On Mon, 10 May 2021 16:03:06 Xing Zhengjun wrote:
>On 4/30/2021 2:43 PM, Hillf Danton wrote:
>> On Fri, 30 Apr 2021 13:33:57 +0800 Xing Zhengjun wrote:
>>>
>>> I use my compaction test case to test it, 1/10 ratio can reproduce 100ms
>>> sleep.
>>>
>>> 60) @ 103942.6 us | shrink_node();
>>>
>>> 60) @ 103795.8 us | shrink_node();
>>
>> Thanks for your test.
>>
>> In bid to cut the number of 100ms sleepers further down, add another place
>> for them to nap by flushing lru cache before falling in sleep, instead of
>> mulling why 50ms or 10ms is more adequate.
>>
>> Alternatively, and simpler IMHO, take a 5ms nap one time until !tmi.
>>
>> --- y/mm/vmscan.c
>> +++ x/mm/vmscan.c
>> @@ -118,6 +118,9 @@ struct scan_control {
>> /* The file pages on the current node are dangerously low */
>> unsigned int file_is_tiny:1;
>>
>> + unsigned int file_tmi:1; /* too many isolated */
>> + unsigned int anon_tmi:1;
>> +
>> /* Allocation order */
>> s8 order;
>>
>> @@ -2092,6 +2095,22 @@ static int current_may_throttle(void)
>> bdi_write_congested(current->backing_dev_info);
>> }
>>
>> +static void set_sc_tmi(struct scan_control *sc, bool file, int tmi)
>> +{
>> + if (file)
>> + sc->file_tmi = tmi;
>> + else
>> + sc->anon_tmi = tmi;
>> +}
>> +
>> +static bool is_sc_tmi(struct scan_control *sc, bool file)
>> +{
>> + if (file)
>> + return sc->file_tmi != 0;
>> + else
>> + return sc->anon_tmi != 0;
>> +}
>> +
>> /*
>> * shrink_inactive_list() is a helper for shrink_node(). It returns the number
>> * of reclaimed pages
>> @@ -2109,11 +2128,23 @@ shrink_inactive_list(unsigned long nr_to
>> enum vm_event_item item;
>> struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>> bool stalled = false;
>> + bool drained = false;
>>
>> while (unlikely(too_many_isolated(pgdat, file, sc))) {
>> if (stalled)
>> return 0;
>>
>> + if (!is_sc_tmi(sc, file)) {
>> + set_sc_tmi(sc, file, 1);
>> + return 0;
>> + }
>> +
>> + if (!drained) {
>> + drained = true;
>> + lru_add_drain_all();
>> + continue;
>> + }
>> +
>> /* wait a bit for the reclaimer. */
>> msleep(100);
>> stalled = true;
>> @@ -2123,6 +2154,9 @@ shrink_inactive_list(unsigned long nr_to
>> return SWAP_CLUSTER_MAX;
>> }
>>
>> + if (is_sc_tmi(sc, file))
>> + set_sc_tmi(sc, file, 0);
>> +
>> lru_add_drain();
>>
>> spin_lock_irq(&lruvec->lru_lock);
>>
>
>I tried the patch, it still can reproduce the 100ms sleep.
>
>52) @ 103829.8 us | shrink_lruvec();
Thanks for you data.
What we learn from it is a 5ms nap a time and no longer than 100ms in total
is an acceptable option.
Hillf
