Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+v2\s+1\/2\]\s+sched\:\s+Add\s+cond_resched_rcu_lock\(\)\s+helper\s*$/: 35 ]

Total 35 documents matching your query.

1. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Sat, 4 May 2013 11:03:16 -0700
Very good! Please send the patch along, and I will ack it. Thanx, Paul -- To unsubscribe from this list: send the line "unsubscribe lvs-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx Mo
/html/lvs-devel/2013-05/msg00033.html (12,662 bytes)

2. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Sat, 4 May 2013 10:23:31 +0300 (EEST)
Hello, Works perfectly. Thanks! Tested CONFIG_PREEMPT_RCU=y/n, the errors messages with extra RCU lock. Regards -- Julian Anastasov <ja@xxxxxx> -- To unsubscribe from this list: send the line "unsubs
/html/lvs-devel/2013-05/msg00032.html (12,378 bytes)

3. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Date: Fri, 3 May 2013 20:09:26 +0200
Oh argh.. I completely overlooked that rcu_read_{,un}lock() are NOPs for PREEMPT=n kernels. /me crawls back under his stone.. -- To unsubscribe from this list: send the line "unsubscribe lvs-devel"
/html/lvs-devel/2013-05/msg00031.html (12,134 bytes)

4. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Fri, 3 May 2013 20:47:32 +0300 (EEST)
Hello, It should work. It is a better version of the 2nd variant I mentioned here: http://marc.info/?l=linux-netdev&m=136741839021257&w=2 I'll stick to this version, hope Peter Zijlstra agrees. Playi
/html/lvs-devel/2013-05/msg00030.html (13,371 bytes)

5. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Fri, 3 May 2013 10:34:44 -0700
This happens in only two cases: 1. CONFIG_PREEMPT_RCU=n kernels. But in this case, rcu_read_unlock() and rcu_read_lock() are free, at least for CONFIG_PROVE_LOCKING=n kernels. And if you have CONFIG_
/html/lvs-devel/2013-05/msg00029.html (14,175 bytes)

6. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Date: Fri, 3 May 2013 19:04:47 +0200
It can do quite a number of superfluous rcu_read_unlock()/lock() pairs for voluntary preemption kernels? -- To unsubscribe from this list: send the line "unsubscribe lvs-devel" in the body of a mess
/html/lvs-devel/2013-05/msg00028.html (13,185 bytes)

7. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Fri, 3 May 2013 09:30:45 -0700
OK, after getting some sleep, I might have located the root cause of my confusion yesterday. The key point is that I don't understand why we cannot get the effect we are looking for with the followin
/html/lvs-devel/2013-05/msg00027.html (14,047 bytes)

8. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Fri, 3 May 2013 10:52:36 +0300 (EEST)
Hello, In this case when CONFIG_PREEMPT_RCU is enabled we (RCU) do not touch the preempt counters. Instead, the units are accounted in current->rcu_read_lock_nesting: __rcu_read_lock: current->rcu_re
/html/lvs-devel/2013-05/msg00026.html (12,652 bytes)

9. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Thu, 2 May 2013 15:31:07 -0700
OK, apologies -- I was looking at the calls to __might_sleep() in mainline, and missed the one that you added. Revisiting that, a question: Does this really want to be "1" instead of PREEMPT_OFFSET?
/html/lvs-devel/2013-05/msg00025.html (14,234 bytes)

10. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Thu, 2 May 2013 23:19:12 +0300 (EEST)
Hello, Yes, the different platforms use different bit, that is why I mentioned about my failed attempt at changing hardirq.h. PREEMPT_ACTIVE is always != 0. But I don't understand what do you mean by
/html/lvs-devel/2013-05/msg00024.html (12,771 bytes)

11. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Thu, 2 May 2013 12:34:09 -0700
OK... PREEMPT_ACTIVE's value is usually 0x10000000. Did it change since 3.9? If not, rcu_sleep_check(preempt_offset & PREEMPT_ACTIVE) is the same as rcu_sleep_check(0). Thanx, Paul -- To unsubscribe
/html/lvs-devel/2013-05/msg00023.html (14,929 bytes)

12. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Thu, 2 May 2013 22:24:55 +0300 (EEST)
Hello, Just to clarify about the test with extra rcu_read_lock because above paragraph is very confusing: - The __might_sleep call with PREEMPT_ACTIVE | PREEMPT_RCU_OFFSET just warns with "BUG: sleep
/html/lvs-devel/2013-05/msg00022.html (13,213 bytes)

13. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Thu, 2 May 2013 21:55:54 +0300 (EEST)
Hello, Note that I'm testing on some 9-year old UP system, i.e. 1 CPU. Now I enabled SMP to test CONFIG_TREE_RCU and the results are same. I think, it should be just like the TINY_RCU in terms of the
/html/lvs-devel/2013-05/msg00021.html (14,326 bytes)

14. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Thu, 2 May 2013 10:32:57 -0700
Could you please also try CONFIG_TREE_RCU? Color me confused. are PREEMPT_LOCK_OFFSET and SOFTIRQ_DISABLE_OFFSET. PREEMPT_ACTIVE is normally a high-order bit, above PREEMPT_MASK, SOFTIRQ_MASK, and HA
/html/lvs-devel/2013-05/msg00020.html (19,273 bytes)

15. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Thu, 2 May 2013 18:54:05 +0300 (EEST)
Hello, I implemented your idea. I tested the following patch in 2 variants, TINY_RCU and CONFIG_TREE_PREEMPT_RCU. I see the error if extra rcu_read_lock is added for testing. I'm using the PREEMPT_AC
/html/lvs-devel/2013-05/msg00019.html (16,717 bytes)

16. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Thu, 2 May 2013 13:06:30 +0300 (EEST)
Hello, Looks like CONFIG_DEBUG_ATOMIC_SLEEP selects CONFIG_PREEMPT_COUNT, so PREEMPT_RCU_OFFSET should be 1 in all cases because preempt_disable() adds 1, while for CONFIG_PREEMPT_RCU case rcu_preemp
/html/lvs-devel/2013-05/msg00018.html (13,219 bytes)

17. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Date: Thu, 2 May 2013 09:27:43 +0200
The __might_sleep(__FILE__, __LINE__, PREEMPT_RCU_OFFSET) I posted in the other email just now should deal with this. -- To unsubscribe from this list: send the line "unsubscribe lvs-devel" in the bo
/html/lvs-devel/2013-05/msg00017.html (12,349 bytes)

18. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Date: Thu, 2 May 2013 09:26:24 +0200
__might_sleep(__FILE__, __LINE__, PREEMPT_RCU_OFFSET); \ __cond_resched_rcu(); \ }) Should work I think.. -- To unsubscribe from this list: send the line "unsubscribe lvs-devel" in the body of a mess
/html/lvs-devel/2013-05/msg00016.html (12,219 bytes)

19. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Wed, 1 May 2013 12:04:12 -0700
The above requires that include/linux/sched.h be included. This might be OK, but please check the current intended uses. Thanx, Paul -- To unsubscribe from this list: send the line "unsubscribe lvs-d
/html/lvs-devel/2013-05/msg00015.html (15,695 bytes)

20. Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper (score: 1)
Author: Julian Anastasov <ja@xxxxxx>
Date: Wed, 1 May 2013 21:22:08 +0300 (EEST)
Hello, It is just a barrier() for the non-preempt case. ... I see your goal. But digging into __might_sleep() I see that rcu_sleep_check() will scream for the non-preempt case because we are under rc
/html/lvs-devel/2013-05/msg00014.html (14,515 bytes)


This search system is powered by Namazu