0
0
mirror of https://gitlab.nic.cz/labs/bird.git synced 2024-12-22 09:41:54 +00:00

Fix memory pre-allocation

When BIRD has no free memory mapped, it allocates several pages in
advance just to be sure that there is some memory available if needed.
This hysteresis tactics works quite well to reduce memory ping-ping with
kernel.

Yet it had a subtle bug: this pre-allocation didn't take a memory
coldlist into account, therefore requesting new pages from kernel even
in cases when there were other pages available. This led to slow memory
bloating.

To demonstrate this behavior fast enough to be seen well, you may:
  * temporarily set the values in sysdep/unix/alloc.c as follows to
    exacerbate the issue:
      #define KEEP_PAGES_MAIN_MAX    4096
      #define KEEP_PAGES_MAIN_MIN    1000
      #define CLEANUP_PAGES_BULK     4096
  * create a config file with several millions of static routes
  * periodically disable all static protocols and then reload config
  * log memory consumption

This should give you a steady growth rate of about 16kB per cycle. If
you don't set the values this high, the issue happens much more slowly,
yet after 14 days of running, you are going to see an OOM kill.

After this fix, pre-allocation uses the memory coldlist to get some hot
pages and the same test as described here gets you a perfectly stable
constant memory consumption (after some initial wobbling).

Thanks to NIX-CZ for reporting and helping to investigate this issue.
Thanks to Santiago for finding the cause in the code.
This commit is contained in:
Maria Matejka 2023-01-18 09:39:45 +01:00
parent 64a2b7aaa3
commit 973aa37e1e

View File

@ -58,6 +58,7 @@ struct free_pages {
};
static void global_free_pages_cleanup_event(void *);
static void *alloc_cold_page(void);
static struct free_pages global_free_pages = {
.min = KEEP_PAGES_MAIN_MIN,
@ -114,6 +115,14 @@ alloc_page(void)
return fp;
}
else
return alloc_cold_page();
}
static void *
alloc_cold_page(void)
{
struct free_pages *fps = &global_free_pages;
/* If there is any free page kept cold, we use that. */
if (!EMPTY_LIST(fps->empty))
@ -170,12 +179,7 @@ global_free_pages_cleanup_event(void *data UNUSED)
/* Cleanup may get called when hot free page cache is short of pages. Replenishing. */
while (fps->cnt / 2 < fps->min)
{
struct free_page *fp = alloc_sys_page();
fp->n = (node) {};
add_tail(&fps->pages, &fp->n);
fps->cnt++;
}
free_page(alloc_cold_page());
/* Or the hot free page cache is too big. Moving some pages to the cold free page cache. */
for (int limit = CLEANUP_PAGES_BULK; limit && (fps->cnt > fps->max / 2); fps->cnt--, limit--)