Re: [PATCH RFC] mm, proc: add PcpFree to meminfo

[Kefeng Wang]

On 2022/8/16 18:50, Greg Kroah-Hartman wrote:
> On Tue, Aug 16, 2022 at 06:11:18PM +0800, Kefeng Wang wrote:
> > On 2022/8/16 17:16, Greg Kroah-Hartman wrote:
> > > On Tue, Aug 16, 2022 at 04:44:26PM +0800, Kefeng Wang wrote:
> > > > From: Liu Shixin <liushixin2@xxxxxxxxxx>
> > > >
> > > > The page on pcplist could be used, but not counted into memory free or
> > > > avaliable, and pcp_free is only showed by show_mem(). Since commit
> > > > d8a759b57035 ("mm, page_alloc: double zone's batchsize"), there is a
> > > > significant decrease in the display of free memory, with a large number
> > > > of cpus and nodes, the number of pages in the percpu list can be very
> > > > large, so it is better to let user to know the pcp count.
> > > >
> > > > Signed-off-by: Liu Shixin <liushixin2@xxxxxxxxxx>
> > > > Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
> > > > ---
> > > >    drivers/base/node.c | 14 +++++++++++++-
> > > >    fs/proc/meminfo.c   |  9 +++++++++
> > > >    2 files changed, 22 insertions(+), 1 deletion(-)
> > > >
> > > > diff --git a/drivers/base/node.c b/drivers/base/node.c
> > > > index eb0f43784c2b..846864e45db6 100644
> > > > --- a/drivers/base/node.c
> > > > +++ b/drivers/base/node.c
> > > > @@ -375,6 +375,9 @@ static ssize_t node_read_meminfo(struct device *dev,
> > > >    	struct sysinfo i;
> > > >    	unsigned long sreclaimable, sunreclaimable;
> > > >    	unsigned long swapcached = 0;
> > > > +	unsigned long free_pcp = 0;
> > > > +	struct zone *zone;
> > > > +	int cpu;
> > > >    	si_meminfo_node(&i, nid);
> > > >    	sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B);
> > > > @@ -382,9 +385,17 @@ static ssize_t node_read_meminfo(struct device *dev,
> > > >    #ifdef CONFIG_SWAP
> > > >    	swapcached = node_page_state_pages(pgdat, NR_SWAPCACHE);
> > > >    #endif
> > > > +	for_each_populated_zone(zone) {
> > > > +		if (zone_to_nid(zone) != nid)
> > > > +			continue;
> > > > +		for_each_online_cpu(cpu)
> > > > +			free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count;
> > > > +	}
> > > > +
> > > >    	len = sysfs_emit_at(buf, len,
> > > >    			    "Node %d MemTotal:       %8lu kB\n"
> > > >    			    "Node %d MemFree:        %8lu kB\n"
> > > > +			    "Node %d PcpFree:        %8lu kB\n"
> > > First off, this sysfs file is a huge violation of the normal sysfs
> > > rules, so I will not allow any new entries to be added.  In fact, the
> > > whole thing should just be removed and multiple files created in its
> > > place.
> > Hi Greg, do you mean to remove all /sys/devices/system/node/node*/meminfo,
> >
> > but this will beak ABI, is it acceptable?
> I do not know, what tool relies on this file?  Any userspace tool should
> always be able to handle a sysfs file being removed, so you should
> probably work with the tool authors to fix this up before removing it.

https://github.com/numactl/numactl/blob/93867c59b0bb29470873a427dc7f06ebaf305221/numastat.c#L841

It seems numastat use this file, but there are maybe more tools,

Cc'ed more mm experts to see more comments.

> thanks,
>
> gre gk-h
> .