[PATCH 3/3 v3] mm/vmalloc: Cache the vmalloc memory info

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



* George Spelvin <linux@xxxxxxxxxxx> wrote:

> Ingo Molnar <mingo@xxxxxxxxxx> wrote:
> > I think this is too complex.
> > 
> > How about something simple like the patch below (on top of the third patch)?
> 
> > It makes the vmalloc info transactional - /proc/meminfo will always print a 
> > consistent set of numbers. (Not that we really care about races there, but it 
> > looks really simple to solve so why not.)
> 
> Looks like a huge simplification!
> 
> It needs a comment about the approximate nature of the locking and
> the obvious race conditions:
> 1) The first caller to get_vmalloc_info() clears vmap_info_changed
>    before updating vmap_info_cache, so a second caller is likely to
>    get stale data for the duration of a calc_vmalloc_info call.
> 2) Although unlikely, it's possible for two threads to race calling
>    calc_vmalloc_info, and the one that computes fresher data updates
>    the cache first, so the later write leaves stale data.
> 
> Other issues:
> 3) Me, I'd make vmap_info_changed a bool, for documentation more than
>    any space saving.
> 4) I wish there were a trylock version of write_seqlock, so we could
>    avoid blocking entirely.  (You *could* hand-roll it, but that eats
>    into the simplicity.)

Ok, fair enough - so how about the attached approach instead, which uses a 64-bit 
generation counter to track changes to the vmalloc state.

This is still very simple, but should not suffer from stale data being returned 
indefinitely in /proc/meminfo. We might race - but that was true before as well 
due to the lock-less RCU list walk - but we'll always return a correct and 
consistent version of the information.

Lightly tested. This is a replacement patch to make it easier to read via email.

I also made sure there's no extra overhead in the !CONFIG_PROC_FS case.

Note that there's an even simpler variant possible I think: we could use just the 
two generation counters and barriers to remove the seqlock.

Thanks,

	Ingo

==============================>
>From f9fd770e75e2edb4143f32ced0b53d7a77969c94 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@xxxxxxxxxx>
Date: Sat, 22 Aug 2015 12:28:01 +0200
Subject: [PATCH] mm/vmalloc: Cache the vmalloc memory info

Linus reported that glibc (rather stupidly) reads /proc/meminfo
for every sysinfo() call, which causes the Git build to use
a surprising amount of CPU time, mostly due to the overhead
of get_vmalloc_info() - which walks a long list to do its
statistics.

Modify Linus's jiffies based patch to use generation counters
to cache the vmalloc info: vmap_unlock() increases the generation
counter, and the get_vmalloc_info() reads it and compares it
against a cached generation counter.

Also use a seqlock to make sure we always print a consistent
set of vmalloc statistics.

Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 mm/vmalloc.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 56 insertions(+), 3 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 605138083880..d72b23436906 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -276,7 +276,21 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 #define VM_LAZY_FREEING	0x02
 #define VM_VM_AREA	0x04
 
-static DEFINE_SPINLOCK(vmap_area_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(vmap_area_lock);
+
+#ifdef CONFIG_PROC_FS
+/*
+ * A seqlock and two generation counters for a simple cache of the
+ * vmalloc allocation statistics info printed in /proc/meminfo.
+ *
+ * ( The assumption of the optimization is that it's read frequently, but
+ *   modified infrequently. )
+ */
+static DEFINE_SEQLOCK(vmap_info_lock);
+static u64 vmap_info_gen;
+static u64 vmap_info_cache_gen;
+static struct vmalloc_info vmap_info_cache;
+#endif
 
 static inline void vmap_lock(void)
 {
@@ -285,6 +299,9 @@ static inline void vmap_lock(void)
 
 static inline void vmap_unlock(void)
 {
+#ifdef CONFIG_PROC_FS
+	WRITE_ONCE(vmap_info_gen, vmap_info_gen+1);
+#endif
 	spin_unlock(&vmap_area_lock);
 }
 
@@ -2699,7 +2716,7 @@ static int __init proc_vmalloc_init(void)
 }
 module_init(proc_vmalloc_init);
 
-void get_vmalloc_info(struct vmalloc_info *vmi)
+static void calc_vmalloc_info(struct vmalloc_info *vmi)
 {
 	struct vmap_area *va;
 	unsigned long free_area_size;
@@ -2746,5 +2763,41 @@ void get_vmalloc_info(struct vmalloc_info *vmi)
 out:
 	rcu_read_unlock();
 }
-#endif
 
+/*
+ * Return a consistent snapshot of the current vmalloc allocation
+ * statistics, for /proc/meminfo:
+ */
+void get_vmalloc_info(struct vmalloc_info *vmi)
+{
+	u64 gen = READ_ONCE(vmap_info_gen);
+
+	/*
+	 * If the generation counter of the cache matches that of
+	 * the vmalloc generation counter then return the cache:
+	 */
+	if (READ_ONCE(vmap_info_cache_gen) == gen) {
+		unsigned int seq;
+
+		do {
+			seq = read_seqbegin(&vmap_info_lock);
+			*vmi = vmap_info_cache;
+		} while (read_seqretry(&vmap_info_lock, seq));
+
+		return;
+	}
+
+	calc_vmalloc_info(vmi);
+
+	/*
+	 * If are racing with a new vmalloc() then we might write
+	 * the old generation counter here - and the next call to
+	 * get_vmalloc_info() will fix things up:
+	 */
+	write_seqlock(&vmap_info_lock);
+	vmap_info_cache = *vmi;
+	WRITE_ONCE(vmap_info_cache_gen, gen);
+	write_sequnlock(&vmap_info_lock);
+}
+
+#endif /* CONFIG_PROC_FS */

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>



[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]