From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Kacur Subject: Re: [ANNOUNCE] 2.6.33-rc8-rt1 Date: Mon, 22 Feb 2010 12:11:28 +0100 Message-ID: <520f0cf11002220311l2a0caa83lf3ae2817b78501b6@mail.gmail.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: LKML , rt-users , Ingo Molnar , Steven Rostedt , Peter Zijlstra , Carsten Emde , Clark Williams , Frank Rowand , Robin Gareus , Gregory Haskins , Philippe Reynes , Fernando Lopez-Lezcano , Will Schmidt , Darren Hart , Jan Blunck , Sven-Thorsten Dietrich , Jon Masters , Mark Knecht , Nick Piggin To: Thomas Gleixner Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org On Mon, Feb 22, 2010 at 12:24 AM, Thomas Gleixner = wrote: > We are pleased to announce the next update to our new preempt-rt > series. > > =A0 =A0- Forward to 2.6.33-rc8 > > Finally I managed to get that beast tamed. > > Some folks were already joking, that my dog ate the 33-rt patch. The > truth is that my reject fixup skills were one line off in the mm/* > code which resulted in -rt eating my files :) > > When I fixed the wreckage of my own stupidty I found out that -rt > triggered a nasty and hard to reproduce mainline scheduler bug, which > refused to reproduce with kernel tracing enabled. Thanks to Peter > Zijlstra for helping me to decode the initial mainline problem and th= e > ones which resulted from fixing the mainline bug! > > It's all fixed now and I'm pretty happy about the state of this > release with the following exceptions: > > =A01) it is only runtime tested on x86_64 (compiles on x86_32, arm, > =A0 =A0powerpc_32/64). > > =A0 =A0I'm going to throw it at my testing infrastructure tomorrow, b= ut I > =A0 =A0wanted to release this before .33-final and of course you folk= s > =A0 =A0are heartely invited to help out with fixing the fallout :) > > =A02) I broke the histogram tracer stuff simply because I got lost in > =A0 =A0the divergence of -rt and mainline kernel/trace/* changes > > =A0 =A0I apologize to Carsten, but I'm sure he will fix that in no ti= me > =A0 =A0as usual > > The current state of the patch on x86_64 is: rock stable! > > =A0 =A0[rt-tests]# chrt -f 1 ./cyclictest -t -a -n -d0 -p80 -i125 > =A0 =A0policy: fifo: loadavg: 509.19 490.53 486.66 364/1055 31899 > > =A0 =A0T: 0 (27682) P:80 I:125 C:1170997397 Min: 2 Act: 3 Avg: 3 Max:= 34 > =A0 =A0T: 1 (27683) P:79 I:125 C:1170997397 Min: 2 Act: 3 Avg: 3 Max:= 34 > > =A0 =A0That's an uptime of ~1.6 days with a load of hackbench, recurs= ive > =A0 =A0grep and extensive networking traffic going on. > > The merge of the spinlock namespace cleanup and the initial > annotations took a big chunk away from the -rt patch size: > > =A0 =A0 =A0 =A0patch-2.6.31.12-rt21.patch =A0 =A0 1680354 > =A0 =A0 =A0 =A0patch-2.6.33-rc8.patch =A0 =A0 =A0 =A0 1179390 > =A0 =A0 =A0 =A0patch-2.6.33-rc8+git.patch =A0 =A0 1067064 > > We are zooming in, but there is still a way to go! > Woohoo! More -rt fun. Unfortunately, I can't log in on my T500 with this kernel though. The following shows-up on my serial console. ------------[ cut here ]------------ WARNING: at /home/jkacur/rt.linux.git/net/mac80211/rx.c:2467 ieee80211_= rx+0x4c/0 x721 [mac80211]() Hardware name: 2241B48 Modules linked in: bridge stp bnep sco btusb l2cap crc16 bluetooth sunr= pc ipt_RE JECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJ= ECT xt_tc pudp nf_conntrack_ipv6 xt_state ip6table_filter ip6_tables x_tables ipv= 6 cpufreq _ondemand acpi_cpufreq ext3 jbd mbcache dm_mirror dm_region_hash dm_log= dm_multi path scsi_dh dm_mod kvm_intel kvm uinput arc4 ecb snd_hda_codec_conexan= t iwlagn snd_hda_intel iwlcore snd_hda_codec snd_hwdep snd_seq_dummy mac80211 sn= d_seq_oss snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss th= inkpad_ac pi snd_pcm firewire_ohci firewire_core hwmon video ppdev tpm_tis cfg802= 11 sr_mod battery wmi ricoh_mmc parport_pc sg tpm cdrom tpm_bios button ac ata_g= eneric e1 000e iTCO_wdt snd_timer sdhci_pci pata_acpi sdhci i2c_i801 i2c_core par= port mmc_ core iTCO_vendor_support snd joydev snd_page_alloc pcspkr intel_agp sou= ndcore cr c_itu_t rfkill output ahci libata sd_mod scsi_mod crc_t10dif xfs export= fs uhci_h cd ohci_hcd ehci_hcd [last unloaded: microcode] Pid: 10, comm: sirq-tasklet/0 Not tainted 2.6.33-rc8-rt1-debug #1 Call Trace: [] ? ieee80211_rx+0x4c/0x721 [mac80211] [] warn_slowpath_common+0x77/0xa4 [] warn_slowpath_null+0xf/0x11 [] ieee80211_rx+0x4c/0x721 [mac80211] [] ? iwl_led_pattern+0x17a/0x189 [iwlcore] [] ? free_compound_page+0x16/0x18 [] ? iwl_leds_background+0x66/0x219 [iwlcore] [] iwl_rx_reply_rx+0xc29/0xc5a [iwlcore] [] ? trace_hardirqs_on+0xd/0xf [] ? _raw_spin_unlock_irqrestore+0x4c/0x68 [] ? unmap_single+0x27/0x4f [] iwl_rx_handle+0x2a0/0x48d [iwlagn] [] ? _raw_spin_unlock_irqrestore+0x4c/0x68 [] iwl_irq_tasklet+0x5a3/0x73f [iwlagn] [] __tasklet_action+0x8f/0xfd [] tasklet_action+0x7c/0x85 [] run_ksoftirqd+0x18e/0x2d5 [] ? run_ksoftirqd+0x0/0x2d5 [] kthread+0x8c/0x94 [] ? _raw_spin_unlock+0x30/0x4b [] kernel_thread_helper+0x4/0x10 [] ? restore_args+0x0/0x30 [] ? kthread+0x0/0x94 [] ? kernel_thread_helper+0x0/0x10 ---[ end trace 01358557eee38037 ]--- Thanks