Skip to content
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

checking in changes in verify-loader script for log loss simulation #17

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

checking in changes in verify-loader script for log loss simulation #17

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
592104b
checking in changes in verify-loader script for log loss simulation
atri-mandal Dec 8, 2020
f9d7121
adding more documentation + loss count/percentage
atri-mandal Dec 10, 2020
c29fceb
incorporating Peter's comments + changing print statements to new pyt…
atri-mandal Dec 14, 2020
16fd032
more fixes to verify-loader
atri-mandal Dec 14, 2020
b1bfc5c
removing commented lines; fixing print formatting
atri-mandal Dec 14, 2020
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
37 changes: 25 additions & 12 deletions verify-loader
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ def print_stats(invocid, ctx, payload):
assert ctx.prev == statseq
assert timestamp[-1] == 's'
now = time.time()
print("%s: %.2fs (%5.2fs) %12.3f %12.3f %d %d %d %d" % (
print("{}: {:.2f}s ({:5.2f}s) {:12.3f} {:12.3f} {} {} {} {}".format(
invocid, ts, now - ts, lclrate, gblrate, statseq,
ctx.count, ctx.skips, ctx.duplicates))
sys.stdout.flush()
Expand All @@ -122,8 +122,10 @@ def verify(input_gen, report_interval=REPORT_INTERVAL):

ignored_bytes = 0
ignored_count = 0
out_of_seq = 0

report_bytes = 0
# report stats after every <report_interval> MB
report_bytes_target = report_interval * MB
report_ignored_bytes = 0
report_ignored_count = 0
Expand All @@ -135,16 +137,19 @@ def verify(input_gen, report_interval=REPORT_INTERVAL):
try:
for line in input_gen:
line_len = len(line)
#find the log header: loader seq -
if not line.startswith("loader seq - "):
report_ignored_bytes += line_len
report_ignored_count += 1
else:
#check that the line has all the constituent parts (<header> - <uuid> - <seq_num> - <payload>)
try:
_, invocid, seqval, payload = line.split('-', 4)
except Exception:
report_ignored_bytes += line_len
report_ignored_count += 1
else:
#check if seq_num is valid
try:
seq = int(seqval)
except Exception:
Expand All @@ -155,9 +160,11 @@ def verify(input_gen, report_interval=REPORT_INTERVAL):
invocid = invocid.strip()
ctx = contexts[invocid]
prev = ctx.msg(seq, line_len)
# check for out of order lines - this implies LOG LOSS
if prev is not None:
# Bad record encountered, flag it
print("%s: %d %d <-" % (invocid, seq, prev))
print("{}: {} {} <-".format(invocid, seq, prev))
out_of_seq += 1
sys.stdout.flush()
if payload.startswith(" (stats:"):
print_stats(invocid, ctx, payload)
Expand All @@ -176,22 +183,25 @@ def verify(input_gen, report_interval=REPORT_INTERVAL):
for invocid, ctx in contexts.items():
report_count += ctx.report_count
if ctx.report():
print("%s: %d %d %d" % (invocid, ctx.count, ctx.skips, ctx.duplicates))
print("{}: {} {} {}".format(invocid, ctx.count, ctx.skips, ctx.duplicates))
total_bytes += ctx.bytes
total_count += ctx.count

print("interval read rate: %.3f MB/sec, %.3f/sec " \
"(ignored %.3f MB/sec, %.3f/sec); " \
"overall read rate: %.3f MB/sec %.3f/sec " \
"(ignored %.3f MB/sec, %.3f/sec)" % (
print("interval read rate: {%.3f} MB/sec, {%.3f}/sec " \
"(ignored {%.3f} MB/sec, {%.3f}/sec); " \
"overall read rate: {%.3f} MB/sec {%.3f}/sec " \
"(ignored {%.3f} MB/sec, {%.3f}/sec)" \
"(total lines {})" \
"(ignored lines {})".format(
(report_bytes / MB) / (now - report_start),
(report_count / (now - report_start)),
(report_ignored_bytes / MB) / (now - report_start),
(report_ignored_count / (now - report_start)),
(total_bytes / MB) / (now - start),
(total_count / (now - start)),
(ignored_bytes / MB) / (now - start),
(ignored_count / (now - start))))
(ignored_count / (now - start)),
(report_count, report_ignored_count)))
print("--- verify-loader\n")
sys.stdout.flush()

Expand Down Expand Up @@ -219,13 +229,16 @@ def verify(input_gen, report_interval=REPORT_INTERVAL):
if ignored_count + total_count > 0:
print("\n+++ verify-loader")
for invocid, ctx in contexts.items():
print("%s: %d %d %d" % (invocid, ctx.count, ctx.skips, ctx.duplicates))
print("overall read rate: %.3f MB/sec %.3f/sec " \
"(ignored %.3f MB/sec, %.3f/sec)" % (
print("{}: {} {} {}".format(invocid, ctx.count, ctx.skips, ctx.duplicates))

print("overall read rate: {:.3f} MB/sec {:.3f}/sec " \
"(ignored {:.3f} MB/sec, {:.3f}/sec)" \
"(total bytes {}, total lines {}, ignored lines {}, bad sequence {}({:.3f}%))".format(
(total_bytes / MB) / (now - start),
(total_count / (now - start)),
(ignored_bytes / MB) / (now - start),
(ignored_count / (now - start))))
(ignored_count / (now - start)),
total_bytes, total_count, ignored_count, out_of_seq, (out_of_seq*100.0)/total_count))
print("--- verify-loader\n")
if tot_skips + tot_dupes > 0:
ret_val = 1
Expand Down