I currently have dynamic ticks enabled and my Hz at 108 (even though that is suggested for an octcore setup) and no preemption. I'm looking for a middle ground between bandwidth and latency if possible.

rahulthewall · Post by **rahulthewall** » Tue Sep 29, 2009 6:08 pm

rahulthewall wrote:The shutdown lockup is gone now. Maybe bfs-240 fixed it. Thanks.

Spoke too soon - it is not working now. Hmmm (I will have to dig deeper I guess)

rahulthewall · Post by **rahulthewall** » Tue Sep 29, 2009 7:38 pm

rahulthewall wrote:
rahulthewall wrote:The shutdown lockup is gone now. Maybe bfs-240 fixed it. Thanks.
Spoke too soon - it is not working now. Hmmm (I will have to dig deeper I guess)

Disabling BSD Process Accounting seems to solve the shutdown issue here.

DigitalCorpus · Post by **DigitalCorpus** » Tue Sep 29, 2009 8:15 pm

Added BFS scheduler to my config and using 2.6.31 stable from git. No preemption, dynamic ticks on, 108Hz are my current stock settings. Whenever I loaded up my phpsysinfo page, coretemp crashed. It didn't crash if I called it up via ssh login.

I changed no preemption to voluntary preemption and coretemp stopped crashing. Boot times were the same at 21 seconds. So I ran a test. Copy an 8.2 GB file from one disk to another and execute a couple commands. Please pardon by exasperation, but it was OMGWTF slow! It took multiple seconds to load df -h from a fresh boot. I know I am mixing variables here. I happen to be using BFQ for my I/O scheduler between two XFS partitions on different drives. I say iotop reported much less utilized bandwidth while running this test as well.

I'm going to echo 1 > /proc/sys/vm/drop_caches and try again with CFQ and report back if that changes

Edit 1: no change with CFQ. I am using two different kernel versions (2.6.30-zen1 to 2.6.31-zen2) so time to test with CFS w/ and w/o preemtion to see if this is linked to kernel version

cheater1034 · Post by **cheater1034** » Tue Sep 29, 2009 11:46 pm

DigitalCorpus wrote:So I see that some people were using an Interbench to test how effective BFS really was. Reading through the BFS FAQ, Con suggested to not use that benchmark. What should we be using instead?

Aside from CFS, there are other features in Zen worht testing but I don't know how. One example is the SLAB allocators. I already know to avoid SLOB, but how to SLAB, SLUB, SLQB stack and how so you test it? I encoded HD TV on almost a daily basis and with 8GB of RAM, I tend to use /dev/shm as a scratch ram disk.

Also, what is CPU_BFS_AUTOISO. It's description
Code: Select all
 Enable this to automatically enable SCHED_ISO for X
doesn't help me much except for the fact that it pertains to X environments.

Edit: Also, what would be the suggestion of using BFS on a Q6700 server/desktop config? I currently have dynamic ticks enabled and my Hz at 108 (even though that is suggested for an octcore setup) and no preemption. I'm looking for a middle ground between bandwidth and latency if possible.

Interbench is a fine benchmark to use, also kernbench as long as you look at what it's intended to measure (con has an interbench result on his ck.kolivas/patches/bfs page)
Also jens' latt.c, such that he used here: http://lkml.org/lkml/2009/9/7/73 - which is found at git://git.kernel.dk/latt.git

Not exactly sure how to go about testing the slab allocators. Although, generally, I wouldn't expect much of a performance margin between either.

here's a copy past about sched_iso:
"Unique to -ck this is a scheduling policy designed for pseudo-realttime scheduling without requiring superuser privileges (unlike SCHED_RR and SCHED_FIFO). When scheduled SCHED_ISO, a task can receive very low latency scheduling, and can take the full cpu like SCHED_RR, but unlike the realtime tasks they cannot starve the machine as an upper limit to their cpu usage is specified in a tunable (see below). It is designed for realtime like behaviour without risk to hanging for programs not really coded safely enough to be run realtime such as ordinary audio and video playback software. SCHED_ISO does not take a realtime priority, but nice levels like other normal tasks, although the nice value is largely ignored except when the task uses more than its cpu limit."

Anyway, it's beneficial for X and many X tasks (like audio stuff) generally, it's not included by default to autoiso for X, because if X is ran autoiso and an audio app isn't, it could *possibly* lead to skipping in an application like audacious or something. It's kconfig'd in zen. You can run apps sched_iso with schedtool, ex: schedtool -Ie amarok (or X)

If you're running a server/desktop i would disable dynticks. If you're running X on the server/desktop, set HZ=1000
voluntary preemption is junk, don't use it (you can't use it with bfs since it's disabled in Kconfig when bfs is selected. Full preemption is probably your best bet, no preemption is acceptable too - but if you are running X i'd suggest it.

cheater1034 · Post by **cheater1034** » Wed Sep 30, 2009 12:17 am

here's my latt test:

Code: Select all

latt -c8 "make -j2" kernel build      
----                                  
Kernel: 2.6.31-zen2-bfs-3337ea3       
Parameters: min_wait=100ms, max_wait=500ms, clients=8
Entries logged: 5712                                 

Wakeup averages
-------------------------------------
        Max                38796 usec
        Avg                11284 usec
        Stdev               9259 usec
        Stdev mean           123 usec

Work averages
-------------------------------------
        Max               143410 usec
        Avg               101290 usec
        Stdev              17148 usec
        Stdev mean           227 usec

Kernel: 2.6.31-zen2-cfs-3337ea3
Parameters: min_wait=100ms, max_wait=500ms, clients=8
Entries logged: 5880                                 

Wakeup averages
-------------------------------------
        Max                34962 usec
        Avg                 4532 usec
        Stdev               3801 usec
        Stdev mean            50 usec

Work averages
-------------------------------------
        Max               202057 usec
        Avg               119865 usec
        Stdev              16360 usec
        Stdev mean           213 usec

Kernel: 2.6.31-bfs240
Parameters: min_wait=100ms, max_wait=500ms, clients=8
Entries logged: 5448                                 

Wakeup averages
-------------------------------------
        Max                40659 usec
        Avg                11512 usec
        Stdev               9372 usec
        Stdev mean           127 usec

Work averages
-------------------------------------
        Max               152649 usec
        Avg               100517 usec
        Stdev              17549 usec
        Stdev mean           238 usec

Kernel: 2.6.31.1
Parameters: min_wait=100ms, max_wait=500ms, clients=8
Entries logged: 6744

Wakeup averages
-------------------------------------
        Max                54973 usec
        Avg                13978 usec
        Stdev              10848 usec
        Stdev mean           132 usec

Work averages
-------------------------------------
        Max               155076 usec
        Avg                87660 usec
        Stdev              19173 usec
        Stdev mean           233 usec

The correlation is somewhat clear on this test:
* cfs at that commit in zen has much lower latencies than 2.6.31
* bfs has lower wakeup latencies than 2.6.31, but work latencies are closer
* zen2-bfs has lower work latencies than zen2-cfs - cfs = lower wakeup latencies

Basically, huge improvement with zen2-cfs versus 2.6.31 vanilla cfs - zen2-bfs has improvement over 2.6.31-bfs240, zen2-bfs still has lower latencies than zen2-cfs (but it's a MAJOR improvement for cfs)

Anyway, interpret the results :O
kinda strange to see the 2.6.31-bfs versus 2.6.31, and the zen2-bfs versus 2.6.31-bfs (the only thing that really changed is 2.6.32 backports for bfs)

DigitalCorpus · Post by **DigitalCorpus** » Wed Sep 30, 2009 8:03 am

I'll look into the other stuff in about 16 hours when I get home. Crazy shifts at work today and tomorrow. Than you for that heads up about lattency testing. Do I need to enable anything kernel side for that? I run a minimal one if I can get away with it.

cheater1034 wrote:If you're running a server/desktop i would disable dynticks. If you're running X on the server/desktop, set HZ=1000
voluntary preemption is junk, don't use it (you can't use it with bfs since it's disabled in Kconfig when bfs is selected. Full preemption is probably your best bet, no preemption is acceptable too - but if you are running X i'd suggest it.

I have a quad core. I thought it stood to reason that the selected frequency x # of cores/procs would be the real measure of ticks on a system. I'm not looking to run at the very lowest latencies on my system. I'm not looking to run at maximum bandwidth either. Since I can select a range from 100 to 1000 Hz in the Zen config with it seems that the author(s) share this same paradigm (of which you are one, correct?).

What would be a good middle ground? 250Hz, which is effectively 1000Hz? 216Hz (suggested for a quad core), effectively the "magic" 864Hz?

I understand dynamic ticks means that timer interrupts are only triggered when needed, thus can be power saving. I never had a performance issue with them on, nor noticed anything with them off. I have a WattsUp Pro, but never dawned on me to check consumption at the plug iirc. I just find it odd that my system had better latency with dynamic ticks, no preemption, 108Hz, CFS under 2.6.30-zen1 than with what is suggested here. I'll test more soon as I'm about to have my work weekend soon.

timbo · Post by **timbo** » Wed Sep 30, 2009 8:04 am

Hi everyone

Thought I'd give these zen-sources a go...

Added the zen-overlay through layman and compiled the kernel from a blank .config "fresh

", booted and seem's to go well, mmm, needed to copy some photo's from me canon G10, plugged her in all's well till it seemed to stop transferring data and noticed,,,

Sep 30 16:37:56 binklebonk [29941.103638] hub 2-5.1:1.0: state 7 ports 4 chg 0000 evt 0002
Sep 30 16:37:56 binklebonk [29941.103869] hub 2-5.1:1.0: port 1, status 0101, change 0001, 12 Mb/s
Sep 30 16:37:56 binklebonk [29941.214750] hub 2-5.1:1.0: debounce: port 1: total 100ms stable 100ms status 0x101
Sep 30 16:37:56 binklebonk [29941.281890] usb 2-5.1.1: new high speed USB device using ehci_hcd and address 7
Sep 30 16:37:56 binklebonk [29941.366626] usb 2-5.1.1: default language 0x0409
Sep 30 16:37:56 binklebonk [29941.367757] usb 2-5.1.1: udev 7, busnum 2, minor = 134
Sep 30 16:37:56 binklebonk [29941.367762] usb 2-5.1.1: New USB device found, idVendor=04a9, idProduct=318f
Sep 30 16:37:56 binklebonk [29941.367766] usb 2-5.1.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
Sep 30 16:37:56 binklebonk [29941.367770] usb 2-5.1.1: Product: Canon Digital Camera
Sep 30 16:37:56 binklebonk [29941.367773] usb 2-5.1.1: Manufacturer: Canon Inc.
Sep 30 16:37:56 binklebonk [29941.367776] usb 2-5.1.1: SerialNumber: 80A82B2885EC4FD6B179EA7B72EB90B1
Sep 30 16:37:56 binklebonk [29941.367868] usb 2-5.1.1: uevent
Sep 30 16:37:56 binklebonk [29941.367890] usb 2-5.1.1: usb_probe_device
Sep 30 16:37:56 binklebonk [29941.367894] usb 2-5.1.1: configuration #1 chosen from 1 choice
Sep 30 16:37:56 binklebonk [29941.370191] usb 2-5.1.1: adding 2-5.1.1:1.0 (config #1, interface 0)
Sep 30 16:37:56 binklebonk [29941.370221] usb 2-5.1.1:1.0: uevent
Sep 30 16:37:56 binklebonk [29941.370283] drivers/usb/core/inode.c: creating file '007'
Sep 30 16:38:23 binklebonk [29968.902751] usb usb5: usb auto-resume
Sep 30 16:38:23 binklebonk [29968.902756] usb usb5: wakeup_rh
Sep 30 16:38:23 binklebonk [29968.939146] hub 5-0:1.0: hub_resume
Sep 30 16:38:23 binklebonk [29968.939170] hub 5-0:1.0: state 7 ports 2 chg 0000 evt 0000
Sep 30 16:38:23 binklebonk [29968.939522] usb usb7: usb auto-resume
Sep 30 16:38:23 binklebonk [29968.939526] usb usb7: wakeup_rh
Sep 30 16:38:23 binklebonk [29968.976192] hub 7-0:1.0: hub_resume
Sep 30 16:38:23 binklebonk [29968.976216] hub 7-0:1.0: state 7 ports 2 chg 0000 evt 0000
Sep 30 16:38:23 binklebonk [29968.976296] usb usb6: usb auto-resume
Sep 30 16:38:23 binklebonk [29968.976300] usb usb6: wakeup_rh

Odd, what's even more odd if I take out the SD card and put it into my 64,000 type card reader nothing happens, normally Mr KDE would pop up it's usual message.

Recompiled the kernel, make mrpropper, this time I copied my .config files from my gentoo-sources kernel and make oldocofig, all went well rebooted and same thing with the card reader. The system sees it when I boot but nothing when I insert a card...

Sep 30 18:28:11 binklebonk usb-storage: device scan complete
Sep 30 18:28:11 binklebonk scsi 8:0:0:0: Direct-Access Generic USB CF Reader 0.00 PQ: 0 ANSI: 2
Sep 30 18:28:11 binklebonk scsi 8:0:0:1: Direct-Access Generic USB SD Reader 0.00 PQ: 0 ANSI: 2
Sep 30 18:28:11 binklebonk scsi 8:0:0:2: Direct-Access Generic USB MS Reader 0.00 PQ: 0 ANSI: 2
Sep 30 18:28:11 binklebonk scsi 8:0:0:3: Direct-Access Generic USB SM Reader 0.00 PQ: 0 ANSI: 2
Sep 30 18:28:11 binklebonk sd 8:0:0:0: Attached scsi generic sg3 type 0
Sep 30 18:28:11 binklebonk sd 8:0:0:1: Attached scsi generic sg4 type 0
Sep 30 18:28:11 binklebonk sd 8:0:0:2: Attached scsi generic sg5 type 0
Sep 30 18:28:11 binklebonk sd 8:0:0:3: Attached scsi generic sg6 type 0
Sep 30 18:28:11 binklebonk sd 8:0:0:1: [sdd] Attached SCSI removable disk
Sep 30 18:28:11 binklebonk sd 8:0:0:2: [sde] Attached SCSI removable disk
Sep 30 18:28:11 binklebonk sd 8:0:0:3: [sdf] Attached SCSI removable disk
Sep 30 18:28:11 binklebonk sd 8:0:0:0: [sdc] Attached SCSI removable disk

Something strange with usb in kernel or should I look more at my system?

Tim

DigitalCorpus · Post by **DigitalCorpus** » Wed Sep 30, 2009 8:23 am

Sorry for the double post, but even though it is OT, I think that with the extensive testing you all do and the occasional breaking of one's system, I can get a faster response here.

First a side note, sys-fs/reiser4progs-1.0.7 from the zen-overlay never compiles on my server but sys-fs/reiser4progs-1.0.7 from teh normal gentoo repositry works perfectly. Here is a build log and environment log. How can I mask out the one from the zen-overlay until it gets fixed?

Before I test anymore, I need some help resolving an issue. I try and log in via my normal account and I I cannot tell if this is a trace of bash crashing or the kernel oops-ing. Catch is that I can then log in via root without a problem. Not sure if I try root logging in first if it'll still trigger the crash, I cannot reboot atm due to some lengthy video encoding in the background at the moment.

Code: Select all

Sep 29 15:06:18 Atlas sshd[2566]: Accepted publickey for digital from 192.168.128.1 port 62573 ssh2
Sep 29 15:06:18 Atlas sshd[2566]: pam_unix(sshd:session): session opened for user digital by (uid=0)
Sep 29 15:06:18 Atlas kernel: [   33.388802] ------------[ cut here ]------------
Sep 29 15:06:18 Atlas kernel: [   33.388849] Kernel BUG at ffffffff8112aca2 [verbose debug info unavailable]
Sep 29 15:06:18 Atlas kernel: [   33.388899] invalid opcode: 0000 [#1] SMP 
Sep 29 15:06:18 Atlas kernel: [   33.388974] last sysfs file: /sys/devices/pci0000:00/0000:00:1f.5/host3/target3:0:0/3:0:0:0/blo
ck/sdd/queue/nr_requests
Sep 29 15:06:18 Atlas kernel: [   33.389030] CPU 1 
Sep 29 15:06:18 Atlas kernel: [   33.389084] Modules linked in: coretemp it87 hwmon_vid hwmon firmware_class nvidia(P) usbhid fi
rewire_ohci i2c_i801 ehci_hcd uhci_hcd i2c_core firewire_core usbcore sata_sil24 rtc_cmos rtc_core rtc_lib crc_itu_t [last unloa
ded: microcode]
Sep 29 15:06:18 Atlas kernel: [   33.389549] Pid: 2571, comm: bash Tainted: P           2.6.30-zen1 #7 965P-DS3
Sep 29 15:06:18 Atlas kernel: [   33.389599] RIP: 0010:[<ffffffff8112aca2>]  [<ffffffff8112aca2>] 0xffffffff8112aca2
Sep 29 15:06:18 Atlas kernel: [   33.389675] RSP: 0018:ffff880218423938  EFLAGS: 00010246
Sep 29 15:06:18 Atlas kernel: [   33.389721] RAX: 00000000000021b5 RBX: ffffea00076297d0 RCX: 0000000000000002
Sep 29 15:06:18 Atlas kernel: [   33.389771] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88021f9d6000
Sep 29 15:06:18 Atlas kernel: [   33.389806] RBP: ffff880218423978 R08: ffff8802184237f8 R09: ffff88021b5eacd0
Sep 29 15:06:18 Atlas kernel: [   33.389853] R10: 002e626173685f68 R11: 0000000000000001 R12: ffff880218423a38
Sep 29 15:06:18 Atlas kernel: [   33.389903] R13: ffff880219b3bb80 R14: 0000000000001000 R15: 0000000000000002
Sep 29 15:06:18 Atlas kernel: [   33.389953] FS:  00007f19357996f0(0000) GS:ffff88002804e000(0000) knlGS:0000000000000000
Sep 29 15:06:18 Atlas kernel: [   33.390012] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Sep 29 15:06:18 Atlas kernel: [   33.390059] CR2: 0000000002088d38 CR3: 0000000218ce0000 CR4: 00000000000006e0
Sep 29 15:06:18 Atlas kernel: [   33.390100] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
Sep 29 15:06:18 Atlas kernel: [   33.390150] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Sep 29 15:06:18 Atlas kernel: [   33.390200] Process bash (pid: 2571, threadinfo ffff880218422000, task ffff880219c09260)
Sep 29 15:06:18 Atlas kernel: [   33.390256] Stack:
Sep 29 15:06:18 Atlas kernel: [   33.390294]  ffffea00076297d0 0000000000000000 ffffea00076297d0 ffffea00076297d0
Sep 29 15:06:18 Atlas kernel: [   33.390391]  ffff880218423a38 0000000000000000 ffff880219b3bb80 0000000000000000
Sep 29 15:06:18 Atlas kernel: [   33.390538]  ffff8802184239b8 ffffffff8112af68 ffff880218423ba8 ffffea00076297d0
Sep 29 15:06:18 Atlas kernel: [   33.390718] Call Trace:
Sep 29 15:06:18 Atlas kernel: [   33.390757]  [<ffffffff8112af68>] 0xffffffff8112af68
Sep 29 15:06:18 Atlas kernel: [   33.390818]  [<ffffffff8112ae70>] ? 0xffffffff8112ae70
Sep 29 15:06:18 Atlas kernel: [   33.390880]  [<ffffffff8107ab61>] 0xffffffff8107ab61
Sep 29 15:06:18 Atlas kernel: [   33.390941]  [<ffffffff8112a78e>] 0xffffffff8112a78e
Sep 29 15:06:18 Atlas kernel: [   33.390997]  [<ffffffff8111b3bc>] 0xffffffff8111b3bc
Sep 29 15:06:18 Atlas kernel: [   33.391058]  [<ffffffff8110bbc1>] 0xffffffff8110bbc1
Sep 29 15:06:18 Atlas kernel: [   33.391119]  [<ffffffff8107a5e2>] 0xffffffff8107a5e2
Sep 29 15:06:18 Atlas kernel: [   33.391180]  [<ffffffff8107a93d>] 0xffffffff8107a93d
Sep 29 15:06:18 Atlas kernel: [   33.391243]  [<ffffffff8107aa5d>] 0xffffffff8107aa5d
Sep 29 15:06:18 Atlas kernel: [   33.391298]  [<ffffffff81074191>] 0xffffffff81074191
Sep 29 15:06:18 Atlas kernel: [   33.391359]  [<ffffffff810993b2>] 0xffffffff810993b2
Sep 29 15:06:18 Atlas kernel: [   33.391416]  [<ffffffff81050d50>] ? 0xffffffff81050d50
Sep 29 15:06:18 Atlas kernel: [   33.391477]  [<ffffffff81077ed5>] ? 0xffffffff81077ed5
Sep 29 15:06:18 Atlas kernel: [   33.391538]  [<ffffffff810f9406>] ? 0xffffffff810f9406
Sep 29 15:06:18 Atlas kernel: [   33.391595]  [<ffffffff8111afbc>] 0xffffffff8111afbc
Sep 29 15:06:18 Atlas kernel: [   33.391656]  [<ffffffff811190a0>] 0xffffffff811190a0
Sep 29 15:06:18 Atlas kernel: [   33.391717]  [<ffffffff8109a0b5>] 0xffffffff8109a0b5
Sep 29 15:06:18 Atlas kernel: [   33.391779]  [<ffffffff810269d3>] ? 0xffffffff810269d3
Sep 29 15:06:18 Atlas kernel: [   33.391835]  [<ffffffff8109a27c>] 0xffffffff8109a27c
Sep 29 15:06:18 Atlas kernel: [   33.391897]  [<ffffffff8100b2ab>] 0xffffffff8100b2ab
Sep 29 15:06:18 Atlas kernel: [   33.391954] Code: 8b 8d 10 01 00 00 48 39 4b 18 74 2c 49 8b bc 24 80 00 00 00 e8 90 a0 fe ff 4c 89 e7 e8 38 f6 fe ff ba 01 00 08 00 e9 93 fd ff ff <0f> 0b eb fe ab 83 ea 04 e9 25 fe ff ff f6 03 08 0f 84 f4 00 00 
Sep 29 15:06:18 Atlas kernel: [   33.393123] RIP  [<ffffffff8112aca2>] 0xffffffff8112aca2
Sep 29 15:06:18 Atlas kernel: [   33.393184]  RSP <ffff880218423938>
Sep 29 15:06:18 Atlas kernel: [   33.393238] ---[ end trace 1d986197de6acef9 ]---
Sep 29 15:06:18 Atlas sshd[2566]: pam_unix(sshd:session): session closed for user digital

I reverted to a weekly backup from Saturday and the continues to happen. boot and root partitions have no filesystem corruption. Already rebuilt bash and that didn't fix it. Rebuilt kernel after a make clean and that didn't fix it. Don't know what to do next. Running an emerge -e @system @world while I sleep to see if a full rebuild might miraculously fix it. My system will not shutdown cleanly after this btw if that matters

tranquilcool · Post by **tranquilcool** » Wed Sep 30, 2009 9:23 am

what's latest stable version of zen-sources at the moment?
is bfs-240 applied?

thanks.

rahulthewall · Post by **rahulthewall** » Wed Sep 30, 2009 12:06 pm

Can someone please educate me as to what does the warning "clocksource tsc unstable" exactly mean?

Ant P. · Post by **Ant P.** » Wed Sep 30, 2009 12:42 pm

rahulthewall wrote:Can someone please educate me as to what does the warning "clocksource tsc unstable" exactly mean?

You can ignore that, it just means the processor's internal timer is affected by power management so the kernel's using another source.

kernelOfTruth · Post by **kernelOfTruth** » Wed Sep 30, 2009 1:22 pm

@cheater1034:

sorry for the delay !

Part 8 of zen-sources thread created

@Moderators:

please lock part 7 (this thread) thanks !

Official thread: "zen-sources" - Part 7

Testing Performance differences

Re: Testing Performance differences

Re: Testing Performance differences