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.

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

Ned/studentmodulehistory cleaner command #411

Merged
merged 6 commits into from
Jul 19, 2013
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
239 changes: 239 additions & 0 deletions lms/djangoapps/courseware/management/commands/clean_history.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,239 @@
"""A command to clean the StudentModuleHistory table.

When we added XBlock storage, each field modification wrote a new history row
to the db. Now that we have bulk saves to avoid that database hammering, we
need to clean out the unnecessary rows from the database.

This command that does that.

"""

import datetime
import json
import logging
import optparse
import time
import traceback

from django.core.management.base import NoArgsCommand
from django.db import connection


class Command(NoArgsCommand):
"""The actual clean_history command to clean history rows."""

help = "Deletes unneeded rows from the StudentModuleHistory table."

option_list = NoArgsCommand.option_list + (
optparse.make_option(
'--batch',
type='int',
default=100,
help="Batch size, number of module_ids to examine in a transaction.",
),
optparse.make_option(
'--dry-run',
action='store_true',
default=False,
help="Don't change the database, just show what would be done.",
),
optparse.make_option(
'--sleep',
type='float',
default=0,
help="Seconds to sleep between batches.",
),
)

def handle_noargs(self, **options):
# We don't want to see the SQL output from the db layer.
logging.getLogger("django.db.backends").setLevel(logging.INFO)

smhc = StudentModuleHistoryCleaner(
dry_run=options["dry_run"],
)
smhc.main(batch_size=options["batch"], sleep=options["sleep"])


class StudentModuleHistoryCleaner(object):
"""Logic to clean rows from the StudentModuleHistory table."""

DELETE_GAP_SECS = 0.5 # Rows this close can be discarded.
STATE_FILE = "clean_history.json"
BATCH_SIZE = 100

def __init__(self, dry_run=False):
self.dry_run = dry_run
self.next_student_module_id = 0
self.last_student_module_id = 0

def main(self, batch_size=None, sleep=0):
"""Invoked from the management command to do all the work."""

batch_size = batch_size or self.BATCH_SIZE

connection.enter_transaction_management()

self.last_student_module_id = self.get_last_student_module_id()
self.load_state()

while self.next_student_module_id <= self.last_student_module_id:
for smid in self.module_ids_to_check(batch_size):
try:
self.clean_one_student_module(smid)
except Exception: # pylint: disable=W0703
trace = traceback.format_exc()
self.say("Couldn't clean student_module_id {}:\n{}".format(smid, trace))
if not self.dry_run:
self.commit()
self.save_state()
if sleep:
time.sleep(sleep)

def say(self, message):
"""
Display a message to the user.

The message will have a trailing newline added to it.

"""
print message

def commit(self):
"""
Commit the transaction.
"""
self.say("Committing")
connection.commit()

def load_state(self):
"""
Load the latest state from disk.
"""
try:
state_file = open(self.STATE_FILE)
except IOError:
self.say("No stored state")
self.next_student_module_id = 0
else:
with state_file:
state = json.load(state_file)
self.say(
"Loaded stored state: {}".format(
json.dumps(state, sort_keys=True)
)
)
self.next_student_module_id = state['next_student_module_id']

def save_state(self):
"""
Save the state to disk.
"""
state = {
'next_student_module_id': self.next_student_module_id,
}
with open(self.STATE_FILE, "w") as state_file:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is the fact that we're opening the state file every time a problem at all on when the disk is backed by EBS? I don't think it necessarily needs changing, but I am curious if it becomes a factor when you're doing the speed test for this.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We're only saving state once per batch, not once per id, so this should be fine.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure, but with these settings, we'd still have over half a million batches. If an open takes 10ms, that's an hour and a half. Probably not worth worrying about at this point -- I'm mostly just curious where this script will actually spend its time.

json.dump(state, state_file)
self.say("Saved state: {}".format(json.dumps(state, sort_keys=True)))

def get_last_student_module_id(self):
"""
Return the id of the last student_module.
"""
cursor = connection.cursor()
cursor.execute("""
SELECT max(student_module_id) FROM courseware_studentmodulehistory
""")
last = cursor.fetchone()[0]
self.say("Last student_module_id is {}".format(last))
return last

def module_ids_to_check(self, batch_size):
"""Produce a sequence of student module ids to check.

`batch_size` is how many module ids to produce, max.

The sequence starts with `next_student_module_id`, and goes up to
and including `last_student_module_id`.

`next_student_module_id` is updated as each id is yielded.

"""
start = self.next_student_module_id
for smid in range(start, start+batch_size):
if smid > self.last_student_module_id:
break
yield smid
self.next_student_module_id = smid+1

def get_history_for_student_modules(self, student_module_id):
"""
Get the history rows for a student module.

```student_module_id```: the id of the student module we're
interested in.

Return a list: [(id, created), ...], all the rows of history.

"""
cursor = connection.cursor()
cursor.execute("""
SELECT id, created FROM courseware_studentmodulehistory
WHERE student_module_id = %s
ORDER BY created, id
""",
[student_module_id]
)
history = cursor.fetchall()
return history

def delete_history(self, ids_to_delete):
"""
Delete history rows.

```ids_to_delete```: a non-empty list (or set...) of history row ids to delete.

"""
assert ids_to_delete
cursor = connection.cursor()
cursor.execute("""
DELETE FROM courseware_studentmodulehistory
WHERE id IN ({ids})
""".format(ids=",".join(str(i) for i in ids_to_delete))
)

def clean_one_student_module(self, student_module_id):
"""Clean one StudentModule's-worth of history.

`student_module_id`: the id of the StudentModule to process.

"""
delete_gap = datetime.timedelta(seconds=self.DELETE_GAP_SECS)

history = self.get_history_for_student_modules(student_module_id)
if not history:
self.say("No history for student_module_id {}".format(student_module_id))
return

ids_to_delete = []
next_created = None
for history_id, created in reversed(history):
if next_created is not None:
# Compare this timestamp with the next one.
if (next_created - created) < delete_gap:
# This row is followed closely by another, we can discard
# this one.
ids_to_delete.append(history_id)

next_created = created

verb = "Would have deleted" if self.dry_run else "Deleting"
self.say("{verb} {to_delete} rows of {total} for student_module_id {id}".format(
verb=verb,
to_delete=len(ids_to_delete),
total=len(history),
id=student_module_id,
))

if ids_to_delete and not self.dry_run:
self.delete_history(ids_to_delete)
Loading