Skip to content

Add fine grain delay stats #303

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
huitema wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Add fine grain delay stats #303

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f094b01
Add fine grain delay stats
huitema Feb 23, 2026
486d919
Remove TLD GOO WOLTERSKLUWER
huitema Feb 23, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions lib/DnsStats.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,7 +237,7 @@ char const * RegisteredTldName[] = {
"GAP", "GARDEN", "GAY", "GB", "GBIZ", "GD", "GDN", "GE", "GEA", "GENT", "GENTING", "GEORGE",
"GF", "GG", "GGEE", "GH", "GI", "GIFT", "GIFTS", "GIVES", "GIVING", "GL",
"GLASS", "GLE", "GLOBAL", "GLOBO", "GM", "GMAIL", "GMBH", "GMO", "GMX", "GN", "GODADDY",
"GOLD", "GOLDPOINT", "GOLF", "GOO", "GOODYEAR", "GOOG", "GOOGLE", "GOP",
"GOLD", "GOLDPOINT", "GOLF", "GOODYEAR", "GOOG", "GOOGLE", "GOP",
"GOT", "GOV", "GP", "GQ", "GR", "GRAINGER", "GRAPHICS", "GRATIS", "GREEN", "GRIPE",
"GROCERY", "GROUP", "GS", "GT", "GU", "GUCCI", "GUGE", "GUIDE", "GUITARS",
"GURU", "GW", "GY", "HAIR", "HAMBURG", "HANGOUT", "HAUS", "HBO", "HDFC", "HDFCBANK",
Expand Down Expand Up @@ -327,7 +327,7 @@ char const * RegisteredTldName[] = {
"VOTING", "VOTO", "VOYAGE", "VU", "WALES", "WALMART", "WALTER", "WANG",
"WANGGOU", "WATCH", "WATCHES", "WEATHER", "WEATHERCHANNEL", "WEBCAM", "WEBER",
"WEBSITE", "WED", "WEDDING", "WEIBO", "WEIR", "WF", "WHOSWHO", "WIEN", "WIKI",
"WILLIAMHILL", "WIN", "WINDOWS", "WINE", "WINNERS", "WME", "WOLTERSKLUWER", "WOODSIDE",
"WILLIAMHILL", "WIN", "WINDOWS", "WINE", "WINNERS", "WME", "WOODSIDE",
"WORK", "WORKS", "WORLD", "WOW", "WS", "WTC", "WTF", "XBOX", "XEROX",
"XIHUAN", "XIN", "XN--11B4C3D", "XN--1CK2E1B", "XN--1QQW23A", "XN--2SCRJ9C",
"XN--30RR7Y", "XN--3BST00M", "XN--3DS443G", "XN--3E0B707E", "XN--3HCRJ9C",
Expand Down
75 changes: 73 additions & 2 deletions resolver/rsv_recap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,6 +95,8 @@ def __init__(self, query_cc, query_AS, slice_start, slice_duration, recap_file,
self.nb_A_pattern = [ 0, 0, 0, 0, 0, 0, 0 ]
# vector of duplicates (ISP, PDNS, Other)
self.nb_A_prov = [ 0, 0, 0 ]
# vector of count (ISP, PDNS, Others) by time slices (0-300ms-1s-3s-10s-30s)
self.nb_A_under = [[ 0, 0, 0 ],[ 0, 0, 0 ],[ 0, 0, 0 ],[ 0, 0, 0 ],[ 0, 0, 0 ]]
self.zombie = [ 0, 0, 0, 0]
self.first_3s = 0
self.first_10s = 0
Expand Down Expand Up @@ -128,6 +130,9 @@ def init_next_slice(self):
self.previous_slice.nb_A_pattern[i] = self.nb_A_pattern[i]
for i in range(0,3):
self.previous_slice.nb_A_prov[i] = self.nb_A_prov[i]
for i in range(0,5):
for j in range(0,3):
self.previous_slice.nb_A_under[i][j] += self.nb_A_under[i][j]
for i in range(0,4):
self.previous_slice.zombie[i] = self.zombie[i]
self.previous_slice.first_3s = self.first_3s
Expand All @@ -150,6 +155,9 @@ def init_next_slice(self):
self.nb_A_pattern[i] = 0
for i in range(0,3):
self.nb_A_prov[i] = 0
for i in range(0,5):
for j in range(0,3):
self.nb_A_under[i][j] = 0
self.zombie = [ 0, 0, 0, 0]
self.first_3s = 0
self.first_10s = 0
Expand Down Expand Up @@ -179,6 +187,7 @@ def summarize(self):
self.nb_A_pattern[pattern_id-1] += 1

def update_uid(self, r_uid, query_time, rr_type, resolver_tag):
delta_range = [ 0.3, 1, 3, 10, 30 ]
if rr_type == 'HTTPS':
r_uid.has_https = True
elif rr_type == 'AAAA':
Expand All @@ -197,6 +206,10 @@ def update_uid(self, r_uid, query_time, rr_type, resolver_tag):
r_uid.nb_A_prov[prov_index] += 1
if delta_t <= cutoff_delay:
r_uid.has_A_prov[prov_index] = True
for i in range(0, len(delta_range)):
if delta_t <= delta_range[i]:
self.nb_A_under[i][prov_index] += 1
break

def get_header():
s = "CC,AS,start,uids,first_isp,"
Expand All @@ -205,6 +218,11 @@ def get_header():
s += 'first_others,nb_https,nb_AAAA,nb_A,'
s += 'A_ISP_only, A_PDNS_only, A_ISP_PDNS, A_others_only, A_ISP_others, A_PDNS_others, A_all3,'
s += 'nb_A_ISP, nb_A_PDNS, nb_A_others,'
s += 'nb_A_u300ms_ISP, nb_A_u300ms_PDNS, nb_A_u300ms_others,'
s += 'nb_A_u1s_ISP, nb_A_u1s_PDNS, nb_A_u1s_others,'
s += 'nb_A_u3s_ISP, nb_A_u3s_PDNS, nb_A_u3s_others,'
s += 'nb_A_u10s_ISP, nb_A_u10s_PDNS, nb_A_u10s_others,'
s += 'nb_A_u30s_ISP, nb_A_u30s_PDNS, nb_A_u30s_others,'
s += 'zombies,z_ISP,z_PDNS,z_others,first_3s,first_10s,sum_delay,max_delay' + '\n'
return s

Expand All @@ -225,6 +243,9 @@ def save_to_file(self):
s += str(pattern_total) + ','
for dups_total in self.nb_A_prov:
s += str(dups_total) + ','
for i in range(0,5):
for prov_index in range(0,3):
s += str(self.nb_A_under[i][prov_index]) + ','
for z in self.zombie:
s += str(z) + ','
s += str(self.first_3s) + ',' + str(self.first_10s) + ','
Expand Down Expand Up @@ -378,6 +399,11 @@ def save_and_close(self):
'first_others', 'nb_https', 'nb_AAAA', 'nb_A',
'A_ISP_only', ' A_PDNS_only', ' A_ISP_PDNS', ' A_others_only', ' A_ISP_others', ' A_PDNS_others', ' A_all3',
'nb_A_ISP', ' nb_A_PDNS', ' nb_A_others',
'nb_A_u300ms_ISP', 'nb_A_u300ms_PDNS', 'nb_A_u300ms_others',
'nb_A_u1s_ISP', 'nb_A_u1s_PDNS', 'nb_A_u1s_others',
'nb_A_u3s_ISP', 'nb_A_u3s_PDNS', 'nb_A_u3s_others',
'nb_A_u10s_ISP', 'nb_A_u10s_PDNS', 'nb_A_u10s_others',
'nb_A_u30s_ISP', 'nb_A_u30s_PDNS', 'nb_A_u30s_others',
'zombies', 'z_ISP', 'z_PDNS', 'z_others',
'first_3s', 'first_10s', 'sum_delay', 'max_delay'
]
Expand All @@ -388,6 +414,11 @@ def save_and_close(self):
recap_final_columns = [ 'nb_https', 'nb_AAAA', 'nb_A',
'A_ISP_only', 'A_PDNS_only', 'A_ISP_PDNS', 'A_others_only', 'A_ISP_others', 'A_PDNS_others', 'A_all3',
'nb_A_ISP', 'nb_A_PDNS', 'nb_A_others',
'nb_A_u300ms_ISP', 'nb_A_u300ms_PDNS', 'nb_A_u300ms_others',
'nb_A_u1s_ISP', 'nb_A_u1s_PDNS', 'nb_A_u1s_others',
'nb_A_u3s_ISP', 'nb_A_u3s_PDNS', 'nb_A_u3s_others',
'nb_A_u10s_ISP', 'nb_A_u10s_PDNS', 'nb_A_u10s_others',
'nb_A_u30s_ISP', 'nb_A_u30s_PDNS', 'nb_A_u30s_others',
'zombies', 'z_ISP', 'z_PDNS', 'z_others',
'first_3s', 'first_10s', 'sum_delay'
]
Expand All @@ -396,6 +427,12 @@ def save_and_close(self):
'googlepdns', 'cloudflare', 'opendns', 'quad9', 'level3', 'neustar', 'he' ]

class recap_row:
under_names = [
['nb_A_u300ms_ISP', 'nb_A_u300ms_PDNS', 'nb_A_u300ms_others'],
['nb_A_u1s_ISP', 'nb_A_u1s_PDNS', 'nb_A_u1s_others'],
['nb_A_u3s_ISP', 'nb_A_u3s_PDNS', 'nb_A_u3s_others'],
['nb_A_u10s_ISP', 'nb_A_u10s_PDNS', 'nb_A_u10s_others'],
['nb_A_u30s_ISP', 'nb_A_u30s_PDNS', 'nb_A_u30s_others']]
def __init__(self, row):
self.query_cc = row['CC']
self.query_AS = row['AS']
Expand All @@ -419,6 +456,9 @@ def __init__(self, row):
self.nb_A_ISP = row['nb_A_ISP']
self.nb_A_PDNS = row['nb_A_PDNS']
self.nb_A_others = row['nb_A_others']
for i in range(0,5):
for prov_index in range(0,3):
self.nb_A_under[1][prov_index] = row[recap_row.under_names[i][prov_index]]
self.zombies = row['zombies']
self.z_ISP = row['z_ISP']
self.z_PDNS = row['z_PDNS']
Expand Down Expand Up @@ -447,6 +487,9 @@ def add_row(self, row):
self.nb_A_ISP += row['nb_A_ISP']
self.nb_A_PDNS += row['nb_A_PDNS']
self.nb_A_others += row['nb_A_others']
for i in range(0,5):
for prov_index in range(0,3):
self.nb_A_under[1][prov_index] += row[recap_row.under_names[i][prov_index]]
self.zombies += row['zombies']
self.z_ISP += row['z_ISP']
self.z_PDNS += row['z_PDNS']
Expand Down Expand Up @@ -543,7 +586,10 @@ def save_file(self, file_name):
s += str(r_row.A_all3) + ","
s += str(r_row.nb_A_ISP) + ","
s += str(r_row.nb_A_PDNS) + ","
s += str(r_row.nb_A_others) + ","
s += str(r_row.nb_A_others) + ","
for i in range(0,5):
for prov_index in range(0,3):
s += str(self.nb_A_under[1][prov_index])
s += str(r_row.zombies) + ","
s += str(r_row.z_ISP) + ","
s += str(r_row.z_PDNS) + ","
Expand All @@ -566,6 +612,11 @@ def summary_columns():
'first_others', 'nb_https', 'nb_AAAA', 'nb_A',
'A_ISP_only', ' A_PDNS_only', ' A_ISP_PDNS', ' A_others_only', ' A_ISP_others', ' A_PDNS_others', ' A_all3',
'nb_A_ISP', ' nb_A_PDNS', ' nb_A_others',
'nb_A_u300ms_ISP', 'nb_A_u300ms_PDNS', 'nb_A_u300ms_others',
'nb_A_u1s_ISP', 'nb_A_u1s_PDNS', 'nb_A_u1s_others',
'nb_A_u3s_ISP', 'nb_A_u3s_PDNS', 'nb_A_u3s_others',
'nb_A_u10s_ISP', 'nb_A_u10s_PDNS', 'nb_A_u10s_others',
'nb_A_u30s_ISP', 'nb_A_u30s_PDNS', 'nb_A_u30s_others',
'zombies', 'z_ISP', 'z_PDNS', 'z_others',
'first_3s', 'first_10s', 'average_delay', 'max_delay' ]
return columns
Expand All @@ -590,6 +641,8 @@ def summary_row(self):
nb_A_ISP = 0
nb_A_PDNS = 0
nb_A_others = 0
nb_A_under = [
[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]
zombies = 0
z_ISP = 0
z_PDNS = 0
Expand Down Expand Up @@ -623,7 +676,10 @@ def summary_row(self):
nb_A_others += r_row.nb_A_others
zombies += r_row.zombies
z_ISP += r_row.z_ISP
z_PDNS += r_row.z_PDNS
z_PDNS += r_row.z_PDNS
for i in range(0,5):
for j in range(0,3):
nb_A_under[i][j] += r_row.nb_A_under[i][j]
z_others += r_row.z_others
first_3s += r_row.first_3s
first_10s += r_row.first_10s
Expand Down Expand Up @@ -662,6 +718,21 @@ def summary_row(self):
nb_A_ISP,
nb_A_PDNS,
nb_A_others,
nb_A_under[0][0],
nb_A_under[0][1],
nb_A_under[0][2],
nb_A_under[1][0],
nb_A_under[1][1],
nb_A_under[1][2],
nb_A_under[2][0],
nb_A_under[2][1],
nb_A_under[2][2],
nb_A_under[3][0],
nb_A_under[3][1],
nb_A_under[3][2],
nb_A_under[4][0],
nb_A_under[4][1],
nb_A_under[4][2],
zombies,
z_ISP,
z_PDNS,
Expand Down
6 changes: 3 additions & 3 deletions resolver/rsv_recap_daily.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ def load_bucket(bucket):
item = item[:-4]
if item.startswith("queries"):
item = item[7:]
output_file = os.path.join(temp_dir, "recap-daily" + item + ".csv")
output_file = os.path.join(temp_dir, "recap2-daily" + item + ".csv")
bucket = file_bucket(ip2a4, ip2a6, as_names, output_file, source_file, bucket_id, time_loaded)
bucket_list.append(bucket)
bucket_id += 1
Expand Down Expand Up @@ -132,15 +132,15 @@ def load_bucket(bucket):
nb_files = 0
for key in rcl.cc_as_list:
if rcl.cc_as_list[key].total_uids > 10000:
as_file = os.path.join(output_dir, "recap-" +
as_file = os.path.join(output_dir, "recap2-" +
rcl.cc_as_list[key].query_cc + "-" +
rcl.cc_as_list[key].query_AS + ".csv")
rcl.cc_as_list[key].save_file(as_file)
print("Saved: " + str(len(rcl.cc_as_list[key].slices)) + " slice in " + as_file)
nb_files += 1
print("Saved " + str(nb_files) + " CC/AS files.")

summary_file = os.path.join(output_dir, "recap-summary.csv")
summary_file = os.path.join(output_dir, "recap2-summary.csv")
df = rcl.summary_df()
df.to_csv(summary_file)
print("Saved " + str(df.shape[0]) + " CC/AS summaries in " + summary_file)
Loading