Vivek Goyal wrote:
> On Wed, May 13, 2009 at 10:39:07AM +0800, Gui Jianfeng wrote:
>> Vivek Goyal wrote:
>> ...
>>>
>>> +/*
>>> + * traverse through all the io_groups associated with this cgroup and calculate
>>> + * the aggr disk time received by all the groups on respective disks.
>>> + */
>>> +static u64 calculate_aggr_disk_time(struct io_cgroup *iocg)
>>> +{
>>> + struct io_group *iog;
>>> + struct hlist_node *n;
>>> + u64 disk_time = 0;
>>> +
>>> + rcu_read_lock();
>> This function is in slow-path, so no need to call rcu_read_lock(), just need to ensure
>> that the caller already holds the iocg->lock.
>>
>
> Or can we get rid of requirement of iocg_lock here and just read the io
> group data under rcu read lock? Actually I am wondering why do we require
> an iocg_lock here. We are not modifying the rcu protected list. We are
> just traversing through it and reading the data.
Yes, i think removing the iocg->lock from caller(io_cgroup_disk_time_read())
is a better choice.
>
> Thanks
> Vivek
>
>>> + hlist_for_each_entry_rcu(iog, n, &iocg->group_data, group_node) {
>>> + /*
>>> + * There might be groups which are not functional and
>>> + * waiting to be reclaimed upon cgoup deletion.
>>> + */
>>> + if (rcu_dereference(iog->key))
>>> + disk_time += iog->entity.total_service;
>>> + }
>>> + rcu_read_unlock();
>>> +
>>> + return disk_time;
>>> +}
>>> +
>> --
>> Regards
>> Gui Jianfeng
>
>
>
--
Regards
Gui Jianfeng
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel
