diff options
| author | Donald Sharp <sharpd@nvidia.com> | 2025-03-24 14:11:35 -0400 |
|---|---|---|
| committer | Donald Sharp <sharpd@nvidia.com> | 2025-03-25 09:10:46 -0400 |
| commit | 937a9fb3e923beb1cf0a795daddb178cb1fe0ec4 (patch) | |
| tree | 47313603c293309310f970122c06cbc12237b7f7 /zebra/zserv.c | |
| parent | 12bf042c688fedf82637fab9ff77aa1eab271160 (diff) | |
zebra: Limit reading packets when MetaQ is full
Currently Zebra is just reading packets off the zapi
wire and stacking them up for processing in zebra
in the future. When there is significant churn
in the network the size of zebra can grow without
bounds due to the MetaQ sizing constraints. This
ends up showing by the number of nexthops in the
system. Reducing the number of packets serviced
to limit the metaQ size to the packets to process
allieviates this problem.
Signed-off-by: Donald Sharp <sharpd@nvidia.com>
Diffstat (limited to 'zebra/zserv.c')
| -rw-r--r-- | zebra/zserv.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/zebra/zserv.c b/zebra/zserv.c index d477cd051f..aab1bd0062 100644 --- a/zebra/zserv.c +++ b/zebra/zserv.c @@ -530,6 +530,12 @@ static void zserv_process_messages(struct event *thread) struct stream_fifo *cache = stream_fifo_new(); uint32_t p2p = zrouter.packets_to_process; bool need_resched = false; + uint32_t meta_queue_size = zebra_rib_meta_queue_size(); + + if (meta_queue_size < p2p) + p2p = p2p - meta_queue_size; + else + p2p = 0; frr_with_mutex (&client->ibuf_mtx) { uint32_t i; |