Skip to content

fix/recover oom#1127

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.

Sign up for GitHub

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

Closed
Oppen wants to merge 2 commits into from
Closed

fix/recover oom #1127

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5d6b82d
fix: recover from panics
Oppen Sep 30, 2024
af92e33
fix: missed v3
Oppen Sep 30, 2024
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
20 changes: 18 additions & 2 deletions operator/pkg/operator.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -7,6 +7,7 @@ import (
"encoding/hex"
"fmt"
"log"
"runtime"
"sync"
"time"

Expand DownExpand Up@@ -241,8 +242,16 @@ func (o *Operator) ProcessNewBatchLogV2(newBatchLog *servicemanager.ContractAlig
wg.Add(verificationDataBatchLen)
for _, verificationData := range verificationDataBatch {
go func(data VerificationData) {
defer wg.Done()
defer func() {
if r := recover(); r != nil {
// Most common panic we experience is runtime OOM, so GC to keep going
runtime.GC()
o.Logger.Errorf("Verification goroutine panicked", "msg", r, "verification_data", verificationData)
}
wg.Done()
}()
o.verify(data, results)
//FIXME: include in the defer with failure metric
o.metrics.IncOperatorTaskResponses()
}(verificationData)
}
Expand DownExpand Up@@ -312,7 +321,14 @@ func (o *Operator) ProcessNewBatchLogV3(newBatchLog *servicemanager.ContractAlig
wg.Add(verificationDataBatchLen)
for _, verificationData := range verificationDataBatch {
go func(data VerificationData) {
defer wg.Done()
defer func() {
if r := recover(); r != nil {
// Most common panic we experience is runtime OOM, so GC to keep going
runtime.GC()
o.Logger.Errorf("Verification goroutine panicked", "msg", r, "verification_data", verificationData)
}
wg.Done()
}()
o.verify(data, results)
o.metrics.IncOperatorTaskResponses()
}(verificationData)
Expand Down