如何在内存压力下保持可执行代码在内存中？在Linux中
这里的目标是在Linux中，在内存压力期间将每个正在运行的进程的可执行代码保存在内存中。如何在内存压力下保持可执行代码在内存中？在Linux中,linux,memory,memory-management,linux-kernel,memory-pressure,Linux,Memory,Memory Management,Linux Kernel,Memory Pressure,这里的目标是在Linux中，在内存压力期间将每个正在运行的进程的可执行代码保存在内存中。 在Linux中，我能够立即（1秒）造成高内存压力，并通过 stress--vm bytes$（awk'/MemAvailable/{printf”%d\n'，$2+4000；}'
在Linux中，我能够立即（1秒）造成高内存压力，并通过
stress--vm bytes$（awk'/MemAvailable/{printf”%d\n'，$2+4000；}'CONFIG\u-swap[ 867.746593] Mem-Info:
[ 867.746607] active_anon:1390927 inactive_anon:4670 isolated_anon:0
active_file:94 inactive_file:72 isolated_file:0
unevictable:13868 dirty:0 writeback:0 unstable:0
slab_reclaimable:5906 slab_unreclaimable:12919
mapped:1335 shmem:4805 pagetables:5126 bounce:0
free:40680 free_pcp:978 free_cma:0
active\u file:94 inactive\u file:72，我们让他们在活动列表中无限地走一圈，那么这项工作就应该完成了。或者也许还有别的办法
我可以修补和测试自定义内核。我只是不知道如何在代码中更改什么，以便始终将活动的可执行代码保留在内存中（我认为这实际上可以避免磁盘抖动）
编辑：以下是我迄今为止的工作成果（应用于内核4.18.5之上）：
这是活动文件：26925非活动文件：76
，几乎27兆活动文件…
所以，我不知道这有多好。我是否在内存中保留所有活动文件而不是可执行文件？在firefox编译期间，我已经有了500个Active（file）
（EDIT2:，但这是根据：cat/proc/meminfo | grep-F--“Active（file）
，它显示的值与上面的Active_文件：
来自dmesg！！！）不同，这让我怀疑它只是exes/libs…
也许有人可以建议如何只保留可执行代码？（如果这不是已经发生的事情）
想法
EDIT3:使用上述补丁，可能需要（定期）运行sudo sysctl vm.drop_caches=1
来释放一些陈旧的内存（？），这样，如果在firefox编译后调用stress
，我会得到：活动的_文件：142281非活动的_文件：0孤立的_文件：0
（142megs），然后丢弃文件缓存（另一种方式：echo 1 | sudo tee/proc/sys/vm/drop_caches
）然后再次运行stress
，我得到：active_文件：22233 inactive_文件：160隔离_文件：0
（22megs）-我不确定
没有上述补丁的结果：
上述修补程序的结果：警告：如果启用了交换，请不要使用此修补程序，因为两个用户的效果更差。我只在内核中禁用交换的情况下测试了此修补程序！（即未设置配置交换）
在进一步通知（或有人想出更好的方法）之前，我正在使用（对我来说，它是有效的）以下方法，以避免在即将耗尽内存时发生任何磁盘抖动/OS冻结，从而尽快触发OOM killer（最长1秒）：
第3版
在触发OOM killer之前，在内存压力下避免磁盘抖动（持续读取）的初步补丁
更多信息：https://gist.github.com/constantoverride/84eba764f487049ed642eb2111a20830
diff——git a/include/linux/mmzone.hb/include/linux/mmzone.h
索引32699b2..7636498 100644
---a/include/linux/mmzone.h
+++b/include/linux/mmzone.h
@@-208,7+208,7@@enum lru_列表{
#为（lru=0；lru
不幸的是，上面的标签被转换成了空格，所以如果你想要原始补丁的话，它是空的
此修补程序所做的不是在内存压力下退出活动（文件）
页面，因此不会导致kswapd0
（但在iotop
中看到的是每个程序本身）在每次出现错误时重新读取每个正在运行的进程的可执行页面，以便允许程序运行
if (page_referenced(page, 0, sc->target_mem_cgroup,
&vm_flags)) {
nr_rotated += hpage_nr_pages(page);
/*
* Identify referenced, file-backed active pages and
* give them one more trip around the active list. So
* that executable code get better chances to stay in
* memory under moderate memory pressure. Anon pages
* are not likely to be evicted by use-once streaming
* IO, plus JVM can create lots of anon VM_EXEC pages,
* so we ignore them here.
*/
if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
list_add(&page->lru, &l_active);
continue;
}
}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 32699b2..7636498 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -208,7 +208,7 @@ enum lru_list {
#define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++)
-#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)
+#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_INACTIVE_FILE; lru++)
static inline int is_file_lru(enum lru_list lru)
{
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 03822f8..1f3ffb5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2234,7 +2234,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
- file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+ file = //lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
spin_lock_irq(&pgdat->lru_lock);
@@ -2345,7 +2345,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
sc->priority == DEF_PRIORITY);
blk_start_plug(&plug);
- while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
+ while (nr[LRU_INACTIVE_ANON] || //nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
unsigned long nr_anon, nr_file, percentage;
unsigned long nr_scanned;
@@ -2372,7 +2372,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
*/
- nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
+ nr_file = nr[LRU_INACTIVE_FILE] //+ nr[LRU_ACTIVE_FILE]
+ ;
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
/*
@@ -2391,7 +2392,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
percentage = nr_anon * 100 / scan_target;
} else {
unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
- targets[LRU_ACTIVE_FILE] + 1;
+ //targets[LRU_ACTIVE_FILE] +
+ 1;
lru = LRU_FILE;
percentage = nr_file * 100 / scan_target;
}
[ 745.830511] Mem-Info:
[ 745.830521] active_anon:855546 inactive_anon:20453 isolated_anon:0
active_file:26925 inactive_file:76 isolated_file:0
unevictable:10652 dirty:0 writeback:0 unstable:0
slab_reclaimable:26975 slab_unreclaimable:13525
mapped:24238 shmem:20456 pagetables:4028 bounce:0
free:14935 free_pcp:177 free_cma:0
revision 3
preliminary patch to avoid disk thrashing (constant reading) under memory pressure before OOM-killer triggers
more info: https://gist.github.com/constantoverride/84eba764f487049ed642eb2111a20830
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 32699b2..7636498 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -208,7 +208,7 @@ enum lru_list {
#define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++)
-#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)
+#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_INACTIVE_FILE; lru++)
static inline int is_file_lru(enum lru_list lru)
{
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 03822f8..1f3ffb5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2086,9 +2086,9 @@ static unsigned long shrink_list(enum lr
struct scan_control *sc)
{
if (is_active_lru(lru)) {
- if (inactive_list_is_low(lruvec, is_file_lru(lru),
- memcg, sc, true))
- shrink_active_list(nr_to_scan, lruvec, sc, lru);
+ //if (inactive_list_is_low(lruvec, is_file_lru(lru),
+ // memcg, sc, true))
+ // shrink_active_list(nr_to_scan, lruvec, sc, lru);
return 0;
}
@@ -2234,7 +2234,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
- file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+ file = //lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
spin_lock_irq(&pgdat->lru_lock);
@@ -2345,7 +2345,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
sc->priority == DEF_PRIORITY);
blk_start_plug(&plug);
- while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
+ while (nr[LRU_INACTIVE_ANON] || //nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
unsigned long nr_anon, nr_file, percentage;
unsigned long nr_scanned;
@@ -2372,7 +2372,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
*/
- nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
+ nr_file = nr[LRU_INACTIVE_FILE] //+ nr[LRU_ACTIVE_FILE]
+ ;
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
/*
@@ -2391,7 +2392,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
percentage = nr_anon * 100 / scan_target;
} else {
unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
- targets[LRU_ACTIVE_FILE] + 1;
+ //targets[LRU_ACTIVE_FILE] +
+ 1;
lru = LRU_FILE;
percentage = nr_file * 100 / scan_target;
}
@@ -2409,10 +2411,12 @@ static void shrink_node_memcg(struct pgl
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
+ if (LRU_FILE != lru) { //avoid this block for LRU_ACTIVE_FILE
lru += LRU_ACTIVE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
+ }
scan_adjusted = true;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dbdc46a84f63..7a0b7e32ff45 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2445,6 +2445,13 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
BUG();
}
+ if (NR_ACTIVE_FILE == lru) {
+ long long kib_active_file_now=global_node_page_state(NR_ACTIVE_FILE) * MAX_NR_ZONES;
+ if (kib_active_file_now <= 256*1024) {
+ nr[lru] = 0; //don't reclaim any Active(file) (see /proc/meminfo) if they are under 256MiB
+ continue;
+ }
+ }
*lru_pages += size;
nr[lru] = scan;
}