def upload_db_cache_to_s3():
"""
Update the S3 bucket with the bokchoy DB cache files.
"""
fingerprint = fingerprint_bokchoy_db_files(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)
zipfile_name, zipfile_path = create_tarfile_from_db_cache(
fingerprint, BOKCHOY_DB_FILES, CACHE_FOLDER)
upload_to_s3(zipfile_name, zipfile_path, CACHE_BUCKET_NAME)
def refresh_bokchoy_db_cache_from_s3(fingerprint=None):
"""
If the cache files for the current fingerprint exist
in s3 then replace what you have on disk with those.
If no copy exists on s3 then continue without error.
"""
if not fingerprint:
fingerprint = fingerprint_bokchoy_db_files(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)
bucket_name = CACHE_BUCKET_NAME
path = CACHE_FOLDER
if is_fingerprint_in_bucket(fingerprint, bucket_name):
zipfile_name = '{}.tar.gz'.format(fingerprint)
get_file_from_s3(bucket_name, zipfile_name, path)
zipfile_path = os.path.join(path, zipfile_name)
print("Extracting db cache files.")
extract_files_from_zip(BOKCHOY_DB_FILES, zipfile_path, path)
os.remove(zipfile_path)
def update_local_bokchoy_db_from_s3():
"""
Update the MYSQL database for bokchoy testing:
* Determine if your current cache files are up to date
with all the migrations
* If not then check if there is a copy up at s3
* If so then download then extract it
* Otherwise apply migrations as usual
"""
fingerprint = fingerprint_bokchoy_db_files(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)
if does_fingerprint_on_disk_match(fingerprint):
print("DB cache files match the current migrations.")
# TODO: we don't really need to apply migrations, just to
# load the db cache files into the database.
apply_migrations(BOKCHOY_DB_FILES, update_cache_files=False)
elif is_fingerprint_in_bucket(fingerprint, CACHE_BUCKET_NAME):
print("Found updated bokchoy db files at S3.")
refresh_bokchoy_db_cache_from_s3(fingerprint=fingerprint)
# TODO: we don't really need to apply migrations, just to
# load the db cache files into the database.
apply_migrations(BOKCHOY_DB_FILES, update_cache_files=False)
# Write the new fingerprint to disk so that it reflects the
# current state of the system.
compute_fingerprint_and_write_to_disk(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)
else:
msg = "{} {} {}".format("Did not find updated bokchoy db files at S3.",
"Loading the bokchoy db files from disk",
"and running migrations.")
print(msg)
apply_migrations(BOKCHOY_DB_FILES, update_cache_files=True)
# Write the new fingerprint to disk so that it reflects the
# current state of the system.
# E.g. you could have added a new migration in your PR.
compute_fingerprint_and_write_to_disk(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)
def update_local_bokchoy_db_from_s3(options):
"""
Prepare the local MYSQL test database for running bokchoy tests. Since
most pull requests do not introduce migrations, this task provides
an optimization for caching the state of the db when migrations are
added into a bucket in s3. Subsequent commits can avoid rerunning
migrations by using the cache files from s3, until the local cache files
are updated by running the `update_bokchoy_db_cache` Paver task, and
committing the updated cache files to github.
Steps:
1. Determine which migrations, if any, need to be applied to your current
db cache files to make them up to date
2. Compute the sha1 fingerprint of the local db cache files and the output
of the migration
3a. If the fingerprint computed in step 2 is equal to the local
fingerprint file, load the cache files into the MYSQL test database
3b. If the fingerprints are not equal, but there is bucket matching the
fingerprint computed in step 2, download and extract the contents of
bucket (db cache files) and load them into the MYSQL test database
3c. If the fingerprints are not equal AND there is no bucket matching the
fingerprint computed in step 2, load the local db cache files into
the MYSQL test database and apply any needed migrations. Create a
bucket in s3 named the fingerprint computed in step 2 and push the
newly updated db cache files to the bucket.
NOTE: the computed fingerprints referenced in this and related functions
represent the state of the db cache files and migration output PRIOR
to running migrations. The corresponding s3 bucket named for a given
fingerprint contains the db cache files AFTER applying migrations
"""
fingerprint = fingerprint_bokchoy_db_files(MIGRATION_OUTPUT_FILES, ALL_DB_FILES)
fingerprints_match = does_fingerprint_on_disk_match(fingerprint)
# Calculating the fingerprint already reset the DB, so we don't need to
# do it again (hence use_existing_db=True below)
if fingerprints_match:
print("DB cache files match the current migrations.")
reset_test_db(BOKCHOY_DB_FILES, update_cache_files=False, use_existing_db=True)
elif is_fingerprint_in_bucket(fingerprint, CACHE_BUCKET_NAME):
print("Found updated bokchoy db files at S3.")
refresh_bokchoy_db_cache_from_s3(fingerprint, CACHE_BUCKET_NAME, BOKCHOY_DB_FILES)
reset_test_db(BOKCHOY_DB_FILES, update_cache_files=False, use_existing_db=True)
else:
msg = u"{} {} {}".format(
"Did not find updated bokchoy db files at S3.",
"Loading the bokchoy db files from disk",
"and running migrations."
)
print(msg)
reset_test_db(BOKCHOY_DB_FILES, update_cache_files=True, use_existing_db=True)
# Check one last time to see if the fingerprint is present in
# the s3 bucket. This could occur because the bokchoy job is
# sharded and running the same task in parallel
if not is_fingerprint_in_bucket(fingerprint, CACHE_BUCKET_NAME):
upload_db_cache_to_s3(fingerprint, BOKCHOY_DB_FILES, CACHE_BUCKET_NAME)
else:
msg = u"{} {}. {}".format(
"Found a matching fingerprint in bucket ",
CACHE_BUCKET_NAME,
"Not pushing to s3"
)
print(msg)
rewrite_fingerprint = getattr(options, 'rewrite_fingerprint', False)
# If the rewrite_fingerprint flag is set, and the fingerpint has changed,
# write it to disk.
if not fingerprints_match and rewrite_fingerprint:
print("Updating fingerprint and writing to disk.")
compute_fingerprint_and_write_to_disk(MIGRATION_OUTPUT_FILES, ALL_DB_FILES)
def update_local_bokchoy_db_from_s3(options):
"""
Prepare the local MYSQL test database for running bokchoy tests. Since
most pull requests do not introduce migrations, this task provides
an optimization for caching the state of the db when migrations are
added into a bucket in s3. Subsequent commits can avoid rerunning
migrations by using the cache files from s3, until the local cache files
are updated by running the `update_bokchoy_db_cache` Paver task, and
committing the updated cache files to github.
Steps:
1. Determine which migrations, if any, need to be applied to your current
db cache files to make them up to date
2. Compute the sha1 fingerprint of the local db cache files and the output
of the migration
3a. If the fingerprint computed in step 2 is equal to the local
fingerprint file, load the cache files into the MYSQL test database
3b. If the fingerprints are not equal, but there is bucket matching the
fingerprint computed in step 2, download and extract the contents of
bucket (db cache files) and load them into the MYSQL test database
3c. If the fingerprints are not equal AND there is no bucket matching the
fingerprint computed in step 2, load the local db cache files into
the MYSQL test database and apply any needed migrations. Create a
bucket in s3 named the fingerprint computed in step 2 and push the
newly updated db cache files to the bucket.
NOTE: the computed fingerprints referenced in this and related functions
represent the state of the db cache files and migration output PRIOR
to running migrations. The corresponding s3 bucket named for a given
fingerprint contains the db cache files AFTER applying migrations
"""
fingerprint = fingerprint_bokchoy_db_files(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)
fingerprints_match = does_fingerprint_on_disk_match(fingerprint)
# Calculating the fingerprint already reset the DB, so we don't need to
# do it again (hence use_existing_db=True below)
if fingerprints_match:
print("DB cache files match the current migrations.")
reset_test_db(BOKCHOY_DB_FILES,
update_cache_files=False,
use_existing_db=True)
elif is_fingerprint_in_bucket(fingerprint, CACHE_BUCKET_NAME):
print("Found updated bokchoy db files at S3.")
refresh_bokchoy_db_cache_from_s3(fingerprint, CACHE_BUCKET_NAME,
BOKCHOY_DB_FILES)
reset_test_db(BOKCHOY_DB_FILES,
update_cache_files=False,
use_existing_db=True)
else:
msg = "{} {} {}".format("Did not find updated bokchoy db files at S3.",
"Loading the bokchoy db files from disk",
"and running migrations.")
print(msg)
reset_test_db(BOKCHOY_DB_FILES,
update_cache_files=True,
use_existing_db=True)
# Check one last time to see if the fingerprint is present in
# the s3 bucket. This could occur because the bokchoy job is
# sharded and running the same task in parallel
if not is_fingerprint_in_bucket(fingerprint, CACHE_BUCKET_NAME):
upload_db_cache_to_s3(fingerprint, BOKCHOY_DB_FILES,
CACHE_BUCKET_NAME)
else:
msg = "{} {}. {}".format("Found a matching fingerprint in bucket ",
CACHE_BUCKET_NAME, "Not pushing to s3")
print(msg)
rewrite_fingerprint = getattr(options, 'rewrite_fingerprint', False)
# If the rewrite_fingerprint flag is set, and the fingerpint has changed,
# write it to disk.
if not fingerprints_match and rewrite_fingerprint:
print("Updating fingerprint and writing to disk.")
compute_fingerprint_and_write_to_disk(MIGRATION_OUTPUT_FILES,
ALL_DB_FILES)