__GFP_RETRY_MAYFAIL can spend quite a bit of time reclaiming, and this can be wasted effort given that there is a fallback code path in case memory allocation fails. __GFP_NORETRY does perform some light-weight reclaim, but it will fail under OOM conditions, allowing the fallback to be taken as an alternative to hard-OOMing the system. There is a four-way tradeoff that must be balanced: 1) Minimize use of the fallback path; 2) Avoid full-up OOM; 3) Do a light-wait allocation request; 4) Avoid dipping into the emergency reserves.
Showing the changes to kernel (1 of 1 file). Show all
Unified · Split
| @@ -3517,8 +3517,20 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, · 3516 unmodified lines | ||
| 3517 | 3517 | bnode = get_cached_bnode(*krcp); |
| 3518 | 3518 | if (!bnode && can_alloc) { |
| 3519 | 3519 | krc_this_cpu_unlock(*krcp, *flags); |
| 3520 | + | |
| 3521 | + // __GFP_NORETRY - allows a light-weight direct reclaim | |
| 3522 | + // what is OK from minimizing of fallback hitting point of | |
| 3523 | + // view. Apart of that it forbids any OOM invoking what is | |
| 3524 | + // also beneficial since we are about to release memory soon. | |
| 3525 | + // | |
| 3526 | + // __GFP_NOMEMALLOC - prevents from consuming of all the | |
| 3527 | + // memory reserves. Please note we have a fallback path. | |
| 3528 | + // | |
| 3529 | + // __GFP_NOWARN - it is supposed that an allocation can | |
| 3530 | + // be failed under low memory or high memory pressure | |
| 3531 | + // scenarios. | |
| 3520 | 3532 | bnode = (struct kvfree_rcu_bulk_data *) |
| 3521 | − __get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOMEMALLOC | __GFP_NOWARN); | |
| 3533 | + __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); | |
| 3522 | 3534 | *krcp = krc_this_cpu_lock(flags); |
| 3523 | 3535 | } |
| 3524 | 3536 | |