tag:blogger.com,1999:blog-6469704299235308349.post1355759293702853013..comments2024-03-28T15:50:13.644+11:00Comments on -ck hacking: BFS 497, linux-4.7-ck4ckhttp://www.blogger.com/profile/02904761195451530213noreply@blogger.comBlogger33125tag:blogger.com,1999:blog-6469704299235308349.post-53921474332043651782016-09-22T23:46:14.931+10:002016-09-22T23:46:14.931+10:00Thanks Pedro. Added to the pending/ director and w...Thanks Pedro. Added to the pending/ director and will go in the next release.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-5641592320241445332016-09-21T08:21:45.941+10:002016-09-21T08:21:45.941+10:00Con, kernel build fail with bfs497 and all the pat...Con, kernel build fail with bfs497 and all the patches in pending applied when SMT_NICE=disabled (SMT_NICE=y builds fine).<br />I managed to build successfully with the following modification. However I'm not sure it is correct.<br /><br />Pedro<br /><br />@@ -745,6 +745,8 @@<br /> /* Sorry, you lose */<br /> return false;<br /> }<br />+#else<br />+#define smt_schedule(p, this_rq) (true)<br /> #endif /* CONFIG_SMT_NICE */<br /> #ifdef CONFIG_SMP<br /> /*Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-60271773360652500982016-09-21T07:30:06.757+10:002016-09-21T07:30:06.757+10:00I will, given it fixes the remaining freezes, but ...I will, given it fixes the remaining freezes, but I was waiting to see if there were any other changes that needed to go in.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-55382519861190296532016-09-21T03:57:56.005+10:002016-09-21T03:57:56.005+10:00Are you plan to release ck5?Are you plan to release ck5?Anonymoushttps://www.blogger.com/profile/17986933114644119267noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-15766705730333776952016-09-21T03:09:40.418+10:002016-09-21T03:09:40.418+10:00This comment has been removed by the author.Anonymoushttps://www.blogger.com/profile/17986933114644119267noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-72176728260900855802016-09-20T16:41:13.099+10:002016-09-20T16:41:13.099+10:00OK, will check, thanks.OK, will check, thanks.Oleksandr Natalenkohttps://www.blogger.com/profile/12098091624630953604noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-87432617977837040152016-09-20T08:47:41.096+10:002016-09-20T08:47:41.096+10:00No you have NOT applied the patch I have directed ...No you have NOT applied the patch I have directed you to.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-52774444371380428322016-09-20T08:47:09.197+10:002016-09-20T08:47:09.197+10:00There is an extra patch in the pending/ directory ...There is an extra patch in the pending/ directory that should fix this.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-54726656986990114942016-09-20T08:46:34.914+10:002016-09-20T08:46:34.914+10:00Did you check the pending/ directory? The fix in t...Did you check the pending/ directory? The fix in there should do the trick.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-44012941737649139042016-09-20T05:54:54.261+10:002016-09-20T05:54:54.261+10:00Con, broken ARM build reported.
https://kojipkgs....Con, broken ARM build reported.<br /><br />https://kojipkgs.fedoraproject.org//work/tasks/6478/15706478/build.log<br /><br />Could you please take a look at it?<br /><br />===<br />kernel/sched/bfs.c: In function 'context_switch':<br />kernel/sched/bfs.c:2079:3: error: implicit declaration of function 'switch_mm_irqs_off' [-Werror=implicit-function-declaration]<br /> switch_mm_irqs_off(oldmm, mm, next);<br /> ^~~~~~~~~~~~~~~~~~<br />===Oleksandr Natalenkohttps://www.blogger.com/profile/12098091624630953604noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-11724921513223608582016-09-20T04:55:05.851+10:002016-09-20T04:55:05.851+10:00Ok, but
$ dmesg | grep -i "BFS CPU"
[ ...Ok, but<br /><br />$ dmesg | grep -i "BFS CPU"<br />[ 0.736436] BFS CPU scheduler v0.497 by Con Kolivas.<br /><br />and<br /><br />$ uname -r<br />4.7.4-ck4<br /><br />Which means I already had this path applied.Anonymoushttps://www.blogger.com/profile/17986933114644119267noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-31792447031989605472016-09-20T03:59:39.698+10:002016-09-20T03:59:39.698+10:00On Haswell E here. I'm running with the perfor...On Haswell E here. I'm running with the performance governor turned on. Though not sure if it's getting initialized properly. In the boot logs I receive "ENERGY_PERF_BIAS: Set to 'normal', was 'performance'." Though, cpupower still shows the governor as performance.<br /><br />The only thing I noticed with the freeze is it happens if I have a long running process taking up all of the cores, and startup another process that also requires heavy cpu usage.<br /><br />This is how it always happens for me. CLion is loading a particularly large cmake file. (Unreal just uses one giant cmake file) Then in Virtualbox I start up a Windows 10 VM. After a few seconds I freeze. It also happens if Discord is running during heavy cpu use. <br />zarhttps://www.blogger.com/profile/11802628129636689039noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-77611340461483260832016-09-19T22:08:22.957+10:002016-09-19T22:08:22.957+10:00Hi, I have tried BFS with 4.7.4 kernel and it work...Hi, I have tried BFS with 4.7.4 kernel and it works good, but there is some "freezing" lag when cpu is on load and I try to change song in player. Can that be solved somehow ? Thanks.Anonymoushttps://www.blogger.com/profile/01638322095138521537noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-31180118942680658552016-09-19T10:38:20.294+10:002016-09-19T10:38:20.294+10:00That's probably related to the bug that this p...That's probably related to the bug that this patch fixes: <a href="http://ck.kolivas.org/patches/bfs/4.0/4.7/Pending/bfs497-revert-othercpufreq.patch" rel="nofollow">bfs497-revert-othercpufreq.patch</a>ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-68556134100068919022016-09-19T08:08:10.112+10:002016-09-19T08:08:10.112+10:00I hit that kind of bug:
[ 202.694145] INFO: rcu_...I hit that kind of bug:<br /><br />[ 202.694145] INFO: rcu_preempt detected stalls on CPUs/tasks:<br />[ 202.694150] Tasks blocked on level-0 rcu_node (CPUs 0-3): P4030<br />[ 202.694151] (detected by 3, t=60002 jiffies, g=25053, c=25052, q=1020526)<br />[ 202.694154] baloo_file_extr R running task 0 4030 3950 0x00000000<br />[ 202.694156] ffff880077433e00 ffff8800414e1e70 ffff880197baa640 0000000200016900<br />[ 202.694158] ffff8800414e1980 ffff8800414e3fc0 ffff880077434000 ffff88019ed16940<br />[ 202.694160] 0000000000000000 ffff8800414e1980 0000000000000000 ffff880077433e18<br />[ 202.694161] Call Trace:<br />[ 202.694168] [] preempt_schedule_common+0x1f/0x40<br />[ 202.694170] [] preempt_schedule+0x26/0x30<br />[ 202.694172] [] ___preempt_schedule+0x16/0x18<br />[ 202.694174] [] _raw_spin_unlock_irqrestore+0x26/0x30<br />[ 202.694176] [] __sched_setscheduler.constprop.43+0x2c2/0x520<br />[ 202.694179] [] ? __do_page_fault+0x1f5/0x510<br />[ 202.694180] [] do_sched_setscheduler+0x80/0xc0<br />[ 202.694182] [] sys_sched_setscheduler+0x12/0x20<br />[ 202.694183] [] entry_SYSCALL_64_fastpath+0x1a/0xa4<br />[ 202.694184] baloo_file_extr R running task 0 4030 3950 0x00000000<br />[ 202.694186] ffff880077433e00 ffff8800414e1e70 ffff880197baa640 0000000200016900<br />[ 202.694187] ffff8800414e1980 ffff8800414e3fc0 ffff880077434000 ffff88019ed16940<br />[ 202.694188] 0000000000000000 ffff8800414e1980 0000000000000000 ffff880077433e18<br />[ 202.694190] Call Trace:<br />[ 202.694192] [] preempt_schedule_common+0x1f/0x40<br />[ 202.694193] [] preempt_schedule+0x26/0x30<br />[ 202.694194] [] ___preempt_schedule+0x16/0x18<br />[ 202.694196] [] _raw_spin_unlock_irqrestore+0x26/0x30<br />[ 202.694197] [] __sched_setscheduler.constprop.43+0x2c2/0x520<br />[ 202.694198] [] ? __do_page_fault+0x1f5/0x510<br />[ 202.694200] [] do_sched_setscheduler+0x80/0xc0<br />[ 202.694201] [] sys_sched_setscheduler+0x12/0x20<br />[ 202.694203] [] entry_SYSCALL_64_fastpath+0x1a/0xa4<br />Anonymoushttps://www.blogger.com/profile/17986933114644119267noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-12039306960688718842016-09-17T02:53:51.561+10:002016-09-17T02:53:51.561+10:00Works great for me, feels faster. Gentoo-4.7.4-ck...Works great for me, feels faster. Gentoo-4.7.4-ck, Haswell, nvidia, intel graphics onboard. Thanks for the great work!Harold Naparstnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-44054305065148813312016-09-16T16:55:11.799+10:002016-09-16T16:55:11.799+10:00Then are you sure you're actually blaming the ...Then are you sure you're actually blaming the right thing? Could be unrelated screwage with Discord. You could also try disabling interactive mode in the interim which won't require a new kernel.<br /><br />After that, add the two patches in the testing directory. They add a tunable that will allow the cpufreq load estimator to test a variety of different mechanisms. <br />You can set values from 0-5 in:<br />/proc/sys/kernel/smt_load<br />3 is how ck4 is set. Try 0 and 5.<br />ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-21587778218707269492016-09-16T16:43:53.740+10:002016-09-16T16:43:53.740+10:00Gah. Can you try a patch then instead?Gah. Can you try a patch then instead?ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-58534639172681576442016-09-16T12:53:34.606+10:002016-09-16T12:53:34.606+10:00Interesting and no doubt related to the cpufreq ch...Interesting and no doubt related to the cpufreq changes. Which governor are you using? pstates? I assume you have hyperthread enabled on your machine as well? If you know how to, try briefly setting the pstate governor to performance instead of powersave. Additionally try disabling hyperthreading in your bios temporarily. Neither of these is a solution, but to help me diagnose what the issue might be.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-71418138074491175712016-09-16T00:32:19.327+10:002016-09-16T00:32:19.327+10:00Min FPS are notably higher with bfs490 and bfs497....Min FPS are notably higher with bfs490 and bfs497. So we can expect that games will be smoother with new bfs?<br /><br />Thank you allAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-77926195558034615502016-09-15T22:37:55.596+10:002016-09-15T22:37:55.596+10:00I have finished the code of my embedded version an...I have finished the code of my embedded version and new implementation of skip list for BFS. In short, there is improvement comparing to the baseline version. If you are instersting, please visit http://cchalpha.blogspot.com/2016/09/about-skip-list-in-bfs.html and http://cchalpha.blogspot.com/2016/09/new-implementaion-of-skip-list-for-bfs.html for detail.Alfred Chenhttps://www.blogger.com/profile/03164306846702841944noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-20260013149006921562016-09-15T07:38:06.861+10:002016-09-15T07:38:06.861+10:00I've put the rq latencies results.
cfs has bee...I've put the rq latencies results.<br />cfs has been tested with SCHED_AUTOGROUP disabled. Both kernels were using acpi-cpufreq+performance governor.<br /><br />PedroAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-71853476468134736852016-09-15T05:37:20.494+10:002016-09-15T05:37:20.494+10:00I have tested gaming performance, sorta, using Uni...I have tested gaming performance, sorta, using Unigine Valley, system config & results are there: https://docs.google.com/spreadsheets/d/1EayezAsGlJdXjZbS3b9m7YtvtRF-DJ3xrT3hYCvfymQ/edit?usp=sharing<br /><br />If that's of any use :)<br /><br />br, EduardoAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-49717566916203502362016-09-15T05:07:26.169+10:002016-09-15T05:07:26.169+10:00I am the one from Arch forum who had problems usin...I am the one from Arch forum who had problems using rsync to backup ~22G while running linux-ck-piledriver 4.7.3. I am now running rsync tests with Graysky's latest release, 4.7.3-5, from linux-ck repo, and so far after hours I haven't encountered freezes.<br /><br />Good job! mclangnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-37150891655294078822016-09-15T04:56:20.237+10:002016-09-15T04:56:20.237+10:00the version without the patch is working perfectly...the version without the patch is working perfectly in my machine, thanks for your work con, I couldn't test the patch because it' isn't in the repo, but for me it isn't any need of use because the bfs 497 is perfect stable and reliable included temps(but it is colder in the city that days too xD)alberto gomez marinhttps://www.blogger.com/profile/17503198631333546101noreply@blogger.com