| Message ID | 1463659121-84124-1-git-send-email-puck.chen@hisilicon.com |
|---|---|
| State | New |
| Headers | show |
On 2016/5/20 1:45, Vlastimil Babka wrote: > On 19.5.2016 19:23, Hugh Dickins wrote: >> On Thu, 19 May 2016, Vlastimil Babka wrote: >>> On 05/19/2016 02:11 PM, Vlastimil Babka wrote: >>>> On 05/19/2016 01:58 PM, Chen Feng wrote: >>>>> While testing the kcompactd in my platform 3G MEM only DMA ZONE. >>>>> I found the kcompactd never wakeup. It seems the zoneindex >>>>> has already minus 1 before. So the traverse here should be <=. >>>> >>>> Ouch, thanks! >>>> >>>>> Signed-off-by: Chen Feng <puck.chen@hisilicon.com> >>>> >>>> Fixes: 0f87baf4f7fb ("mm: wake kcompactd before kswapd's short sleep") >>> >>> Bah, not that one. >>> >>> Fixes: accf62422b3a ("mm, kswapd: replace kswapd compaction with waking >>> up kcompactd") >>> >>>> Cc: stable@vger.kernel.org >>>> Acked-by: Vlastimil Babka <vbabka@suse.cz> >>>> >>>>> --- >>>>> mm/compaction.c | 2 +- >>>>> 1 file changed, 1 insertion(+), 1 deletion(-) >>>>> >>>>> diff --git a/mm/compaction.c b/mm/compaction.c >>>>> index 8fa2540..e5122d9 100644 >>>>> --- a/mm/compaction.c >>>>> +++ b/mm/compaction.c >>>>> @@ -1742,7 +1742,7 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) >>>>> struct zone *zone; >>>>> enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx; >>>>> >>>>> - for (zoneid = 0; zoneid < classzone_idx; zoneid++) { >>>>> + for (zoneid = 0; zoneid <= classzone_idx; zoneid++) { >>>>> zone = &pgdat->node_zones[zoneid]; >>>>> >>>>> if (!populated_zone(zone)) >> >> Ignorant question: kcompactd_do_work() just below has a similar loop: > Yes, my mistake. > You spelled "Important" wrong. > >> should that one be saying "zoneid <= cc.classzone_idx" too? > > Yes. Chen, can you send updated patch (also with the ack/cc/fixes tags I added?) > OK, I will send it out soon. > Thanks! > >> Hugh >> > > > . >
On 2016/5/20 1:45, Vlastimil Babka wrote: > On 19.5.2016 19:23, Hugh Dickins wrote: >> On Thu, 19 May 2016, Vlastimil Babka wrote: >>> On 05/19/2016 02:11 PM, Vlastimil Babka wrote: >>>> On 05/19/2016 01:58 PM, Chen Feng wrote: >>>>> While testing the kcompactd in my platform 3G MEM only DMA ZONE. >>>>> I found the kcompactd never wakeup. It seems the zoneindex >>>>> has already minus 1 before. So the traverse here should be <=. >>>> >>>> Ouch, thanks! >>>> >>>>> Signed-off-by: Chen Feng <puck.chen@hisilicon.com> >>>> >>>> Fixes: 0f87baf4f7fb ("mm: wake kcompactd before kswapd's short sleep") >>> >>> Bah, not that one. >>> >>> Fixes: accf62422b3a ("mm, kswapd: replace kswapd compaction with waking >>> up kcompactd") >>> >>>> Cc: stable@vger.kernel.org >>>> Acked-by: Vlastimil Babka <vbabka@suse.cz> >>>> >>>>> --- >>>>> mm/compaction.c | 2 +- >>>>> 1 file changed, 1 insertion(+), 1 deletion(-) >>>>> >>>>> diff --git a/mm/compaction.c b/mm/compaction.c >>>>> index 8fa2540..e5122d9 100644 >>>>> --- a/mm/compaction.c >>>>> +++ b/mm/compaction.c >>>>> @@ -1742,7 +1742,7 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) >>>>> struct zone *zone; >>>>> enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx; >>>>> >>>>> - for (zoneid = 0; zoneid < classzone_idx; zoneid++) { >>>>> + for (zoneid = 0; zoneid <= classzone_idx; zoneid++) { >>>>> zone = &pgdat->node_zones[zoneid]; >>>>> >>>>> if (!populated_zone(zone)) >> >> Ignorant question: kcompactd_do_work() just below has a similar loop: > > You spelled "Important" wrong. > >> should that one be saying "zoneid <= cc.classzone_idx" too? > > Yes. Chen, can you send updated patch (also with the ack/cc/fixes tags I added?) > kcompactd_do_work() This fix already added by Andrew Morton <akpm@linux-foundation.org> I will not sent it. > Thanks! > >> Hugh >> > > > . >
diff --git a/mm/compaction.c b/mm/compaction.c index 8fa2540..e5122d9 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1742,7 +1742,7 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) struct zone *zone; enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx; - for (zoneid = 0; zoneid < classzone_idx; zoneid++) { + for (zoneid = 0; zoneid <= classzone_idx; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone))
While testing the kcompactd in my platform 3G MEM only DMA ZONE. I found the kcompactd never wakeup. It seems the zoneindex has already minus 1 before. So the traverse here should be <=. Signed-off-by: Chen Feng <puck.chen@hisilicon.com> --- mm/compaction.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 1.9.1