Messages in this thread | | | Date | Thu, 15 Mar 2012 12:58:57 -0500 | From | Dimitri Sivanich <> | Subject | Re: [PATCH RFC] rcu: Limit GP initialization to CPUs that have been online |
| |
On Wed, Mar 14, 2012 at 09:56:57AM -0700, Paul E. McKenney wrote: > On Wed, Mar 14, 2012 at 08:17:17AM -0700, Paul E. McKenney wrote: > > On Wed, Mar 14, 2012 at 08:08:01AM -0500, Dimitri Sivanich wrote: > > > On Wed, Mar 14, 2012 at 01:40:41PM +0100, Mike Galbraith wrote: > > > > On Wed, 2012-03-14 at 10:24 +0100, Mike Galbraith wrote: > > > > > On Tue, 2012-03-13 at 17:24 -0700, Paul E. McKenney wrote: > > > > > > The following builds, but is only very lightly tested. Probably full > > > > > > of bug, especially when exercising CPU hotplug. > > > > > > > > > > You didn't say RFT, but... > > > > > > > > > > To beat on this in a rotund 3.0 kernel, the equivalent patch would be > > > > > the below? My box may well answer that before you can.. hope not ;-) > > > > > > > > (Darn, it did. Box says boot stall with virgin patch in tip too though. > > > > Wedging it straight into 3.0 was perhaps a tad premature;) > > > > > > I saw the same thing with 3.3.0-rc7+ and virgin patch on UV. Boots fine without the patch. > > > > Right... Bozo here forgot to set the kernel parameters for large-system > > emulation during testing. Apologies for the busted patch, will fix. > > > > And thank you both for the testing!!! > > > > Hey, at least I labeled it "RFC". ;-) > > Does the following work better? It does pass my fake-big-system tests > (more testing in the works).
This one stalls for me at the same place the other one did. Once again, if I remove the patch and rebuild, it boots just fine.
Is there some debug/trace information that you would like me to provide?
> > Thanx, Paul > > ------------------------------------------------------------------------ > > rcu: Limit GP initialization to CPUs that have been online > > The current grace-period initialization initializes all leaf rcu_node > structures, even those corresponding to CPUs that have never been online. > This is harmless in many configurations, but results in 200-microsecond > latency spikes for kernels built with NR_CPUS=4096. > > This commit therefore keeps track of the largest-numbered CPU that has > ever been online, and limits grace-period initialization to rcu_node > structures corresponding to that CPU and to smaller-numbered CPUs. > > Reported-by: Dimitri Sivanich <sivanich@sgi.com> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > diff --git a/kernel/rcutree.c b/kernel/rcutree.c > index c3b05ef..5688443 100644 > --- a/kernel/rcutree.c > +++ b/kernel/rcutree.c > @@ -91,6 +91,8 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); > > static struct rcu_state *rcu_state; > > +int rcu_max_cpu __read_mostly; /* Largest # CPU that has ever been online. */ > + > /* > * The rcu_scheduler_active variable transitions from zero to one just > * before the first task is spawned. So when this variable is zero, RCU > @@ -1129,8 +1131,9 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) > __releases(rcu_get_root(rsp)->lock) > { > unsigned long gp_duration; > - struct rcu_node *rnp = rcu_get_root(rsp); > struct rcu_data *rdp = this_cpu_ptr(rsp->rda); > + struct rcu_node *rnp; > + struct rcu_node *rnp_root = rcu_get_root(rsp); > > WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); > > @@ -1159,26 +1162,28 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) > * completed. > */ > if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) { > - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ > > /* > * Propagate new ->completed value to rcu_node structures > * so that other CPUs don't have to wait until the start > * of the next grace period to process their callbacks. > + * We must hold the root rcu_node structure's ->lock > + * across rcu_for_each_node_breadth_first() in order to > + * synchronize with CPUs coming online for the first time. > */ > rcu_for_each_node_breadth_first(rsp, rnp) { > + raw_spin_unlock(&rnp_root->lock); /* remain disabled. */ > raw_spin_lock(&rnp->lock); /* irqs already disabled. */ > rnp->completed = rsp->gpnum; > raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ > + raw_spin_lock(&rnp_root->lock); /* already disabled. */ > } > - rnp = rcu_get_root(rsp); > - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ > } > > rsp->completed = rsp->gpnum; /* Declare the grace period complete. */ > trace_rcu_grace_period(rsp->name, rsp->completed, "end"); > rsp->fqs_state = RCU_GP_IDLE; > - rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ > + rcu_start_gp(rsp, flags); /* releases root node's ->lock. */ > } > > /* > @@ -2440,6 +2445,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) > unsigned long mask; > struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); > struct rcu_node *rnp = rcu_get_root(rsp); > + struct rcu_node *rnp_init; > > /* Set up local state, ensuring consistent view of global state. */ > raw_spin_lock_irqsave(&rnp->lock, flags); > @@ -2462,6 +2468,16 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) > /* Exclude any attempts to start a new GP on large systems. */ > raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */ > > + /* Initialize any rcu_node structures that will see their first use. */ > + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ > + for (rnp_init = per_cpu_ptr(rsp->rda, rcu_max_cpu)->mynode + 1; > + rnp_init <= rdp->mynode; > + rnp_init++) { > + rnp_init->gpnum = rsp->gpnum; > + rnp_init->completed = rsp->completed; > + } > + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ > + > /* Add CPU to rcu_node bitmasks. */ > rnp = rdp->mynode; > mask = rdp->grpmask; > @@ -2495,6 +2511,8 @@ static void __cpuinit rcu_prepare_cpu(int cpu) > rcu_init_percpu_data(cpu, &rcu_sched_state, 0); > rcu_init_percpu_data(cpu, &rcu_bh_state, 0); > rcu_preempt_init_percpu_data(cpu); > + if (cpu > rcu_max_cpu) > + rcu_max_cpu = cpu; > } > > /* > diff --git a/kernel/rcutree.h b/kernel/rcutree.h > index 1e49c56..afdf410 100644 > --- a/kernel/rcutree.h > +++ b/kernel/rcutree.h > @@ -192,11 +192,13 @@ struct rcu_node { > > /* > * Do a full breadth-first scan of the rcu_node structures for the > - * specified rcu_state structure. > + * specified rcu_state structure. The caller must hold either the > + * ->onofflock or the root rcu_node structure's ->lock. > */ > +extern int rcu_max_cpu; > #define rcu_for_each_node_breadth_first(rsp, rnp) \ > for ((rnp) = &(rsp)->node[0]; \ > - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) > + (rnp) <= per_cpu_ptr((rsp)->rda, rcu_max_cpu)->mynode; (rnp)++) > > /* > * Do a breadth-first scan of the non-leaf rcu_node structures for the
| |