From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by lists.proxmox.com (Postfix) with ESMTPS id 634B26027D for ; Tue, 8 Sep 2020 13:19:01 +0200 (CEST) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 582B29509 for ; Tue, 8 Sep 2020 13:19:01 +0200 (CEST) Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com [212.186.127.180]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by firstgate.proxmox.com (Proxmox) with ESMTPS id 3A66794FF for ; Tue, 8 Sep 2020 13:19:00 +0200 (CEST) Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1]) by proxmox-new.maurer-it.com (Proxmox) with ESMTP id EC03E44985 for ; Tue, 8 Sep 2020 13:18:59 +0200 (CEST) To: Proxmox Backup Server development discussion , =?UTF-8?Q?Fabian_Gr=c3=bcnbichler?= References: <20200908091804.27685-1-s.reiter@proxmox.com> <1599563352.ezakbc52qx.astroid@nora.none> From: Stefan Reiter Message-ID: <2be25648-c858-e5eb-a447-76d8ab662bc2@proxmox.com> Date: Tue, 8 Sep 2020 13:18:58 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Thunderbird/60.9.0 MIME-Version: 1.0 In-Reply-To: <1599563352.ezakbc52qx.astroid@nora.none> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 8bit X-SPAM-LEVEL: Spam detection results: 0 AWL 0.460 Adjusted score from AWL reputation of From: address KAM_ASCII_DIVIDERS 0.8 Spam that uses ascii formatting tricks KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment NICE_REPLY_A -1.825 Looks like a legit reply (A) RCVD_IN_DNSWL_MED -2.3 Sender listed at https://www.dnswl.org/, medium trust SPF_HELO_NONE 0.001 SPF: HELO does not publish an SPF Record SPF_PASS -0.001 SPF: sender matches SPF record URIBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to URIBL was blocked. See http://wiki.apache.org/spamassassin/DnsBlocklists#dnsbl-block for more information. [datastore.rs, proxmox.com] Subject: Re: [pbs-devel] [PATCH proxmox-backup] gc: attach context to index reader errors and ignore NotFound X-BeenThere: pbs-devel@lists.proxmox.com X-Mailman-Version: 2.1.29 Precedence: list List-Id: Proxmox Backup Server development discussion List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Sep 2020 11:19:01 -0000 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 >> --- >> 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(res: Result) -> Result, Error> { >> + match res { >> + Ok(t) => Ok(Some(t)), >> + Err(err) => { >> + if let Some(ioerr) = err.downcast_ref::() { >> + 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 { >> 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 { >> -- >> 2.20.1 >> >> >> >> _______________________________________________ >> pbs-devel mailing list >> pbs-devel@lists.proxmox.com >> https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel >> >> >> > > > _______________________________________________ > pbs-devel mailing list > pbs-devel@lists.proxmox.com > https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel > >