Thread (7 messages) 7 messages, 3 authors, 2014-04-01

Re: [BUGREPORT] Tasklet scheduled issue in Linux 3.4.x-rt

From: Thomas Gleixner <hidden>
Date: 2014-03-31 20:50:14
Also in: lkml

On Mon, 3 Mar 2014, Yijing Wang wrote:
Hi list,
   I found a tasklet related issue in linux-stable-rt 3.4.

And after I revert following commit, the test result seems ok(test lasted 40hours).

commit 0d9f73fc1e7270a3f8709c59c913408153d9d9f8
This commit id does not exist in the official stable rt tree.
Author: Ingo Molnar [off-list ref]
Date:   Tue Nov 29 20:18:22 2011 -0500

    tasklet: Prevent tasklets from going into infinite spin in RT
 
I test FC driver IO in this kernel, and after a few hours test, FC IO will abort, I found a lot of tasklet WARNING Call Trace in kernel message,like:

[2012-03-26 18:55:43][  929.252289] ------------[ cut here ]------------
[2012-03-26 18:55:43][  929.252312] WARNING: at kernel/softirq.c:773 __tasklet_action+0x51/0x1a0()
There is no warning at line 773 in any official linux-stable-rt 3.4.
[2012-03-26 18:55:43][  929.252314] Hardware name: Romley
[2012-03-26 18:55:43][  929.252316] Modules linked in: isd_fid(O) ivs_edft(O) ivs_emp(O) ivs_xnet(O) isd_rds(O) isd_idm(O) isd_dft(O) isd_base(O) sdm(O) isd_cmm(O) isd_ibc(O) isd_lib(O) xve_hab(PO) xve_net(PO) xve_cls_msg_filter(PO) xve_dscp(PO) pagepool(PO) iod(O) cmm(PO) util(PO) intel_t10(PO) itest_nid(PO) dmi(PO) bsp_adapter(PO) mpa(O) ipmi_si ipmi_devintf ipmi_msghandler iscsi_sw(PO) iscsi_prot(O) iscsi_seg(PO) iscsi_comm(PO) iscsi_initiator(PO) 8192cu(O) pciehp(PO) pcieaer(PO) pciecore(PO) drvinstallthird(PO) quark(O) sal(O) pmsas(O) foe(O) lfcoe(O) libfc(O) ib_uverbs(O) ibtgt(O) ib_srpt(O) ib_cm(O) ib_sa(O) mlx4_ib(O) ib_umad(O) ib_mad(O) mlx4_core(O) ib_core(O) drvtom(O) cxgb4(O) drvtoecore(O) fcdrv(PO) unflowlevel(PO) unfcommon(O) drvmml(PO) scsi_transport_fc scsi_tgt memtest(PO
 ) drv_iosubsys_ini(O) iocount(O) bsp_mml(PO) agetty_query(PO) cpufreq_powersave af_packet nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_filter ip6_tables xt_limit xt_tcpudp xt_multiport nf_conntr!
ack_ipv4
 nf_defrag_ipv4 xt_state nf_conntrack usr_cache(O) acpi_cpufreq mperf processor thermal_sys sg hwmon iptable_filter ip_tables x_tables ixgbe(O) igb(O) bonding(O) tg(O) netmgmt(O) drvinstall(PO) dal(PO) dca usb_storage(O) uhci_hcd ehci_hcd usbcore(O) usb_common sata_mml(O) ahci(O) libata(O) satahp(O) drvframe(PO) sd_mod crc_t10dif scsi_mod agetty_interface(PO) ext3 jbd mbcache nvram_printk(PO) os_feeddog(PO) os_debug(O) osp_proc(PO) os_rnvramdev(PO) vos(O) bsp(PO) os_die_handler(O) os_oom_handler(O) os_panic_handler(O) biosnvramdriver(O) kbox(O)
[2012-03-26 18:55:43][  929.252460] Pid: 17495, comm: 3th SioT Tainted: P           O 3.4.24.15-0.11-default #1
You have loaded a gazillion of proprietary and out of tree modules and
your kernel is tainted 'P'.

None of our problems. See:

 http://lwn.net/1999/0211/a/lt-binary.html

 https://lwn.net/Articles/287056/

I'm in a good mood today and give you some hints:

- Ingos patch is correct and always has been for RT.

- We had not a single bug report against this in almost 10 years.

- File your bugs to those who abuse our work and violate our license.

Case closed.

     tglx
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help