[pbs-devel] [PATCH proxmox-backup] gc: attach context to index reader errors and ignore NotFound

[Stefan Reiter]

On 9/8/20 1:12 PM, Fabian Grünbichler wrote:
> On September 8, 2020 11:18 am, Stefan Reiter wrote:
>> Ignore NotFound errors during phase 1, this just means that a snapshot
>> was forgotten or pruned between scanning for .fidx/.didx files and
>> actually opening the index to touch the chunks.
> 
> I originally had a similar patch already lying around, but I am not sure
> whether this is not too dangerous in the face of transient errors?
> 
> I'd much rather get to a point where we are sure that no concurrent
> prune/forget operation can happen, and treat all errors as errors,
> instead of treating all not found errors as benign 'must have happened
> cause of concurrent actions'.
> 

So no forget/prune during phase 1 of GC? That sounds like it would cause 
quite some congestion.

> this is not pull, or download/restore, where we can just retry later -
> if we skip the index here, all the chunks it referenced are up for
> garbage collection unless they are saved by another index!
> 

I do see where you're coming from, but what alternative is there? If the 
index file is not found, we can't touch any referenced chunks anyway - 
there are none for us to see.

>>
>> ignore_notfound has to be a real function, since generics are not
>> supported for closures.
>>
>> The open methods for dynamic and fixed indices are switched from the
>> usual format_err! to err.context() to allow checking for the root error
>> (and thus the io::ErrorKind) further up the call chain.
>>
>> Signed-off-by: Stefan Reiter <s.reiter at proxmox.com>
>> ---
>>   src/backup/datastore.rs     | 28 ++++++++++++++++++++++++----
>>   src/backup/dynamic_index.rs |  5 ++++-
>>   src/backup/fixed_index.rs   |  7 +++++--
>>   3 files changed, 33 insertions(+), 7 deletions(-)
>>
>> diff --git a/src/backup/datastore.rs b/src/backup/datastore.rs
>> index ebe47487..1f455d64 100644
>> --- a/src/backup/datastore.rs
>> +++ b/src/backup/datastore.rs
>> @@ -426,6 +426,20 @@ impl DataStore {
>>           Ok(())
>>       }
>>   
>> +    fn ignore_notfound<T>(res: Result<T, Error>) -> Result<Option<T>, Error> {
>> +        match res {
>> +            Ok(t) => Ok(Some(t)),
>> +            Err(err) => {
>> +                if let Some(ioerr) = err.downcast_ref::<std::io::Error>() {
>> +                    if ioerr.kind() == std::io::ErrorKind::NotFound {
>> +                        return Ok(None);
>> +                    }
>> +                }
>> +                Err(err)
>> +            }
>> +        }
>> +    }
>> +
>>       fn mark_used_chunks(&self, status: &mut GarbageCollectionStatus, worker: &WorkerTask) -> Result<(), Error> {
>>   
>>           let image_list = self.list_images()?;
>> @@ -443,11 +457,17 @@ impl DataStore {
>>   
>>               if let Ok(archive_type) = archive_type(&path) {
>>                   if archive_type == ArchiveType::FixedIndex {
>> -                    let index = self.open_fixed_reader(&path)?;
>> -                    self.index_mark_used_chunks(index, &path, status, worker)?;
>> +                    if let Some(index) = Self::ignore_notfound(self.open_fixed_reader(&path))? {
>> +                        self.index_mark_used_chunks(index, &path, status, worker)?;
>> +                    } else {
>> +                        worker.warn(format!("warning: could no longer find fixed index '{:?}'", &path));
>> +                    }
>>                   } else if archive_type == ArchiveType::DynamicIndex {
>> -                    let index = self.open_dynamic_reader(&path)?;
>> -                    self.index_mark_used_chunks(index, &path, status, worker)?;
>> +                    if let Some(index) = Self::ignore_notfound(self.open_dynamic_reader(&path))? {
>> +                        self.index_mark_used_chunks(index, &path, status, worker)?;
>> +                    } else {
>> +                        worker.warn(format!("warning: could no longer find dynamic index '{:?}'", &path));
>> +                    }
>>                   }
>>               }
>>               done += 1;
>> diff --git a/src/backup/dynamic_index.rs b/src/backup/dynamic_index.rs
>> index f70aa44f..a7ce0f24 100644
>> --- a/src/backup/dynamic_index.rs
>> +++ b/src/backup/dynamic_index.rs
>> @@ -86,7 +86,10 @@ impl DynamicIndexReader {
>>           File::open(path)
>>               .map_err(Error::from)
>>               .and_then(Self::new)
>> -            .map_err(|err| format_err!("Unable to open dynamic index {:?} - {}", path, err))
>> +            .map_err(|err| {
>> +                let msg = format!("Unable to open dynamic index {:?} - {}", path, err);
>> +                err.context(msg)
>> +            })
>>       }
>>   
>>       pub fn new(mut file: std::fs::File) -> Result<Self, Error> {
>> diff --git a/src/backup/fixed_index.rs b/src/backup/fixed_index.rs
>> index 5d6cc1ff..bf864173 100644
>> --- a/src/backup/fixed_index.rs
>> +++ b/src/backup/fixed_index.rs
>> @@ -1,4 +1,4 @@
>> -use anyhow::{bail, format_err, Error};
>> +use anyhow::{bail, Error};
>>   use std::io::{Seek, SeekFrom};
>>   
>>   use super::chunk_stat::*;
>> @@ -62,7 +62,10 @@ impl FixedIndexReader {
>>           File::open(path)
>>               .map_err(Error::from)
>>               .and_then(|file| Self::new(file))
>> -            .map_err(|err| format_err!("Unable to open fixed index {:?} - {}", path, err))
>> +            .map_err(|err| {
>> +                let msg = format!("Unable to open fixed index {:?} - {}", path, err);
>> +                err.context(msg)
>> +            })
>>       }
>>   
>>       pub fn new(mut file: std::fs::File) -> Result<Self, Error> {
>> -- 
>> 2.20.1
>>
>>
>>
>> _______________________________________________
>> pbs-devel mailing list
>> pbs-devel at lists.proxmox.com
>> https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel
>>
>>
>>
> 
> 
> _______________________________________________
> pbs-devel mailing list
> pbs-devel at lists.proxmox.com
> https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel
> 
>