diff options
| author | Donald Sharp <sharpd@nvidia.com> | 2023-07-21 13:10:03 -0400 |
|---|---|---|
| committer | Donald Sharp <sharpd@nvidia.com> | 2023-07-21 13:10:03 -0400 |
| commit | bdc17624059c1722e5208523cb06fe9b0ed7acb2 (patch) | |
| tree | f8a059a6caf80f615a9eefc35d7394a8fe220031 /bgpd/bgpd.h | |
| parent | 4215e8011b52abaccc96198cb8fa6d7034521dc9 (diff) | |
bgpd: Replace peer->ibuf_scratch
The peer->ibuf_scratch was allocating 65535 * 10 bytes
for scratch space to hold data incoming from a read
from a peer. When you have 4k peers this is 262,1400,000
or 262 mb of data. Which is crazy large. Especially
since the i/o pthread is reading per peer without
any chance of having the data interfere with other reads.
Signed-off-by: Donald Sharp <sharpd@nvidia.com>
Diffstat (limited to 'bgpd/bgpd.h')
| -rw-r--r-- | bgpd/bgpd.h | 3 |
1 files changed, 0 insertions, 3 deletions
diff --git a/bgpd/bgpd.h b/bgpd/bgpd.h index a9d77f862f..5c42abef5e 100644 --- a/bgpd/bgpd.h +++ b/bgpd/bgpd.h @@ -1163,9 +1163,6 @@ struct peer { struct stream_fifo *ibuf; // packets waiting to be processed struct stream_fifo *obuf; // packets waiting to be written - /* used as a block to deposit raw wire data to */ - uint8_t ibuf_scratch[BGP_EXTENDED_MESSAGE_MAX_PACKET_SIZE - * BGP_READ_PACKET_MAX]; struct ringbuf *ibuf_work; // WiP buffer used by bgp_read() only struct stream *curr; // the current packet being parsed |