Nathan Lynch writes:
> Michael Ellerman writes:
>> Tyrel Datwyler writes:
>>> On 8/11/20 6:20 PM, Nathan Lynch wrote:
+static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb)
+{
+ const unsigned int resched_interval = 20;
+
+ BUG_ON(lmb < drmem_inf
Michael Ellerman writes:
> Tyrel Datwyler writes:
>> On 8/11/20 6:20 PM, Nathan Lynch wrote:
>>>
>>> +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb)
>>> +{
>>> + const unsigned int resched_interval = 20;
>>> +
>>> + BUG_ON(lmb < drmem_info->lmbs);
>>> + BUG_ON(lmb >
Tyrel Datwyler writes:
> On 8/11/20 6:20 PM, Nathan Lynch wrote:
>> The drmem lmb list can have hundreds of thousands of entries, and
>> unfortunately lookups take the form of linear searches. As long as
>> this is the case, traversals have the potential to monopolize the CPU
>> and provoke lockup
On 8/11/20 6:20 PM, Nathan Lynch wrote:
> The drmem lmb list can have hundreds of thousands of entries, and
> unfortunately lookups take the form of linear searches. As long as
> this is the case, traversals have the potential to monopolize the CPU
> and provoke lockup reports, workqueue stalls, an
Le 12/08/2020 à 15:46, Nathan Lynch a écrit :
Hi Christophe,
Christophe Leroy writes:
+static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb)
+{
+ const unsigned int resched_interval = 20;
+
+ BUG_ON(lmb < drmem_info->lmbs);
+ BUG_ON(lmb >= drmem_info->lmbs
Hi Christophe,
Christophe Leroy writes:
>> +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb)
>> +{
>> +const unsigned int resched_interval = 20;
>> +
>> +BUG_ON(lmb < drmem_info->lmbs);
>> +BUG_ON(lmb >= drmem_info->lmbs + drmem_info->n_lmbs);
>
> BUG_ON() shall b
Le 12/08/2020 à 03:20, Nathan Lynch a écrit :
The drmem lmb list can have hundreds of thousands of entries, and
unfortunately lookups take the form of linear searches. As long as
this is the case, traversals have the potential to monopolize the CPU
and provoke lockup reports, workqueue stalls,
The drmem lmb list can have hundreds of thousands of entries, and
unfortunately lookups take the form of linear searches. As long as
this is the case, traversals have the potential to monopolize the CPU
and provoke lockup reports, workqueue stalls, and the like unless
they explicitly yield.
Rather
