Push to Amazon Glacier using amazonka

Here is a small Haskell package for pushing files to Amazon Glacier: https://github.com/carlohamalainen/glacier-push. It uses Brendan Hay’s amazonka API, in particular amazonka-glacier.

One thing that I couldn’t find in amazonka was a way to calculate the tree hash of a file. The Glacier API needs this for each part that is uploaded as well as the whole file. Amazon explains how to calculate the tree hash in their Glacier docs and provides sample code in Java and C++. Since the algorithm is recursive, it is quite short in Haskell:

oneMb :: Int64
oneMb = 1024*1024

treeHash :: BS.ByteString -> Hash
treeHash s = treeHash' $ map sha256 $ oneMbChunks s
    treeHash' []  = error "Internal error in treeHash'."
    treeHash' [x] = B16.encode x
    treeHash' xs  = treeHash' $ next xs

    next :: [BS.ByteString] -> [BS.ByteString]
    next []       = []
    next [a]      = [a]
    next (a:b:xs) = sha256 (BS.append a b) : next xs

    oneMbChunks :: BS.ByteString -> [BS.ByteString]
    oneMbChunks x
      | BS.length x <= oneMb = [x]
      | otherwise            = BS.take oneMb x : oneMbChunks (BS.drop oneMb x)

    sha256 :: BS.ByteString -> BS.ByteString
    sha256 = cs . SHA256.hashlazy

To push a large file to Glacier we do three things: initiate the multipart upload, upload each part (say, 100Mb chunks), and then finalize the upload.

Initiate the multipart upload

We do this to get an uploadId which is then used for each of the multipart uploads. We use initiateMultipartUpload, and need to set the part size.

initiateMulti env vault _partSize = send' env mpu
    mpu = initiateMultipartUpload accountId vault
            & imuPartSize .~ (Just $ cs $ show _partSize)

Upload the parts

With the response from initiating the multipart upload (the mu parameter in uploadOnePart) we can push a single part using uploadMultipartPart. Here we have to also set the checksum and content range:

uploadOnePart env vault mu p = do
    let Part{..} = p

    body <- toHashed <$> getPart _path (_partStart, _partEnd)

    uploadId <- case mu ^. imursUploadId of
                    Nothing     -> throw MissingUploadID
                    Just uid    -> return uid

    let ump = uploadMultipartPart accountId vault uploadId body
                & umpChecksum .~ (Just $ cs $ p ^. partHash)
                & umpRange    .~ Just cr

    send' env ump


    contentRange :: Int64 -> Int64 -> Text
    contentRange x y = "bytes " `append` cs (show x) `append` accountId `append` cs (show y) `append` "/*"

Complete the multipart upload

Completing the multipart upload lets Glacier know that it should start its job of assembling all the parts into a full archive. We have to set the archive size and the tree hash of the entire file.

completeMulti env vault mp mu = do
    uploadId <- case mu ^. imursUploadId of
                    Nothing     -> throw MissingUploadID
                    Just uid    -> return uid

    let cmu = completeMultipartUpload accountId vault uploadId
                & cmuArchiveSize .~ (Just $ cs $ show $ mp ^. multipartArchiveSize)
                & cmuChecksum    .~ (Just $ cs $ mp ^. multipartFullHash)

    send' env cmu


In each of these functions I used a helper for sending the request:

send' env x = liftIO $ runResourceT . runAWST env $ send x

I run the main block of work in a KatipContextT since I am using katip for structured logging. Adding new key-value info to the log context is accomplished using katipAddContext.

go vault' path = do
    $(logTM) InfoS "Startup."

    let vault = cs vault'

    let myPartSize = 128*oneMb

    mp  <- liftIO $ mkMultiPart path myPartSize

    env <- liftIO $ newEnv'
    mu  <- liftIO $ initiateMulti env vault myPartSize

    let uploadId = fromMaybe (error "No UploadId in response, can't continue multipart upload.")
                 $ mu ^. imursUploadId

    partResponses <- forM (mp ^. multiParts) $ \p ->
        katipAddContext (sl "uploadId" uploadId) $
        katipAddContext (sl "location" $ fromMaybe "(nothing)" $ mu ^. imursLocation) $ do
            doWithRetries 10 (uploadOnePart env vault mu p)

    case lefts partResponses of
        []   -> do $(logTM) InfoS "All parts uploaded successfully, now completing the multipart upload."
                   catch (do completeResponse <- completeMulti env vault mp mu
                             katipAddContext (sl "uploadId" uploadId)                             $
                              katipAddContext (sl "archiveId" $ completeResponse ^. acoArchiveId) $
                               katipAddContext (sl "checksum" $ completeResponse ^. acoChecksum ) $
                                katipAddContext (sl "location" $ completeResponse ^. acoLocation) $ do
                                  $(logTM) InfoS "Done"
                                  liftIO exitSuccess)
                         (\e -> do logServiceError "Failed to complete multipart upload." e
                                   $(logTM) ErrorS "Failed."
                                   liftIO exitFailure)

        errs -> do forM_ errs (logServiceError "Failed part upload.")
                   $(logTM) ErrorS "Too many part errors."
                   liftIO exitFailure

logServiceError msg (ServiceError e)
    = let smsg :: Text
          smsg = toText $ fromMaybe "" $ e ^. serviceMessage

          scode :: Text
          scode = toText $ e ^. serviceCode

        in katipAddContext (sl "serviceMessage" smsg) $
            katipAddContext (sl "serviceCode" scode)  $
             (headersAsContext $ e ^. serviceHeaders) $
               $(logTM) ErrorS msg

logServiceError msg (TransportError e)
    = let txt :: Text
          txt = toText $ show e
        in katipAddContext (sl "TransportError" txt) $
            $(logTM) ErrorS msg

logServiceError msg (SerializeError e)
    = let txt :: Text
          txt = toText $ show e
        in katipAddContext (sl "SerializeError" txt) $
            $(logTM) ErrorS msg

I found it handy to write this little helper function to turn each header from an amazonka ServiceError into a Katip context key/value pair:

headersAsContext :: KatipContext m => [Header] -> m a -> m a
headersAsContext hs = foldl (.) id $ map headerToContext hs
    headerToContext :: KatipContext m => Header -> m a -> m a
    headerToContext (h, x) = let h' = cs $ CI.original h :: Text
                                 x' = cs x               :: Text
                               in katipAddContext (sl h' x')

Katip can write to ElasticSearch using katip-elasticsearch. Then you’d be able to search for errors on specific header fields, etc.

Sample run

glacier-push-exe basement myfile
[2017-08-30 12:44:47][glacier-push.main][Info][x4][1724][ThreadId 7][main:Main app/Main.hs:300:7] Startup.
[2017-08-30 12:44:50][glacier-push.main][Info][x4][1724][ThreadId 7][location:/998720554704/vaults/basement/multipart-uploads/vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][partEnd:134217727][partStart:0][uploadId:vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][main:Main app/Main.hs:213:15] Uploading part.
[2017-08-30 12:45:45][glacier-push.main][Info][x4][1724][ThreadId 7][location:/998720554704/vaults/basement/multipart-uploads/vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][partEnd:268435455][partStart:134217728][uploadId:vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][main:Main app/Main.hs:213:15] Uploading part.
[2017-08-30 12:46:37][glacier-push.main][Info][x4][1724][ThreadId 7][location:/998720554704/vaults/basement/multipart-uploads/vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][partEnd:293601279][partStart:268435456][uploadId:vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][main:Main app/Main.hs:213:15] Uploading part.
[2017-08-30 12:46:55][glacier-push.main][Info][x4][1724][ThreadId 7][main:Main app/Main.hs:320:22] All parts uploaded successfully, now completing the multipart upload.
[2017-08-30 12:46:57][glacier-push.main][Info][x4][1724][ThreadId 7][archiveId:bImG6jM0eQGNC7kIJTsC_wtcAXdPDUtJ-NyfstrkxeyTtXC_iEgkvenH-h_eQH-LYbhVKWJM7WuZlb7OHKtgKJNEpOtVaqxEhlNRTHphUtLCurcHAQDHKkiTnIXTpFxgPgvP9Q0axA][checksum:4f08645d8f3705dc222eef7547591c400362806abb7a6298b9267ebf2be7d901][location:/998720554704/vaults/basement/archives/bImG6jM0eQGNC7kIJTsC_wtcAXdPDUtJ-NyfstrkxeyTtXC_iEgkvenH-h_eQH-LYbhVKWJM7WuZlb7OHKtgKJNEpOtVaqxEhlNRTHphUtLCurcHAQDHKkiTnIXTpFxgPgvP9Q0axA][uploadId:vZMCGNsLGhfTJ_hJ-CJ_OF_juCAY1IaZDl_A3YqOZXnuQRH_AtPiMaUE-K1JDew-ZwiIuDZgR3QbjsJIEfWtGeMNeKDs][main:Main app/Main.hs:326:37] Done

The lines are pretty long (as they are intended for consumption into ElasticSearch, not human parsing) so here is one with line breaks:

[2017-08-30 12:45:45]
 [ThreadId 7]
 [main:Main app/Main.hs:213:15] Uploading part.

Checking out and compiling

Use Stack. Then:

$ git clone https://github.com/carlohamalainen/glacier-push.git
$ cd glacier-push
$ stack build

To browse the source on github, have a look at:

FSA B3164 bottom bracket replacement

My Boardman Team TXC 650b hardtail mountain bike has an FSA crankset and bottom bracket. After a year and a half the bottom bracket got quite rough so I decided to swap it out with a Hope Hollowtech II bottom bracket.

I couldn’t find much online about this bottom bracket. Markings include: “FSA B3164 MegaExo 24mm MS185” and “BC1.37″ x 24T”.

I replaced it with this Hope bottom bracket, the 68/73mm model.


It comes with three spacers but not all are needed.

The drive side cup of the new bottom bracket screwed in easily but I stripped the thread of the bottom bracket on the non-drive side, probably due to gunk in the threads.

I managed to get the cup out and then used a dremel (on low speed) to clean up the threads.

To chase the threads, I made a few cuts into the new bottom bracket cup (following this video), which let me push into the bottom bracket enough to bite into the thread. If you do this you’ll probably destroy the thread completely, rendering the frame junk.


ghc-imported-from => ghc-mod (August 2017)

I have a pull request to merge ghc-imported-from into ghc-mod. The main benefit of being part of ghc-mod is that I don’t have to duplicate ghc-mod’s infrastructure for handling sandboxes, GHC options, interfaces to other build tools like Stack, and compatibility with more versions of GHC.

The pull request is still under review, so until then you can try it out by cloning the development branches:

git clone -b imported-from https://github.com/DanielG/ghc-mod.git ghc-mod-imported-from
cd ghc-mod-imported-from
cabal update && cabal sandbox init && cabal install
export PATH=`pwd`/.cabal-sandbox/bin:$PATH

Assuming that you use Plugged for managing Vim/Neovim plugins, use my branch of ghcmod-vim by adding this to your vimrc:

call plug#begin('~/.vim/plugged')

Plug 'carlohamalainen/ghcmod-vim', { 'branch': 'ghcmod-imported-from-cmd', 'for' : 'haskell' }

Install the plugin with :PlugInstall in vim.

Recently, xdg-open stopped working for me (others have had the same issue) so I recommend setting ghcmod_browser in your vimrc:

let g:ghcmod_browser = '/usr/bin/firefox'

Here are some handy key mappings:

au FileType  haskell nnoremap  :GhcModType
au FileType  haskell nnoremap  :GhcModInfo
au FileType  haskell nnoremap  :GhcModTypeClear

au FileType lhaskell nnoremap  :GhcModType
au FileType lhaskell nnoremap  :GhcModInfo
au FileType lhaskell nnoremap  :GhcModTypeClear

au FileType haskell  nnoremap  :GhcModOpenDoc
au FileType lhaskell nnoremap  :GhcModOpenDoc

au FileType haskell  nnoremap  :GhcModDocUrl
au FileType lhaskell nnoremap  :GhcModDocUrl

au FileType haskell  vnoremap  :GhcModOpenHaddockVismode
au FileType lhaskell vnoremap  :GhcModOpenHaddockVismode

au FileType haskell  vnoremap  :GhcModEchoUrlVismode
au FileType lhaskell vnoremap  :GhcModEchoUrlVismode

On the command line, use the imported-from command. It tells you the defining module, the exporting module, and the Haddock URL:

$ ghc-mod imported-from Foo.hs 9 34
base- Prelude /opt/ghc/7.10.3/share/doc/ghc/html/libraries/base-

From Vim/Neovim, navigate to a symbol and hit F4 which will open the Haddock URL in your browser, or F5 to echo the command-line output.

Ubuntu 17 – device not managed

I plugged in a D-Link DUB-1312 to my laptop running Ubuntu Zesty but Network Manager said that the interface was “not managed”.

The fix, found here, is to remove the contents of one file. Better to save the original file and touch an empty one:

$ sudo mv    /usr/lib/NetworkManager/conf.d/10-globally-managed-devices.conf{,_ORIGINAL}
$ sudo touch /usr/lib/NetworkManager/conf.d/10-globally-managed-devices.conf

For reference, here’s the info about the DUB-1312 USB ethernet adapter:

$ sudo apt update
$ sudo apt install hwinfo
$ sudo hwinfo --netcard

(other output snipped)

40: USB 00.0: 0200 Ethernet controller
  [Created at usb.122]
  Unique ID: VQs5.d0KcpDt5qE6
  Parent ID: 75L1.MLPSY0FvjsF
  SysFS ID: /devices/pci0000:00/0000:00:14.0/usb2/2-6/2-6.4/2-6.4.3/2-6.4.3:1.0
  SysFS BusID: 2-6.4.3:1.0
  Hardware Class: network
  Model: "D-Link DUB-1312"
  Hotplug: USB
  Vendor: usb 0x2001 "D-Link"
  Device: usb 0x4a00 "D-Link DUB-1312"
  Revision: "1.00"
  Serial ID: "000000000005FA"
  Driver: "ax88179_178a"
  Driver Modules: "ax88179_178a"
  Device File: enxe46f13f4be18
  HW Address: e4:6f:13:f4:be:18
  Permanent HW Address: e4:6f:13:f4:be:18
  Link detected: yes
  Module Alias: "usb:v2001p4A00d0100dcFFdscFFdp00icFFiscFFip00in00"
  Driver Info #0:
    Driver Status: ax88179_178a is active
    Driver Activation Cmd: "modprobe ax88179_178a"
  Config Status: cfg=new, avail=yes, need=no, active=unknown
  Attached to: #33 (Hub)

Structured logging to AWS ElasticSearch

A while ago I wrote about how to set up a structured logging service using PostgreSQL. AWS now makes it possible to have the same functionality (plus more) in the “serverless” style. For background on the idea of serverless architecture, watch this talk: GOTO 2017 • Serverless: the Future of Software Architecture • Peter Sbarski. Parts of this post are based on this guide on serverless AWS lambda elasticsearch and kibana.

First, create an Amazon Elasticsearch Service Domain. I used the smallest instance size since it’s just for personal use. Full docs are here.

For programmatic access control, create an AWS IAM user and make a note of its “arn” identifier, e.g. arn:aws:iam::000000000000:user/myiamuser. Then add an access policy as follows. We also add access to our IP address for the kibana interface. I made an ElasticSearch domain called “logs”; see the Resource field below:

  &quot;Version&quot;: &quot;2012-10-17&quot;,
  &quot;Statement&quot;: [
      &quot;Effect&quot;: &quot;Allow&quot;,
      &quot;Principal&quot;: {
        &quot;AWS&quot;: &quot;arn:aws:iam::000000000000:user/myiamuser&quot;
      &quot;Action&quot;: &quot;es:*&quot;,
      &quot;Resource&quot;: &quot;arn:aws:es:ap-southeast-1:000000000000:domain/logs/*&quot;
      &quot;Effect&quot;: &quot;Allow&quot;,
      &quot;Principal&quot;: {
        &quot;AWS&quot;: &quot;*&quot;
      &quot;Action&quot;: &quot;es:*&quot;,
      &quot;Resource&quot;: &quot;arn:aws:es:ap-southeast-1:000000000000:domain/logs/*&quot;,
      &quot;Condition&quot;: {
        &quot;IpAddress&quot;: {
          &quot;aws:SourceIp&quot;: &quot;xxx.xxx.xxx.xxx&quot;

To post to the ElasticSearch instance we use requests-aws4auth:

sudo pip install requests-aws4auth

Then we can post a document, a json blob, using the following script. Set the host, region, AWS key, and AWS secret key. This script saves the system temperature under an index system-stats with the ISO date attached.

import datetime 

from elasticsearch import Elasticsearch, RequestsHttpConnection
from requests_aws4auth import AWS4Auth

HOST        = 'search-logs-xxxxxxxxxxxxxxxxxxxxxxxxxx.ap-southeast-1.es.amazonaws.com' # see 'Endpoint' in ES status page
REGION      = 'ap-southeast-1' # choose the correct region
def get_temp():
    return 42.0 # actually read from 'sensors' or similar

if __name__ == '__main__':
    now  = datetime.datetime.now()
    date = now.date().isoformat()

    doc = {'host': 'blah', 'temperature': get_temp(), 'datetime': now.isoformat()}

    awsauth = AWS4Auth(AWS_KEY, AWS_SECRET, REGION, 'es')

    es = Elasticsearch(
            hosts=[{'host': HOST, 'port': 443}],
            http_auth=awsauth, use_ssl=True, verify_certs=True,

    _index = 'system-stats-' + date
    _type  = 'temperature'
    print doc
    print es.index(index=_index, doc_type=_type, body=doc)

To query data we use elasticsearch-dsl.

sudo pip install elasticsearch-dsl
from elasticsearch import Elasticsearch
from elasticsearch import RequestsHttpConnection
from requests_aws4auth import AWS4Auth

from elasticsearch_dsl import Search

from datetime import datetime

HOST        = 'search-logs-xxxxxxxxxxxxxxxxxxxxxxxxxx.ap-southeast-1.es.amazonaws.com' # see 'Endpoint' in ES status page
REGION      = 'ap-southeast-1' # choose the correct region

awsauth = AWS4Auth(AWS_KEY, AWS_SECRET, REGION, 'es')

client = Elasticsearch(
            hosts=[{'host': HOST, 'port': 443}],
            http_auth=awsauth, use_ssl=True, verify_certs=True,

plot_date      = '2017-08-06'
monitored_host = 'blah'

s = Search(using=client, index='system-stats-' + plot_date) \
       .query('match', host=monitored_host)

response = s.execute()

xy = [(datetime.strptime(hit.datetime, '%Y-%m-%dT%H:%M:%S.%f'), hit.temperature) for hit in response]
xy = sorted(xy, key=lambda z: z[0])

for (x, y) in xy:

Sample output:

$ python3 dump.py 
2017-08-06 04:00:02.337370 32.0
2017-08-06 05:00:01.779796 37.0
2017-08-06 07:00:01.789370 37.0
2017-08-06 11:00:01.711586 40.0
2017-08-06 12:00:02.054906 42.0
2017-08-06 16:00:02.075869 44.0
2017-08-06 18:00:01.619764 43.0
2017-08-06 19:00:02.319470 38.0
2017-08-06 20:00:03.098032 43.0
2017-08-06 22:00:03.629017 43.0

For exploring the data you can also use kibana, which is included with the ElasticSearch service from AWS.

Another nifty thing about the AWS infrastructure is that you can use Lambda to create ElasticSearch entries when objects drop in an S3 bucket. More details in this post.