diff options
| author |   Steven Luong <sluong@cisco.com> | 2019-11-20 11:20:08 -0800 |
|---|---|---|
| committer |   Dave Barach <openvpp@barachs.net> | 2019-11-25 15:05:51 +0000 |
| commit | 70449b9b9bf8dbe3b4aa4d9af35c759789b03fe1 (patch) | |
| tree | 13faf049d3007a5a3314e69680bb6f652cb84529 /src/vlib/threads.c | |
| parent | ac0e98a67553747b823d8398896559bb07cafe3d (diff) | |
vlib: address vlib_error_t scaling issuestable/1901
Encoding the vpp node index into the vlib_error_t as a 10-bit quantity
limits us to 1K graph nodes. Unfortunately, a few nodes need 6 bit
per-node error codes. Only a very few nodes have so many counters.
It turns out that there are about 2K total error counters in the system,
which is (approximately) the maximum error heap index.
The current (index,code) encoding limits the number of interfaces to
around 250, since each interface has two associated graph nodes and we
have about 500 "normal, interior" graph node
This patch adds an error-index to node-index map, so we can store
error heap indices directly in the vlib_buffer_t.
Type: refactor
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Ic2e91a5b344c9df3b98b264cacda246e06092a94
Diffstat (limited to 'src/vlib/threads.c')
| -rw-r--r-- | src/vlib/threads.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/src/vlib/threads.c b/src/vlib/threads.c index 56f9d790ee6..5bd94760456 100644 --- a/src/vlib/threads.c +++ b/src/vlib/threads.c @@ -856,6 +856,7 @@ start_workers (vlib_main_t * vm) /* zap the (per worker) frame freelists, etc */ nm_clone->frame_sizes = 0; nm_clone->frame_size_hash = hash_create (0, sizeof (uword)); + nm_clone->node_by_error = nm->node_by_error; /* Packet trace buffers are guaranteed to be empty, nothing to do here */ @@ -1175,6 +1176,7 @@ vlib_worker_thread_node_refork (void) nm_clone->processes = vec_dup_aligned (nm->processes, CLIB_CACHE_LINE_BYTES); + nm_clone->node_by_error = nm->node_by_error; } void |