On Sat, Jul 13, 2019 at 7:58 AM Yang Shi <shy828301@xxxxxxxxx> wrote:
>
> On Thu, Jul 11, 2019 at 6:10 PM Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
> >
> >
> > Can we please get some review of this one? It has been in -mm since
> > May 22, no issues that I've heard of.
> >
> >
> > From: Yafang Shao <laoar.shao@xxxxxxxxx>
> > Subject: mm/vmscan: expose cgroup_ino for memcg reclaim tracepoints
> >
> > We can use the exposed cgroup_ino to trace specified cgroup.
> >
> > For example,
> > step 1, get the inode of the specified cgroup
> > $ ls -di /tmp/cgroupv2/foo
> > step 2, set this inode into tracepoint filter to trace this cgroup only
> > (assume the inode is 11)
> > $ cd /sys/kernel/debug/tracing/events/vmscan/
> > $ echo 'cgroup_ino == 11' > mm_vmscan_memcg_reclaim_begin/filter
> > $ echo 'cgroup_ino == 11' > mm_vmscan_memcg_reclaim_end/filter
> >
> > The reason I made this change is to trace a specific container.
>
> I'm wondering how useful this is. You could filter events by cgroup
> with bpftrace easily. For example:
>
> # bpftrace -e 'tracepoint:syscalls:sys_enter_openat /cgroup ==
> cgroupid("/sys/fs/cgroup/unified/mycg")/ { printf("%s\n",
> str(args->filename)); }':
>
Seems the bpftrace get the cgroupid from the current task and then
compare the task-cgroupid with the speficied cgroupid?
While in the memcg reclaim, the pages in a memcg may be reclaimed by a
process in other memcgs, i.e. the parent memcg,
so we can't use the process's memcg as the filter.
The way to use bpftrace here is using kprobe to do it, I guess.
But as the tracepoint is already there, we can make little change to enhance it.
Thanks
Yafang
>
> >
> > Sometimes there're lots of containers on one host. Some of them are
> > not important at all, so we don't care whether them are under memory
> > pressure. While some of them are important, so we want't to know if
> > these containers are doing memcg reclaim and how long this relaim
> > takes.
> >
> > Without this change, we don't know the memcg reclaim happend in which
> > container.
> >
> > Link: http://lkml.kernel.org/r/1557649528-11676-1-git-send-email-laoar.shao@xxxxxxxxx
> > Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
> > Cc: Michal Hocko <mhocko@xxxxxxxx>
> > Cc: <shaoyafang@xxxxxxxxxxxxxx>
> > Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> > Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> > ---
> >
> > include/trace/events/vmscan.h | 71 ++++++++++++++++++++++++++------
> > mm/vmscan.c | 18 +++++---
> > 2 files changed, 72 insertions(+), 17 deletions(-)
> >
> > --- a/include/trace/events/vmscan.h~mm-vmscan-expose-cgroup_ino-for-memcg-reclaim-tracepoints
> > +++ a/include/trace/events/vmscan.h
> > @@ -127,18 +127,43 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_be
> > );
> >
> > #ifdef CONFIG_MEMCG
> > -DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
> > +DECLARE_EVENT_CLASS(mm_vmscan_memcg_reclaim_begin_template,
> >
> > - TP_PROTO(int order, gfp_t gfp_flags),
> > + TP_PROTO(unsigned int cgroup_ino, int order, gfp_t gfp_flags),
> >
> > - TP_ARGS(order, gfp_flags)
> > + TP_ARGS(cgroup_ino, order, gfp_flags),
> > +
> > + TP_STRUCT__entry(
> > + __field(unsigned int, cgroup_ino)
> > + __field(int, order)
> > + __field(gfp_t, gfp_flags)
> > + ),
> > +
> > + TP_fast_assign(
> > + __entry->cgroup_ino = cgroup_ino;
> > + __entry->order = order;
> > + __entry->gfp_flags = gfp_flags;
> > + ),
> > +
> > + TP_printk("cgroup_ino=%u order=%d gfp_flags=%s",
> > + __entry->cgroup_ino, __entry->order,
> > + show_gfp_flags(__entry->gfp_flags))
> > );
> >
> > -DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
> > +DEFINE_EVENT(mm_vmscan_memcg_reclaim_begin_template,
> > + mm_vmscan_memcg_reclaim_begin,
> >
> > - TP_PROTO(int order, gfp_t gfp_flags),
> > + TP_PROTO(unsigned int cgroup_ino, int order, gfp_t gfp_flags),
> >
> > - TP_ARGS(order, gfp_flags)
> > + TP_ARGS(cgroup_ino, order, gfp_flags)
> > +);
> > +
> > +DEFINE_EVENT(mm_vmscan_memcg_reclaim_begin_template,
> > + mm_vmscan_memcg_softlimit_reclaim_begin,
> > +
> > + TP_PROTO(unsigned int cgroup_ino, int order, gfp_t gfp_flags),
> > +
> > + TP_ARGS(cgroup_ino, order, gfp_flags)
> > );
> > #endif /* CONFIG_MEMCG */
> >
> > @@ -167,18 +192,40 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_en
> > );
> >
> > #ifdef CONFIG_MEMCG
> > -DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end,
> > +DECLARE_EVENT_CLASS(mm_vmscan_memcg_reclaim_end_template,
> >
> > - TP_PROTO(unsigned long nr_reclaimed),
> > + TP_PROTO(unsigned int cgroup_ino, unsigned long nr_reclaimed),
> >
> > - TP_ARGS(nr_reclaimed)
> > + TP_ARGS(cgroup_ino, nr_reclaimed),
> > +
> > + TP_STRUCT__entry(
> > + __field(unsigned int, cgroup_ino)
> > + __field(unsigned long, nr_reclaimed)
> > + ),
> > +
> > + TP_fast_assign(
> > + __entry->cgroup_ino = cgroup_ino;
> > + __entry->nr_reclaimed = nr_reclaimed;
> > + ),
> > +
> > + TP_printk("cgroup_ino=%u nr_reclaimed=%lu",
> > + __entry->cgroup_ino, __entry->nr_reclaimed)
> > );
> >
> > -DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end,
> > +DEFINE_EVENT(mm_vmscan_memcg_reclaim_end_template,
> > + mm_vmscan_memcg_reclaim_end,
> >
> > - TP_PROTO(unsigned long nr_reclaimed),
> > + TP_PROTO(unsigned int cgroup_ino, unsigned long nr_reclaimed),
> >
> > - TP_ARGS(nr_reclaimed)
> > + TP_ARGS(cgroup_ino, nr_reclaimed)
> > +);
> > +
> > +DEFINE_EVENT(mm_vmscan_memcg_reclaim_end_template,
> > + mm_vmscan_memcg_softlimit_reclaim_end,
> > +
> > + TP_PROTO(unsigned int cgroup_ino, unsigned long nr_reclaimed),
> > +
> > + TP_ARGS(cgroup_ino, nr_reclaimed)
> > );
> > #endif /* CONFIG_MEMCG */
> >
> > --- a/mm/vmscan.c~mm-vmscan-expose-cgroup_ino-for-memcg-reclaim-tracepoints
> > +++ a/mm/vmscan.c
> > @@ -3191,8 +3191,10 @@ unsigned long mem_cgroup_shrink_node(str
> > sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
> > (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
> >
> > - trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
> > - sc.gfp_mask);
> > + trace_mm_vmscan_memcg_softlimit_reclaim_begin(
> > + cgroup_ino(memcg->css.cgroup),
> > + sc.order,
> > + sc.gfp_mask);
> >
> > /*
> > * NOTE: Although we can get the priority field, using it
> > @@ -3203,7 +3205,9 @@ unsigned long mem_cgroup_shrink_node(str
> > */
> > shrink_node_memcg(pgdat, memcg, &sc, &lru_pages);
> >
> > - trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
> > + trace_mm_vmscan_memcg_softlimit_reclaim_end(
> > + cgroup_ino(memcg->css.cgroup),
> > + sc.nr_reclaimed);
> >
> > *nr_scanned = sc.nr_scanned;
> > return sc.nr_reclaimed;
> > @@ -3241,7 +3245,9 @@ unsigned long try_to_free_mem_cgroup_pag
> >
> > zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];
> >
> > - trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
> > + trace_mm_vmscan_memcg_reclaim_begin(
> > + cgroup_ino(memcg->css.cgroup),
> > + 0, sc.gfp_mask);
> >
> > psi_memstall_enter(&pflags);
> > noreclaim_flag = memalloc_noreclaim_save();
> > @@ -3251,7 +3257,9 @@ unsigned long try_to_free_mem_cgroup_pag
> > memalloc_noreclaim_restore(noreclaim_flag);
> > psi_memstall_leave(&pflags);
> >
> > - trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
> > + trace_mm_vmscan_memcg_reclaim_end(
> > + cgroup_ino(memcg->css.cgroup),
> > + nr_reclaimed);
> >
> > return nr_reclaimed;
> > }
> > _
> >
