Lines Matching refs:buckets
54 continuous. With a hash table, mapping between the hash table buckets and
56 the buckets that held it are simply reassigned to other next hops::
70 choose a subset of buckets that are currently not used for forwarding
72 keeping the "busy" buckets intact. This way, established flows are ideally
80 certain number of buckets, according to its weight and the number of
81 buckets in the hash table. In accordance with the source code, we will call
86 Next hops that have fewer buckets than their wants count, are called
98 buckets:
105 underweight next hops. If, after considering all buckets in this manner,
109 There may not be enough "idle" buckets to satisfy the updated wants counts
112 of balance until idle buckets do appear, possibly never. If set to a
117 item. Thus buckets:
127 When offloading resilient groups, the algorithm that distributes buckets
133 created and buckets populated for the first time.
154 ``nexthop_res_grp_activity_update()`` API. The buckets identified this way
157 Offloaded buckets should be flagged as either "offload" or "trap". This is
179 ``NHA_RES_GROUP_BUCKETS`` Number of buckets in the hash table.
219 to request a dump of matching buckets. The attributes recognized at dump
225 ``NHA_OIF`` If specified, limits the dump to buckets that contain
227 ``NHA_MASTER`` If specified, limits the dump to buckets that contain
235 ``NHA_RES_BUCKET_NH_ID`` If specified, limits the dump to just the buckets
247 buckets 8 idle_timer 60 unbalanced_timer 300
249 The last command creates a resilient next-hop group. It will have 8 buckets
259 This can be confirmed by looking at individual buckets::
271 Note the two buckets that have a shorter idle time. Those are the ones that
273 that next hop 1 be given 6 buckets instead of 4.
279 exposes debugfs interface that allows marking individual buckets as busy.