fix(web): fix plot endpoint to accept form params and fix test assertions

.gitea/ISSUE_TEMPLATE/bug_report.yaml

@@ -1,97 +0,0 @@
-name: "Bug Report"
-description: "Report a bug or unexpected behavior to help us improve"
-title: "[BUG]: "
-labels: ["bug"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        ## ⚠️ Before You Begin
-        Please ensure you have:
-        - [ ] Searched existing issues to avoid duplicates
-        - [ ] Confirmed this is a bug, not a question or configuration problem
-
-  - type: textarea
-    id: description
-    attributes:
-      label: "📋 Description"
-      description: "Provide a clear and concise description of the bug"
-      placeholder: "What happened? What did you expect to happen instead?"
-    validations:
-      required: true
-
-  - type: textarea
-    id: reproduction
-    attributes:
-      label: "🔁 Steps to Reproduce"
-      description: "Step-by-step instructions to reproduce the issue"
-      placeholder: |
-        1. Go to '...'
-        2. Click on '....'
-        3. Scroll down to '....'
-        4. See error
-    validations:
-      required: true
-
-  - type: textarea
-    id: expected
-    attributes:
-      label: "✅ Expected Behavior"
-      description: "What you expected to happen"
-      placeholder: "A clear description of what should happen..."
-    validations:
-      required: true
-
-  - type: textarea
-    id: actual
-    attributes:
-      label: "❌ Actual Behavior"
-      description: "What actually happened"
-      placeholder: "Include error messages, stack traces, or unexpected outcomes..."
-    validations:
-      required: true
-
-  - type: textarea
-    id: logs
-    attributes:
-      label: "📄 Logs / Screenshots"
-      description: |
-        Provide relevant logs, error messages, or screenshots.
-        For logs, please use a pastebin and share the URL.
-        **Remember to remove any sensitive information (API keys, passwords, etc.).**
-      placeholder: "Paste logs here or provide a Gist URL..."
-    validations:
-      required: false
-
-  - type: markdown
-    attributes:
-      value: |
-        ---
-        ## 🖥️ Environment Details
-        Please fill out the relevant information below.
-
-  - type: textarea
-    id: additional
-    attributes:
-      label: "📎 Additional Context"
-      description: "Any other information that might be relevant"
-      placeholder: |
-        - Database type and version (e.g., PostgreSQL 15, SQLite)
-        - Reverse proxy/CDN in use (e.g., Nginx, Cloudflare)
-        - Any custom configuration
-        - Related issues or PRs
-    validations:
-      required: false
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: "✅ Submission Checklist"
-      description: "Please confirm the following before submitting"
-      options:
-        - label: "I have searched for existing issues (open and closed) that report the same problem"
-          required: true
-        - label: "I have provided clear steps to reproduce the issue"
-          required: true
-        - label: "I have included relevant logs or error messages (with sensitive info removed)"
-          required: false

.gitea/ISSUE_TEMPLATE/feature_request.yaml

@@ -1,99 +0,0 @@
-name: "Feature Request"
-description: "Suggest a new feature or enhancement for this project"
-title: "[FEATURE]: "
-labels: ["enhancement"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        ## ⚠️ Before You Begin
-        Please ensure you have:
-        - [ ] Searched existing issues (open and closed) to avoid duplicates
-        - [ ] Reviewed the [project documentation](https://git.vmn.su/max/vmn-ansible/wiki) for existing functionality
-        - [ ] Confirmed this is a feature request, not a bug or configuration question
-
-
-  - type: textarea
-    id: problem
-    attributes:
-      label: "🎯 Problem Statement"
-      description: "What problem does this feature solve? What can't you do today?"
-      placeholder: |
-        I'm always frustrated when...
-        Currently, it's hard/impossible to...
-        This feature would help me because...
-    validations:
-      required: true
-
-  - type: textarea
-    id: solution
-    attributes:
-      label: "💡 Proposed Solution"
-      description: "Describe the solution you'd like to see"
-      placeholder: |
-        A clear description of what you want to happen.
-        If you have a specific API, UI, or implementation in mind, describe it here.
-    validations:
-      required: true
-
-  - type: textarea
-    id: screenshots
-    attributes:
-      label: "📸 Screenshots"
-      description: "If you can, provide screenshots or diagrams of the proposed feature"
-      placeholder: "Drag and drop images or paste links..."
-    validations:
-      required: false
-
-  - type: textarea
-    id: technical
-    attributes:
-      label: "⚙️ Technical Approach"
-      description: "If you have ideas about how to implement this, share them here"
-      placeholder: |
-        - Which components/modules would be affected?
-        - Any database schema changes?
-        - API design considerations?
-    validations:
-      required: false
-
-  - type: textarea
-    id: acceptance
-    attributes:
-      label: "✅ Acceptance Criteria"
-      description: "What does 'done' look like for this feature?"
-      placeholder: |
-        - [ ] Feature works in the UI
-        - [ ] API endpoints are documented
-        - [ ] Tests are added
-        - [ ] Documentation is updated
-    validations:
-      required: false
-
-  - type: dropdown
-    id: contribution
-    attributes:
-      label: "🤝 Are you willing to contribute this feature?"
-      description: "Knowing if you can help implement this helps us prioritize"
-      options:
-        - "Yes, I can contribute"
-        - "Yes, but I need guidance"
-        - "No, but I can test/review"
-        - "No, I'm just requesting"
-    validations:
-      required: true
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: "✅ Submission Checklist"
-      description: "Please confirm the following before submitting"
-      options:
-        - label: "I have searched for existing issues (open and closed) that request the same feature"
-          required: true
-        - label: "I have explained the problem this feature solves"
-          required: true
-        - label: "I have described a concrete solution or direction"
-          required: true
-        - label: "I have considered alternatives and explained why they fall short"
-          required: false

.gitea/ISSUE_TEMPLATE/refactor.yaml

@@ -1,134 +0,0 @@
-name: "Refactor Request"
-description: "Propose a code restructuring or cleanup with no behavior change"
-title: "[REFACTOR]: "
-labels: ["refactoring"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        ## ⚠️ Before You Begin
-        Please ensure you have:
-        - [ ] Searched existing issues (open and closed) to avoid duplicates
-        - [ ] Reviewed the [project documentation](https://git.vmn.su/max/vmn-ansible/wiki) for architecture guidelines
-        - [ ] Confirmed this is a refactor (code restructuring with NO behavior change), not a bug fix or new feature
-
-
-  - type: textarea
-    id: problem
-    attributes:
-      label: "🎯 Problem Statement"
-      description: "What pain points does the current code cause? Why is this refactor needed?"
-      placeholder: |
-        The current implementation is difficult to maintain because...
-        This code has accumulated technical debt due to...
-        I'm constantly frustrated when working with this module because...
-    validations:
-      required: true
-
-  - type: textarea
-    id: scope
-    attributes:
-      label: "📂 Scope"
-      description: "Which files, modules, or components need refactoring? Be specific."
-      placeholder: |
-        - File paths: `src/auth/`, `internal/handler/`
-        - Component: `UserService` class
-    validations:
-      required: true
-
-  - type: textarea
-    id: current-state
-    attributes:
-      label: "🔍 Current State"
-      description: "Describe the current code structure, its issues, and why it's problematic"
-      placeholder: |
-        - The function `processUser()` is 500+ lines long
-        - Duplicated logic across 3 different files
-        - Mixed concerns (business logic + HTTP handling)
-        - Poor test coverage makes changes risky
-        - Naming is unclear and inconsistent
-    validations:
-      required: true
-
-  - type: textarea
-    id: proposed-changes
-    attributes:
-      label: "💡 Proposed Solution"
-      description: "What should the code look like after the refactor?"
-      placeholder: |
-        - Extract `processUser()` into smaller, focused functions
-        - Consolidate duplicated logic into a shared utility
-        - Separate business logic from HTTP handlers
-        - Introduce interfaces for better testability
-        - Rename variables and functions for clarity
-    validations:
-      required: true
-
-  - type: textarea
-    id: constraints
-    attributes:
-      label: "🚫 Constraints"
-      description: "What must NOT change? Public APIs, behavior, backward compatibility, performance characteristics?"
-      placeholder: |
-        - All public APIs must remain identical
-        - Database schema must not change
-        - External behavior must be identical
-        - Response formats must stay the same
-        - Performance must not degrade
-    validations:
-      required: true
-
-  - type: textarea
-    id: benefits
-    attributes:
-      label: "📈 Expected Benefits"
-      description: "What improvements will this refactor bring?"
-      placeholder: |
-        - Improved maintainability
-        - Better testability
-        - Reduced code duplication
-        - Clearer separation of concerns
-        - Easier onboarding for new contributors
-    validations:
-      required: false
-
-  - type: textarea
-    id: risks
-    attributes:
-      label: "⚠️ Risks & Mitigations"
-      description: "What could go wrong, and how will you mitigate it?"
-      placeholder: |
-        - Risk: Regression bugs
-          Mitigation: Comprehensive test coverage before and after
-        - Risk: Large diff making code review difficult
-          Mitigation: Break into smaller, incremental PRs
-    validations:
-      required: false
-
-  - type: dropdown
-    id: contribution
-    attributes:
-      label: "🤝 Are you willing to contribute this refactor?"
-      description: "Knowing if you can help implement this helps us prioritize"
-      options:
-        - "Yes, I can contribute"
-        - "Yes, but I need guidance"
-        - "No, but I can review"
-        - "No, I'm just suggesting"
-    validations:
-      required: true
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: "✅ Submission Checklist"
-      description: "Please confirm the following before submitting"
-      options:
-        - label: "I have searched for existing issues (open and closed) that request the same refactor"
-          required: true
-        - label: "I have clearly explained the problem this refactor solves"
-          required: true
-        - label: "I have described the scope of the refactor (specific files/modules)"
-          required: false
-        - label: "I have identified what must NOT change (APIs, behavior, backward compatibility)"
-          required: false

.gitignore

@@ -1,3 +1,52 @@
 .vscode
 __pycache__
-test_data
+test_data
+
+# Python
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+ENV/
+env/
+
+# IDE
+.idea/
+*.swp
+*.swo
+
+# Environment variables
+.env
+.env.local
+
+# Test coverage
+.htmlcov/
+.coverage
+.coverage.*
+coverage.xml
+
+# Pytest
+.pytest_cache/
+
+# Generated files
+*.png
+*.csv
+data/samples/*.csv

README.md

@@ -0,0 +1,78 @@
+# Disk Checker
+
+Disk benchmarking and latency visualization tool for fio and badblocks output.
+
+## Features
+
+- Parse fio JSON+ latency CSV files
+- Generate histogram and CDF plots
+- REST API for remote benchmarking
+- Async job management for long-running benchmarks
+
+## Installation
+
+```bash
+git clone <repository>
+cd disk-checker
+python -m venv venv
+source venv/bin/activate
+pip install -e ".[dev]"
+```
+
+## CLI Usage
+
+```bash
+# Basic usage
+python -m disk_checker scan_latency.csv
+
+# With options
+python -m disk_checker scan_latency.csv --metric read_clat --unit ms --log-x
+
+# Generate CDF
+python -m disk_checker scan_latency.csv --cdf
+
+# View all metrics
+python -m disk_checker scan_latency.csv --all-metrics
+```
+
+## API Usage
+
+```bash
+# Start the server
+python -m disk_checker.scripts.serve --host 0.0.0.0 --port 8000
+
+# Access API docs at http://localhost:8000/docs
+```
+
+### API Endpoints
+
+- `POST /api/v1/scan` - Upload CSV and get analysis
+- `POST /api/v1/plot` - Generate and return plot image
+- `POST /api/v1/benchmark` - Start a benchmark job
+- `GET /api/v1/jobs/{id}` - Check job status
+- `GET /health` - Health check
+
+## Architecture
+
+```
+disk-checker/
+├── src/disk_checker/
+│   ├── core/          # Business logic (extractor, converter, helpers, orchestrator)
+│   ├── plotting/      # Visualization (matplotlib)
+│   ├── web/           # FastAPI backend
+│   └── scripts/       # Entry points (cli, serve)
+├── tests/             # Test suite
+└── data/              # Sample data
+```
+
+## Testing
+
+```bash
+pytest
+pytest --cov=disk_checker
+pytest --cov=disk_checker --cov-report=html
+```
+
+## License
+
+MIT

data/samples/scan_latency_job0.csv

@@ -0,0 +1,67 @@
+nsec, read_slat_ns_count, read_slat_ns_cumulative, read_slat_ns_percentile, read_clat_ns_count, read_clat_ns_cumulative, read_clat_ns_percentile, read_lat_ns_count, read_lat_ns_cumulative, read_lat_ns_percentile, write_slat_ns_count, write_slat_ns_cumulative, write_slat_ns_percentile, write_clat_ns_count, write_clat_ns_cumulative, write_clat_ns_percentile, write_lat_ns_count, write_lat_ns_cumulative, write_lat_ns_percentile, trim_slat_ns_count, trim_slat_ns_cumulative, trim_slat_ns_percentile, trim_clat_ns_count, trim_clat_ns_cumulative, trim_clat_ns_percentile, trim_lat_ns_count, trim_lat_ns_cumulative, trim_lat_ns_percentile, 
+19791872, , , , 1, 1, 0.00016775708773695687, , , , , , , , , , , , , , , , , , , , , , 
+22413312, , , , 4, 5, 0.0008387854386847844, , , , , , , , , , , , , , , , , , , , , , 
+22675456, , , , 9, 14, 0.0023485992283173965, , , , , , , , , , , , , , , , , , , , , , 
+22937600, , , , 2, 16, 0.00268411340379131, , , , , , , , , , , , , , , , , , , , , , 
+23461888, , , , 2, 18, 0.003019627579265224, , , , , , , , , , , , , , , , , , , , , , 
+23724032, , , , 7, 25, 0.004193927193423922, , , , , , , , , , , , , , , , , , , , , , 
+23986176, , , , 14, 39, 0.006542526421741319, , , , , , , , , , , , , , , , , , , , , , 
+24248320, , , , 1, 40, 0.006710283509478276, , , , , , , , , , , , , , , , , , , , , , 
+24772608, , , , 2, 42, 0.007045797684952189, , , , , , , , , , , , , , , , , , , , , , 
+25034752, , , , 2, 44, 0.007381311860426103, , , , , , , , , , , , , , , , , , , , , , 
+25296896, , , , 4, 48, 0.00805234021137393, , , , , , , , , , , , , , , , , , , , , , 
+25559040, , , , 8, 56, 0.009394396913269586, , , , , , , , , , , , , , , , , , , , , , 
+25821184, , , , 9, 65, 0.010904210702902198, , , , , , , , , , , , , , , , , , , , , , 
+26083328, , , , 9, 74, 0.012414024492534809, , , , , , , , , , , , , , , , , , , , , , 
+26345472, , , , 16, 90, 0.01509813789632612, , , , , , , , , , , , , , , , , , , , , , 
+26607616, , , , 10, 100, 0.016775708773695688, , , , , , , , , , , , , , , , , , , , , , 
+26869760, , , , 34, 134, 0.022479449756752222, , , , , , , , , , , , , , , , , , , , , , 
+27131904, , , , 38, 172, 0.028854219090756583, , , , , , , , , , , , , , , , , , , , , , 
+27394048, , , , 49, 221, 0.037074316389867475, , , , , , , , , , , , , , , , , , , , , , 
+27656192, , , , 57, 278, 0.04663647039087401, , , , , , , , , , , , , , , , , , , , , , 
+27918336, , , , 90, 368, 0.061734608287200135, , , , , , , , , , , , , , , , , , , , , , 
+28180480, , , , 91, 459, 0.0770005032712632, , , , , , , , , , , , , , , , , , , , , , 
+28442624, , , , 105, 564, 0.09461499748364369, , , , , , , , , , , , , , , , , , , , , , 
+28704768, , , , 149, 713, 0.11961080355645026, , , , , , , , , , , , , , , , , , , , , , 
+28966912, , , , 152, 865, 0.1451098808924677, , , , , , , , , , , , , , , , , , , , , , 
+29229056, , , , 170, 1035, 0.17362858580775037, , , , , , , , , , , , , , , , , , , , , , 
+29491200, , , , 183, 1218, 0.20432813286361348, , , , , , , , , , , , , , , , , , , , , , 
+29753344, , , , 171, 1389, 0.23301459486663312, , , , , , , , , , , , , , , , , , , , , , 
+30015488, , , , 174, 1563, 0.2622043281328636, , , , , , , , , , , , , , , , , , , , , , 
+30277632, , , , 187, 1750, 0.2935749035396745, , , , , , , , , , , , , , , , , , , , , , 
+30539776, , , , 158, 1908, 0.32008052340211374, , , , , , , , , , , , , , , , , , , , , , 
+30801920, , , , 154, 2062, 0.3459151149136051, , , , , , , , , , , , , , , , , , , , , , 
+31064064, , , , 167, 2229, 0.3739305485656769, , , , , , , , , , , , , , , , , , , , , , 
+31326208, , , , 174, 2403, 0.4031202818319074, , , , , , , , , , , , , , , , , , , , , , 
+31588352, , , , 175, 2578, 0.43247777218587485, , , , , , , , , , , , , , , , , , , , , , 
+31850496, , , , 174, 2752, 0.46166750545210533, , , , , , , , , , , , , , , , , , , , , , 
+32112640, , , , 162, 2914, 0.4888441536654924, , , , , , , , , , , , , , , , , , , , , , 
+32374784, , , , 162, 3076, 0.5160208018788793, , , , , , , , , , , , , , , , , , , , , , 
+32636928, , , , 209, 3285, 0.5510820332159033, , , , , , , , , , , , , , , , , , , , , , 
+32899072, , , , 168, 3453, 0.5792652239557121, , , , , , , , , , , , , , , , , , , , , , 
+33161216, , , , 188, 3641, 0.6108035564502601, , , , , , , , , , , , , , , , , , , , , , 
+33423360, , , , 162, 3803, 0.637980204663647, , , , , , , , , , , , , , , , , , , , , , 
+33816576, , , , 324, 4127, 0.692333501090421, , , , , , , , , , , , , , , , , , , , , , 
+34340864, , , , 352, 4479, 0.7513839959738299, , , , , , , , , , , , , , , , , , , , , , 
+34865152, , , , 315, 4794, 0.8042274786109713, , , , , , , , , , , , , , , , , , , , , , 
+35389440, , , , 291, 5085, 0.8530447911424258, , , , , , , , , , , , , , , , , , , , , , 
+35913728, , , , 259, 5344, 0.8964938768662976, , , , , , , , , , , , , , , , , , , , , , 
+36438016, , , , 157, 5501, 0.9228317396409998, , , , , , , , , , , , , , , , , , , , , , 
+36962304, , , , 98, 5599, 0.9392719342392216, , , , , , , , , , , , , , , , , , , , , , 
+37486592, , , , 75, 5674, 0.9518537158194934, , , , , , , , , , , , , , , , , , , , , , 
+38010880, , , , 26, 5700, 0.9562154001006542, , , , , , , , , , , , , , , , , , , , , , 
+38535168, , , , 22, 5722, 0.9599060560308673, , , , , , , , , , , , , , , , , , , , , , 
+39059456, , , , 25, 5747, 0.9640999832242912, , , , , , , , , , , , , , , , , , , , , , 
+39583744, , , , 17, 5764, 0.9669518537158195, , , , , , , , , , , , , , , , , , , , , , 
+40108032, , , , 26, 5790, 0.9713135379969804, , , , , , , , , , , , , , , , , , , , , , 
+40632320, , , , 23, 5813, 0.9751719510149304, , , , , , , , , , , , , , , , , , , , , , 
+41156608, , , , 18, 5831, 0.9781915785941956, , , , , , , , , , , , , , , , , , , , , , 
+41680896, , , , 21, 5852, 0.9817144774366717, , , , , , , , , , , , , , , , , , , , , , 
+42205184, , , , 22, 5874, 0.9854051333668847, , , , , , , , , , , , , , , , , , , , , , 
+42729472, , , , 15, 5889, 0.9879214896829391, , , , , , , , , , , , , , , , , , , , , , 
+43253760, , , , 18, 5907, 0.9909411172622044, , , , , , , , , , , , , , , , , , , , , , 
+43778048, , , , 25, 5932, 0.9951350444556283, , , , , , , , , , , , , , , , , , , , , , 
+44302336, , , , 15, 5947, 0.9976514007716826, , , , , , , , , , , , , , , , , , , , , , 
+44826624, , , , 8, 5955, 0.9989934574735783, , , , , , , , , , , , , , , , , , , , , , 
+45350912, , , , 3, 5958, 0.9994967287367891, , , , , , , , , , , , , , , , , , , , , , 
+45875200, , , , 3, 5961, 1.0, , , , , , , , , , , , , , , , , , , , , , 

data/samples/scan_latency_job1.csv

@@ -0,0 +1,68 @@
+nsec, read_slat_ns_count, read_slat_ns_cumulative, read_slat_ns_percentile, read_clat_ns_count, read_clat_ns_cumulative, read_clat_ns_percentile, read_lat_ns_count, read_lat_ns_cumulative, read_lat_ns_percentile, write_slat_ns_count, write_slat_ns_cumulative, write_slat_ns_percentile, write_clat_ns_count, write_clat_ns_cumulative, write_clat_ns_percentile, write_lat_ns_count, write_lat_ns_cumulative, write_lat_ns_percentile, trim_slat_ns_count, trim_slat_ns_cumulative, trim_slat_ns_percentile, trim_clat_ns_count, trim_clat_ns_cumulative, trim_clat_ns_percentile, trim_lat_ns_count, trim_lat_ns_cumulative, trim_lat_ns_percentile, 
+22151168, , , , 3, 3, 0.00025161452654533256, , , , , , , , , , , , , , , , , , , , , , 
+22413312, , , , 4, 7, 0.0005871005619391093, , , , , , , , , , , , , , , , , , , , , , 
+22675456, , , , 8, 15, 0.0012580726327266628, , , , , , , , , , , , , , , , , , , , , , 
+22937600, , , , 5, 20, 0.0016774301769688837, , , , , , , , , , , , , , , , , , , , , , 
+23461888, , , , 2, 22, 0.001845173194665772, , , , , , , , , , , , , , , , , , , , , , 
+23724032, , , , 5, 27, 0.002264530738907993, , , , , , , , , , , , , , , , , , , , , , 
+23986176, , , , 7, 34, 0.0028516313008471023, , , , , , , , , , , , , , , , , , , , , , 
+25034752, , , , 3, 37, 0.0031032458273924346, , , , , , , , , , , , , , , , , , , , , , 
+25296896, , , , 1, 38, 0.003187117336240879, , , , , , , , , , , , , , , , , , , , , , 
+25559040, , , , 4, 42, 0.003522603371634656, , , , , , , , , , , , , , , , , , , , , , 
+25821184, , , , 2, 44, 0.003690346389331544, , , , , , , , , , , , , , , , , , , , , , 
+26083328, , , , 10, 54, 0.004529061477815986, , , , , , , , , , , , , , , , , , , , , , 
+26345472, , , , 15, 69, 0.005787134110542649, , , , , , , , , , , , , , , , , , , , , , 
+26607616, , , , 22, 91, 0.007632307305208421, , , , , , , , , , , , , , , , , , , , , , 
+26869760, , , , 19, 110, 0.00922586597332886, , , , , , , , , , , , , , , , , , , , , , 
+27131904, , , , 35, 145, 0.012161368783024406, , , , , , , , , , , , , , , , , , , , , , 
+27394048, , , , 60, 205, 0.017193659313931058, , , , , , , , , , , , , , , , , , , , , , 
+27656192, , , , 53, 258, 0.0216388492828986, , , , , , , , , , , , , , , , , , , , , , 
+27918336, , , , 78, 336, 0.028180826973077246, , , , , , , , , , , , , , , , , , , , , , 
+28180480, , , , 90, 426, 0.03572926276943722, , , , , , , , , , , , , , , , , , , , , , 
+28442624, , , , 128, 554, 0.046464815902038076, , , , , , , , , , , , , , , , , , , , , , 
+28704768, , , , 174, 728, 0.061058458441667365, , , , , , , , , , , , , , , , , , , , , , 
+28966912, , , , 209, 937, 0.0785876037909922, , , , , , , , , , , , , , , , , , , , , , 
+29229056, , , , 222, 1159, 0.09720707875534682, , , , , , , , , , , , , , , , , , , , , , 
+29491200, , , , 250, 1409, 0.11817495596745785, , , , , , , , , , , , , , , , , , , , , , 
+29753344, , , , 310, 1719, 0.14417512371047556, , , , , , , , , , , , , , , , , , , , , , 
+30015488, , , , 289, 2008, 0.1684139897676759, , , , , , , , , , , , , , , , , , , , , , 
+30277632, , , , 325, 2333, 0.19567223014342028, , , , , , , , , , , , , , , , , , , , , , 
+30539776, , , , 341, 2674, 0.22427241466073974, , , , , , , , , , , , , , , , , , , , , , 
+30801920, , , , 338, 3012, 0.2526209846515139, , , , , , , , , , , , , , , , , , , , , , 
+31064064, , , , 352, 3364, 0.28214375576616624, , , , , , , , , , , , , , , , , , , , , , 
+31326208, , , , 368, 3732, 0.3130084710223937, , , , , , , , , , , , , , , , , , , , , , 
+31588352, , , , 310, 4042, 0.3390086387654114, , , , , , , , , , , , , , , , , , , , , , 
+31850496, , , , 314, 4356, 0.3653442925438229, , , , , , , , , , , , , , , , , , , , , , 
+32112640, , , , 370, 4726, 0.3963767508177472, , , , , , , , , , , , , , , , , , , , , , 
+32374784, , , , 377, 5103, 0.4279963096536107, , , , , , , , , , , , , , , , , , , , , , 
+32636928, , , , 346, 5449, 0.45701585171517234, , , , , , , , , , , , , , , , , , , , , , 
+32899072, , , , 349, 5798, 0.48628700830327937, , , , , , , , , , , , , , , , , , , , , , 
+33161216, , , , 334, 6132, 0.5143000922586597, , , , , , , , , , , , , , , , , , , , , , 
+33423360, , , , 313, 6445, 0.5405518745282227, , , , , , , , , , , , , , , , , , , , , , 
+33816576, , , , 740, 7185, 0.6026167910760715, , , , , , , , , , , , , , , , , , , , , , 
+34340864, , , , 724, 7909, 0.663339763482345, , , , , , , , , , , , , , , , , , , , , , 
+34865152, , , , 653, 8562, 0.7181078587603791, , , , , , , , , , , , , , , , , , , , , , 
+35389440, , , , 666, 9228, 0.7739662836534429, , , , , , , , , , , , , , , , , , , , , , 
+35913728, , , , 584, 9812, 0.8229472448209343, , , , , , , , , , , , , , , , , , , , , , 
+36438016, , , , 499, 10311, 0.864799127736308, , , , , , , , , , , , , , , , , , , , , , 
+36962304, , , , 399, 10710, 0.8982638597668372, , , , , , , , , , , , , , , , , , , , , , 
+37486592, , , , 298, 11008, 0.9232575694036735, , , , , , , , , , , , , , , , , , , , , , 
+38010880, , , , 192, 11200, 0.9393608991025748, , , , , , , , , , , , , , , , , , , , , , 
+38535168, , , , 108, 11308, 0.9484190220582068, , , , , , , , , , , , , , , , , , , , , , 
+39059456, , , , 71, 11379, 0.9543738991864463, , , , , , , , , , , , , , , , , , , , , , 
+39583744, , , , 57, 11436, 0.9591545751908077, , , , , , , , , , , , , , , , , , , , , , 
+40108032, , , , 47, 11483, 0.9630965361066846, , , , , , , , , , , , , , , , , , , , , , 
+40632320, , , , 46, 11529, 0.966954625513713, , , , , , , , , , , , , , , , , , , , , , 
+41156608, , , , 42, 11571, 0.9704772288853476, , , , , , , , , , , , , , , , , , , , , , 
+41680896, , , , 38, 11609, 0.9736643462215885, , , , , , , , , , , , , , , , , , , , , , 
+42205184, , , , 38, 11647, 0.9768514635578294, , , , , , , , , , , , , , , , , , , , , , 
+42729472, , , , 47, 11694, 0.9807934244737063, , , , , , , , , , , , , , , , , , , , , , 
+43253760, , , , 37, 11731, 0.9838966703010987, , , , , , , , , , , , , , , , , , , , , , 
+43778048, , , , 51, 11782, 0.9881741172523694, , , , , , , , , , , , , , , , , , , , , , 
+44302336, , , , 40, 11822, 0.9915289776063071, , , , , , , , , , , , , , , , , , , , , , 
+44826624, , , , 41, 11863, 0.9949677094690933, , , , , , , , , , , , , , , , , , , , , , 
+45350912, , , , 29, 11892, 0.9973999832256982, , , , , , , , , , , , , , , , , , , , , , 
+45875200, , , , 16, 11908, 0.9987419273672733, , , , , , , , , , , , , , , , , , , , , , 
+46399488, , , , 10, 11918, 0.9995806424557577, , , , , , , , , , , , , , , , , , , , , , 
+46923776, , , , 4, 11922, 0.9999161284911515, , , , , , , , , , , , , , , , , , , , , , 
+73924608, , , , 1, 11923, 1.0, , , , , , , , , , , , , , , , , , , , , , 

pyproject.toml

@@ -0,0 +1,53 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "disk-checker"
+version = "0.1.0"
+description = "Disk benchmarking and latency visualization tool"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "pandas>=2.0",
+    "numpy>=1.24",
+    "matplotlib>=3.7",
+    "fastapi>=0.100",
+    "uvicorn[standard]>=0.23",
+    "python-multipart>=0.0.6",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0",
+    "pytest-asyncio>=0.21",
+    "pytest-cov>=4.0",
+    "black>=23.0",
+    "ruff>=0.1.0",
+    "mypy>=1.0",
+]
+
+[project.scripts]
+disk-checker = "disk_checker.scripts.cli:main"
+disk-checker-serve = "disk_checker.scripts.serve:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/disk_checker"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_functions = ["test_*"]
+
+[tool.black]
+line-length = 100
+target-version = ["py310"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.mypy]
+python_version = "3.10"
+warn_return_any = true
+warn_unused_configs = true

scripts/cli.py

@@ -0,0 +1,97 @@
+#!/usr/bin/env python3
+"""
+CLI entry point for disk-checker.
+
+Usage:
+    python -m disk_checker scan_latency.csv
+    disk-checker scan_latency.csv --metric read_clat --unit ms
+"""
+
+import argparse
+import sys
+from pathlib import Path
+
+from disk_checker.core.extractor import load_latency_csv
+from disk_checker.core.helpers import percentile_table
+from disk_checker.plotting.plots import generate_plot
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Plot fio json+ wide-format latency CSV."
+    )
+    parser.add_argument("csv", help="CSV from fio_jsonplus_clat2csv")
+    parser.add_argument("--metric", default=None,
+                       help="Metric to plot (e.g. read_clat). "
+                            "If omitted, the metric with the most I/Os is used.")
+    parser.add_argument("--all-metrics", action="store_true",
+                       help="Plot every metric that has data")
+    parser.add_argument("--unit", choices=["ns", "us", "ms", "s"], default="us",
+                       help="X-axis latency unit (default: us)")
+    parser.add_argument("--log-y", action="store_true")
+    parser.add_argument("--log-x", action="store_true")
+    parser.add_argument("--cdf", action="store_true",
+                       help="Add a CDF subplot below the histogram")
+    parser.add_argument("--cdf-only", action="store_true")
+    parser.add_argument("--normalize", action="store_true",
+                       help="Normalize histogram to a probability density")
+    parser.add_argument("--percentiles", default="50,90,99,99.9,99.99")
+    parser.add_argument("--no-percentiles", action="store_true")
+    parser.add_argument("--output", "-o", default=None)
+    parser.add_argument("--dpi", type=int, default=150)
+    parser.add_argument("--title", default="")
+    parser.add_argument("--show", action="store_true")
+    args = parser.parse_args()
+
+    if not Path(args.csv).is_file():
+        sys.exit(f"error: file not found: {args.csv}")
+
+    df = load_latency_csv(args.csv)
+    if df.empty:
+        sys.exit("error: no latency data in CSV")
+
+    available = sorted(df["metric"].unique())
+    print("Metrics with data:", ", ".join(available))
+
+    if args.all_metrics:
+        metrics = available
+    elif args.metric:
+        if args.metric not in available:
+            sys.exit(f"error: metric {args.metric!r} not in {available}")
+        metrics = [args.metric]
+    else:
+        totals = df.groupby("metric")["count"].sum().sort_values(ascending=False)
+        metrics = [totals.index[0]]
+        print(f"Auto-selected metric: {metrics[0]}")
+
+    output = args.output or f"{Path(args.csv).stem}_latency.png"
+    generate_plot(
+        df=df,
+        metrics=metrics,
+        output_path=Path(output),
+        unit=args.unit,
+        log_y=args.log_y,
+        log_x=args.log_x,
+        normalize=args.normalize,
+        show_cdf=args.cdf,
+        cdf_only=args.cdf_only,
+        title=args.title,
+        dpi=args.dpi,
+    )
+    print(f"Saved plot to {output}")
+
+    if not args.no_percentiles:
+        try:
+            pcts = [float(x) for x in args.percentiles.split(",") if x.strip()]
+        except ValueError:
+            sys.exit("error: --percentiles must be comma-separated numbers")
+        for m in metrics:
+            print(percentile_table(df, m, args.unit, pcts))
+
+    if args.show:
+        import matplotlib.pyplot as plt
+        plt.show()
+
+
+if __name__ == "__main__":
+    main()

scripts/serve.py

@@ -0,0 +1,32 @@
+"""Startup script for the web server."""
+
+import argparse
+import uvicorn
+from pathlib import Path
+
+
+def main():
+    """Main entry point for the web server."""
+    parser = argparse.ArgumentParser(description="Start Disk Checker API server")
+    parser.add_argument("--host", default="127.0.0.1", help="Host to bind to")
+    parser.add_argument("--port", type=int, default=8000, help="Port to bind to")
+    parser.add_argument("--workers", type=int, default=1, help="Number of workers")
+    parser.add_argument("--reload", action="store_true", help="Enable auto-reload")
+    parser.add_argument("--work-dir", type=Path, default=Path("."), help="Work directory")
+    args = parser.parse_args()
+
+    # Set work directory in environment
+    import os
+    os.environ["DISK_CHECKER_WORK_DIR"] = str(args.work_dir)
+
+    uvicorn.run(
+        "disk_checker.web.server:app",
+        host=args.host,
+        port=args.port,
+        workers=args.workers,
+        reload=args.reload,
+    )
+
+
+if __name__ == "__main__":
+    main()

src/disk_checker/__init__.py

@@ -0,0 +1,3 @@
+"""Disk Checker - Disk benchmarking and latency visualization tool."""
+
+__version__ = "0.1.0"

src/disk_checker/__main__.py

@@ -0,0 +1,6 @@
+"""Allow running disk-checker as a module: python -m disk_checker"""
+
+from disk_checker.scripts.cli import main
+
+if __name__ == "__main__":
+    main()

src/disk_checker/core/__init__.py

@@ -0,0 +1,14 @@
+"""Core business logic module."""
+
+from .extractor import load_latency_csv
+from .converter import to_unit, UNIT_FACTORS, UNIT_LABELS
+from .helpers import human_count, percentile_table
+
+__all__ = [
+    "load_latency_csv",
+    "to_unit",
+    "UNIT_FACTORS",
+    "UNIT_LABELS",
+    "human_count",
+    "percentile_table",
+]

src/disk_checker/core/converter.py

@@ -0,0 +1,32 @@
+"""Unit conversion utilities for latency data."""
+
+from typing import Dict
+import numpy as np
+
+UNIT_FACTORS: Dict[str, float] = {
+    "ns": 1.0,
+    "us": 1e3,
+    "ms": 1e6,
+    "s": 1e9,
+}
+
+UNIT_LABELS: Dict[str, str] = {
+    "ns": "ns",
+    "us": "µs",
+    "ms": "ms",
+    "s": "s",
+}
+
+
+def to_unit(values_ns, unit: str) -> np.ndarray:
+    """
+    Convert nanosecond values to the specified unit.
+
+    Args:
+        values_ns: Values in nanoseconds
+        unit: Target unit (ns, us, ms, s)
+
+    Returns:
+        Converted values as numpy array
+    """
+    return np.asarray(values_ns, dtype=float) / UNIT_FACTORS[unit]

src/disk_checker/core/extractor.py

@@ -0,0 +1,88 @@
+"""CSV data extraction module for fio latency data."""
+
+from pathlib import Path
+import pandas as pd
+from typing import Optional
+
+
+def load_latency_csv(path: str) -> pd.DataFrame:
+    """
+    Parse wide-format fio JSON+ CSV into long-format DataFrame.
+
+    Transforms wide-format columns (e.g., read_clat_ns_count) into rows with
+    a metric identifier, making it easier to group and analyze by operation type.
+
+    Args:
+        path: Path to CSV file generated by fio_jsonplus_clat2csv
+
+    Returns:
+        DataFrame with columns: metric, latency_ns, count, cumulative, percentile
+
+    Raises:
+        ValueError: If CSV format is invalid or contains no valid data
+    """
+    df = pd.read_csv(path, skipinitialspace=True)
+    df.columns = [str(c).strip() for c in df.columns]
+
+    # Drop trailing unnamed / empty columns
+    df = df.loc[:, ~df.columns.str.match(r"^Unnamed")]
+    df = df.loc[:, df.columns != ""]
+
+    nsec_col = df.columns[0]
+    if "nsec" not in nsec_col.lower():
+        raise ValueError(
+            f"expected first column to be 'nsec', got {nsec_col!r}"
+        )
+
+    # Coerce the nsec column to numeric
+    df[nsec_col] = pd.to_numeric(df[nsec_col], errors="coerce")
+    df = df.dropna(subset=[nsec_col])
+
+    # Discover metric triples: <metric>_count / _cumulative / _percentile
+    metrics = {}
+    for col in df.columns:
+        if col == nsec_col:
+            continue
+        for suffix in ("_count", "_cumulative", "_percentile"):
+            if col.endswith(suffix):
+                base = col[: -len(suffix)]
+                metrics.setdefault(base, {})[suffix[1:]] = col
+
+    if not metrics:
+        raise ValueError("no *_count columns found in CSV")
+
+    frames = []
+    for base, cols in metrics.items():
+        count_col = cols["count"]
+
+        # Coerce count to numeric
+        counts = pd.to_numeric(df[count_col], errors="coerce")
+
+        # Keep only rows where the count column actually has a number
+        mask = counts.notna()
+        if not mask.any():
+            continue
+
+        sub = pd.DataFrame({
+            "latency_ns": df.loc[mask, nsec_col].values,
+            "count": counts[mask].astype(int).values,
+        })
+        if "cumulative" in cols:
+            sub["cumulative"] = pd.to_numeric(
+                df.loc[mask, cols["cumulative"]], errors="coerce"
+            ).values
+        if "percentile" in cols:
+            sub["percentile"] = pd.to_numeric(
+                df.loc[mask, cols["percentile"]], errors="coerce"
+            ).values
+
+        # read_clat_ns -> read_clat
+        sub["metric"] = base.replace("_ns", "")
+        frames.append(sub)
+
+    if not frames:
+        raise ValueError("no metric had any numeric count data")
+
+    out = pd.concat(frames, ignore_index=True)
+    out = out[out["count"] > 0].reset_index(drop=True)
+    return out

src/disk_checker/core/helpers.py

@@ -0,0 +1,62 @@
+"""Helper functions for formatting and display."""
+
+from typing import List
+import numpy as np
+import pandas as pd
+from matplotlib.ticker import FuncFormatter
+
+from .converter import to_unit, UNIT_LABELS
+
+
+def human_count(x, _pos=None) -> str:
+    """
+    Format large numbers with K/M/G suffixes for axis labels.
+
+    Args:
+        x: Numeric value to format
+        _pos: Matplotlib tick position (unused)
+
+    Returns:
+        Formatted string (e.g., "1.5M", "3.2G")
+    """
+    if x >= 1e9:
+        return f"{x/1e9:.1f}G"
+    if x >= 1e6:
+        return f"{x/1e6:.1f}M"
+    if x >= 1e3:
+        return f"{x/1e3:.0f}k"
+    return f"{x:.0f}"
+
+
+def percentile_table(df: pd.DataFrame, metric: str, unit: str, pcts: List[float]) -> str:
+    """
+    Generate a formatted table showing latency values at specified percentiles.
+
+    Args:
+        df: Long-format DataFrame from load_latency_csv
+        metric: Metric name (e.g., 'read_clat')
+        unit: Display unit (ns, us, ms, s)
+        pcts: List of percentile values (e.g., [50, 90, 99])
+
+    Returns:
+        Formatted string table
+    """
+    g = df[df["metric"] == metric].sort_values("latency_ns")
+    if g.empty:
+        return f"(no data for metric {metric})"
+
+    counts = g["count"].values.astype(float)
+    total = int(counts.sum())
+    cdf = np.cumsum(counts) / total * 100.0
+    lat = to_unit(g["latency_ns"].values, unit)
+
+    lines = [
+        f"\nMetric: {metric}   (total I/Os: {total:,})",
+        f"  {'percentile':>12}  {'latency':>14}",
+    ]
+
+    for p in pcts:
+        idx = min(np.searchsorted(cdf, p), len(lat) - 1)
+        lines.append(f"  {p:>11.2f}%  {lat[idx]:>12.3f} {UNIT_LABELS[unit]}")
+
+    return "\n".join(lines)

src/disk_checker/core/orchestrator.py

@@ -0,0 +1,164 @@
+"""Tool orchestration module for running disk benchmarks."""
+
+import asyncio
+import subprocess
+from dataclasses import dataclass, field
+from enum import Enum
+from pathlib import Path
+from typing import Dict, Optional
+
+
+class ToolStatus(Enum):
+    """Status of a benchmark job."""
+    PENDING = "pending"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"
+
+
+@dataclass
+class JobResult:
+    """Result of a benchmark job."""
+    job_id: str
+    status: ToolStatus
+    output_path: Optional[Path] = None
+    error: Optional[str] = None
+    metadata: Dict = field(default_factory=dict)
+
+
+class Orchestrator:
+    """
+    Orchestrates disk benchmarking tools (fio, badblocks, etc.)
+
+    Provides async interfaces for running benchmarks and collecting results.
+    """
+
+    def __init__(self, work_dir: Path = Path(".")):
+        self.work_dir = work_dir
+        self._jobs: Dict[str, JobResult] = {}
+
+    async def run_fio(
+        self,
+        device: str,
+        job_file: Optional[Path] = None,
+        output_format: str = "jsonplus",
+        **kwargs,
+    ) -> Path:
+        """
+        Run fio benchmark and return path to output file.
+
+        Args:
+            device: Block device path (e.g., '/dev/sda')
+            job_file: Optional fio job file
+            output_format: Output format (json, jsonplus, csv)
+            **kwargs: Additional fio options
+
+        Returns:
+            Path to output file
+
+        Raises:
+            subprocess.CalledProcessError: If fio command fails
+        """
+        job_id = f"fio_{asyncio.get_event_loop().time()}"
+        output_path = self.work_dir / f"{job_id}.{output_format}"
+
+        cmd = ["fio", "--output-format=jsonplus"]
+        if job_file:
+            cmd.extend(["--filename", str(device)])
+        else:
+            cmd.extend(["--name=test", "--rw=randread", "--bs=4k"])
+
+        cmd.extend(["--output", str(output_path)])
+        cmd.extend([f"--output-format={output_format}"])
+
+        for k, v in kwargs.items():
+            cmd.extend([f"--{k}={v}"])
+
+        self._jobs[job_id] = JobResult(
+            job_id=job_id,
+            status=ToolStatus.RUNNING,
+            output_path=output_path,
+        )
+
+        try:
+            await asyncio.create_subprocess_exec(
+                *cmd,
+                stdout=asyncio.subprocess.PIPE,
+                stderr=asyncio.subprocess.PIPE,
+            )
+            self._jobs[job_id] = JobResult(
+                job_id=job_id,
+                status=ToolStatus.COMPLETED,
+                output_path=output_path,
+            )
+            return output_path
+        except subprocess.CalledProcessError as e:
+            self._jobs[job_id] = JobResult(
+                job_id=job_id,
+                status=ToolStatus.FAILED,
+                error=str(e),
+            )
+            raise
+
+    async def run_badblocks(
+        self,
+        device: str,
+        blocks_count: Optional[int] = None,
+        **kwargs,
+    ) -> Path:
+        """
+        Run badblocks scan on device.
+
+        Args:
+            device: Block device path
+            blocks_count: Number of blocks to scan
+            **kwargs: Additional badblocks options
+
+        Returns:
+            Path to badblocks output file
+        """
+        job_id = f"badblocks_{asyncio.get_event_loop().time()}"
+        output_path = self.work_dir / f"{job_id}.txt"
+
+        cmd = ["badblocks", "-w", "-s", "-p", "0", "-t", "RANDOM", "-o"]
+        cmd.extend([str(output_path), str(device)])
+
+        if blocks_count:
+            cmd.extend(["-b", str(blocks_count)])
+
+        for k, v in kwargs.items():
+            cmd.extend([f"-{k}", str(v)])
+
+        self._jobs[job_id] = JobResult(
+            job_id=job_id,
+            status=ToolStatus.RUNNING,
+            output_path=output_path,
+        )
+
+        try:
+            await asyncio.create_subprocess_exec(
+                *cmd,
+                stdout=asyncio.subprocess.PIPE,
+                stderr=asyncio.subprocess.PIPE,
+            )
+            self._jobs[job_id] = JobResult(
+                job_id=job_id,
+                status=ToolStatus.COMPLETED,
+                output_path=output_path,
+            )
+            return output_path
+        except subprocess.CalledProcessError as e:
+            self._jobs[job_id] = JobResult(
+                job_id=job_id,
+                status=ToolStatus.FAILED,
+                error=str(e),
+            )
+            raise
+
+    def get_job_status(self, job_id: str) -> Optional[JobResult]:
+        """Get status of a submitted job."""
+        return self._jobs.get(job_id)
+
+    def list_jobs(self) -> Dict[str, JobResult]:
+        """List all jobs."""
+        return self._jobs.copy()

src/disk_checker/plotting/__init__.py

@@ -0,0 +1,5 @@
+"""Plotting module for disk latency visualization."""
+
+from .plots import draw_histogram, draw_cdf, generate_plot
+
+__all__ = ["draw_histogram", "draw_cdf", "generate_plot"]

src/disk_checker/plotting/plots.py

@@ -0,0 +1,162 @@
+"""Plotting module for disk latency visualization."""
+
+import matplotlib
+matplotlib.use("Agg")  # Non-interactive backend for server environments
+import matplotlib.pyplot as plt
+from matplotlib.ticker import FuncFormatter
+import numpy as np
+from pathlib import Path
+from typing import List, Optional
+
+from disk_checker.core.converter import to_unit, UNIT_LABELS
+from disk_checker.core.helpers import human_count
+
+
+def draw_histogram(
+    ax,
+    df,
+    metrics: List[str],
+    unit: str = "us",
+    log_y: bool = False,
+    log_x: bool = False,
+    normalize: bool = False,
+) -> None:
+    """
+    Draw a histogram showing the distribution of latencies for each metric.
+
+    Uses a step plot (where="post") to show the discrete nature of the data.
+    If normalize=True, Y-axis shows probability density instead of counts.
+
+    Args:
+        ax: Matplotlib axis object
+        df: Long-format DataFrame from load_latency_csv
+        metrics: List of metric names to plot
+        unit: X-axis unit (ns, us, ms, s)
+        log_y: Use logarithmic Y scale
+        log_x: Use logarithmic X scale
+        normalize: Normalize to probability density
+    """
+    for metric in metrics:
+        g = df[df["metric"] == metric].sort_values("latency_ns")
+        if g.empty:
+            continue
+
+        x = to_unit(g["latency_ns"].values, unit)
+        y = g["count"].values.astype(float)
+
+        if normalize:
+            s = y.sum()
+            if s > 0:
+                y = y / s
+
+        ax.step(x, y, where="post", lw=1.4, label=metric)
+        ax.fill_between(x, y, step="post", alpha=0.25)
+
+    ax.set_xlabel(f"Latency ({UNIT_LABELS[unit]})")
+    ax.set_ylabel("Probability" if normalize else "Number of I/Os")
+    ax.set_title("Completion latency distribution")
+    ax.grid(True, which="both", ls=":", alpha=0.5)
+
+    if not normalize:
+        ax.yaxis.set_major_formatter(FuncFormatter(human_count))
+    if log_y:
+        ax.set_yscale("log")
+    if log_x:
+        ax.set_xscale("log")
+    if len(metrics) > 1:
+        ax.legend(title="metric", fontsize=9)
+
+
+def draw_cdf(ax, df, metrics: List[str], unit: str = "us", log_x: bool = False) -> None:
+    """
+    Draw a Cumulative Distribution Function (CDF).
+
+    Shows the percentage of I/Os completed within each latency threshold.
+    Each metric gets its own line; Y-axis ranges from 0% to 100%.
+
+    Args:
+        ax: Matplotlib axis object
+        df: Long-format DataFrame
+        metrics: List of metric names
+        unit: X-axis unit
+        log_x: Use logarithmic X scale
+    """
+    for metric in metrics:
+        g = df[df["metric"] == metric].sort_values("latency_ns")
+        if g.empty:
+            continue
+
+        x = to_unit(g["latency_ns"].values, unit)
+        counts = g["count"].values.astype(float)
+        total = counts.sum()
+        if total <= 0:
+            continue
+
+        cdf = np.cumsum(counts) / total * 100.0
+        ax.plot(x, cdf, lw=1.6, label=f"{metric} (n={int(total):,})")
+
+    ax.set_xlabel(f"Latency ({UNIT_LABELS[unit]})")
+    ax.set_ylabel("Cumulative % of I/Os")
+    ax.set_title("Cumulative latency distribution")
+    ax.set_ylim(0, 100)
+    ax.grid(True, which="both", ls=":", alpha=0.5)
+    ax.yaxis.set_major_formatter(FuncFormatter(lambda v, _: f"{v:.0f}%"))
+
+    if log_x:
+        ax.set_xscale("log")
+    ax.legend(fontsize=9)
+
+
+def generate_plot(
+    df,
+    metrics: List[str],
+    output_path: Path,
+    unit: str = "us",
+    log_y: bool = False,
+    log_x: bool = False,
+    normalize: bool = False,
+    show_cdf: bool = False,
+    cdf_only: bool = False,
+    title: str = "",
+    dpi: int = 150,
+) -> Path:
+    """
+    Generate a complete plot with histogram and/or CDF.
+
+    Creates the appropriate subplot layout based on the options provided.
+
+    Args:
+        df: Long-format DataFrame
+        metrics: Metrics to plot
+        output_path: Where to save the plot
+        unit: X-axis unit
+        log_y: Logarithmic Y scale
+        log_x: Logarithmic X scale
+        normalize: Normalize histogram
+        show_cdf: Show CDF below histogram
+        cdf_only: Show only CDF
+        title: Plot title
+        dpi: Output resolution
+
+    Returns:
+        Path to saved plot
+    """
+    if cdf_only:
+        fig, ax = plt.subplots(figsize=(11, 6))
+        draw_cdf(ax, df, metrics, unit, log_x)
+    elif show_cdf:
+        fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(11, 10))
+        draw_histogram(
+            ax1, df, metrics, unit, log_y, log_x, normalize
+        )
+        draw_cdf(ax2, df, metrics, unit, log_x)
+    else:
+        fig, ax = plt.subplots(figsize=(11, 6))
+        draw_histogram(ax, df, metrics, unit, log_y, log_x, normalize)
+
+    if title:
+        fig.suptitle(title, fontsize=13, y=0.995)
+    fig.tight_layout()
+    fig.savefig(output_path, dpi=dpi, bbox_inches="tight")
+    plt.close(fig)
+    return output_path

src/disk_checker/web/__init__.py

@@ -0,0 +1 @@
+"""Web backend module for disk-checker API."""

src/disk_checker/web/models.py

@@ -0,0 +1,95 @@
+"""Pydantic models for the web API."""
+
+from pydantic import BaseModel, Field
+from typing import List, Optional, Dict, Any
+from enum import Enum
+
+
+class ToolType(str, Enum):
+    """Available benchmarking tools."""
+    FIO = "fio"
+    BADBLOCKS = "badblocks"
+    IO_URING = "io_uring"
+
+
+class JobStatus(str, Enum):
+    """Status of a benchmark job."""
+    PENDING = "pending"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"
+
+
+class MetricInfo(BaseModel):
+    """Information about a metric."""
+    name: str
+    total_ios: int
+    min_latency_ns: Optional[float] = None
+    max_latency_ns: Optional[float] = None
+    avg_latency_ns: Optional[float] = None
+
+
+class PercentileInfo(BaseModel):
+    """Latency value at a specific percentile."""
+    percentile: float
+    latency_ns: float
+    latency_display: str
+
+
+class MetricResult(BaseModel):
+    """Complete result for a metric."""
+    metric: str
+    total_ios: int
+    percentiles: List[PercentileInfo]
+    min_latency_ns: float
+    max_latency_ns: float
+    avg_latency_ns: float
+
+
+class ScanResponse(BaseModel):
+    """Response from CSV scan endpoint."""
+    metrics: List[MetricResult]
+    summary: Dict[str, Any]
+
+
+class BenchmarkRequest(BaseModel):
+    """Request to start a benchmark job."""
+    device: str = Field(..., description="Block device path (e.g., /dev/sda)")
+    tool: ToolType = ToolType.FIO
+    job_file: Optional[str] = None
+    options: Dict[str, Any] = Field(default_factory=dict)
+
+    class Config:
+        json_schema_extra = {
+            "example": {
+                "device": "/dev/sda",
+                "tool": "fio",
+                "options": {
+                    "rw": "randread",
+                    "bs": "4k",
+                    "size": "1G",
+                    "runtime": "60"
+                }
+            }
+        }
+
+
+class JobStatusResponse(BaseModel):
+    """Response with job status."""
+    job_id: str
+    status: JobStatus
+    output_path: Optional[str] = None
+    error: Optional[str] = None
+    created_at: Optional[str] = None
+    completed_at: Optional[str] = None
+
+
+class PlotRequest(BaseModel):
+    """Request to generate a plot."""
+    metric: Optional[str] = None
+    unit: str = Field(default="us", pattern="^(ns|us|ms|s)$")
+    log_x: bool = False
+    log_y: bool = False
+    cdf: bool = False
+    normalize: bool = False
+    title: Optional[str] = None

src/disk_checker/web/routes.py

@@ -0,0 +1,209 @@
+"""API routes for disk-checker web backend."""
+
+import asyncio
+import tempfile
+from pathlib import Path
+from typing import List, Optional
+
+from fastapi import APIRouter, UploadFile, File, HTTPException, Depends, Request
+from fastapi.responses import JSONResponse, FileResponse
+import pandas as pd
+
+from disk_checker.core.extractor import load_latency_csv
+from disk_checker.core.helpers import percentile_table
+from disk_checker.plotting.plots import generate_plot
+from disk_checker.web.models import (
+    ScanResponse,
+    BenchmarkRequest,
+    JobStatusResponse,
+    PlotRequest,
+    MetricInfo,
+    PercentileInfo,
+    MetricResult,
+)
+
+router = APIRouter()
+
+
+def _calculate_metric_results(df: pd.DataFrame, metric: str, pcts: List[float]) -> MetricResult:
+    """Calculate detailed results for a metric."""
+    metric_df = df[df["metric"] == metric]
+    counts = metric_df["count"].values.astype(float)
+    total_ios = int(counts.sum())
+
+    latencies_ns = metric_df["latency_ns"].values
+
+    # Calculate percentiles
+    percentiles = []
+    cdf = __import__('numpy').cumsum(counts) / total_ios * 100.0
+    for p in pcts:
+        idx = min(__import__('numpy').searchsorted(cdf, p), len(latencies_ns) - 1)
+        percentiles.append(PercentileInfo(
+            percentile=p,
+            latency_ns=float(latencies_ns[idx]),
+            latency_display=f"{latencies_ns[idx]:.3f} ns"
+        ))
+
+    return MetricResult(
+        metric=metric,
+        total_ios=total_ios,
+        percentiles=percentiles,
+        min_latency_ns=float(latencies_ns.min()),
+        max_latency_ns=float(latencies_ns.max()),
+        avg_latency_ns=float(latencies_ns.mean()),
+    )
+
+
+@router.post("/scan", response_model=ScanResponse)
+async def scan_csv(file: UploadFile = File(...)):
+    """
+    Upload a fio JSON+ CSV and return analysis.
+    """
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp:
+        content = await file.read()
+        tmp.write(content)
+        tmp_path = tmp.name
+
+    try:
+        df = load_latency_csv(tmp_path)
+        if df.empty:
+            raise HTTPException(status_code=400, detail="No valid data in CSV")
+
+        # Calculate metrics
+        metrics = []
+        pcts = [50, 90, 99, 99.9, 99.99]
+        for metric in sorted(df["metric"].unique()):
+            metrics.append(_calculate_metric_results(df, metric, pcts))
+
+        summary = {
+            "total_metrics": len(metrics),
+            "total_ios": sum(m.total_ios for m in metrics),
+        }
+
+        return ScanResponse(metrics=metrics, summary=summary)
+    finally:
+        Path(tmp_path).unlink(missing_ok=True)
+
+
+@router.post("/plot")
+async def generate_plot_endpoint(
+    file: UploadFile = File(...),
+    metric: Optional[str] = None,
+    unit: str = "us",
+    log_x: bool = False,
+    log_y: bool = False,
+    cdf: bool = False,
+    normalize: bool = False,
+    title: Optional[str] = None,
+):
+    """
+    Generate and return a latency plot.
+    """
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp:
+        content = await file.read()
+        tmp.write(content)
+        tmp_path = tmp.name
+
+    try:
+        df = load_latency_csv(tmp_path)
+        if df.empty:
+            raise HTTPException(status_code=400, detail="No valid data in CSV")
+
+        # Determine metrics
+        available = sorted(df["metric"].unique())
+        if request.metric:
+            if request.metric not in available:
+                raise HTTPException(
+                    status_code=400,
+                    detail=f"Metric {request.metric} not found"
+                )
+            metrics = [request.metric]
+        else:
+            totals = df.groupby("metric")["count"].sum().sort_values(ascending=False)
+            metrics = [totals.index[0]]
+
+        # Generate plot
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as img:
+            output_path = Path(img.name)
+
+        generate_plot(
+            df=df,
+            metrics=metrics,
+            output_path=output_path,
+            unit=unit,
+            log_x=log_x,
+            log_y=log_y,
+            normalize=normalize,
+            show_cdf=cdf,
+            title=title or "",
+        )
+
+        return FileResponse(output_path, media_type="image/png")
+    finally:
+        Path(tmp_path).unlink(missing_ok=True)
+
+
+@router.post("/benchmark", response_model=JobStatusResponse)
+async def start_benchmark(request: BenchmarkRequest):
+    """
+    Start a disk benchmark job.
+    """
+    orchestrator = request.app.state.orchestrator
+
+    job_id = f"bench_{asyncio.get_event_loop().time()}"
+
+    async def run_job():
+        try:
+            if request.tool == "fio":
+                output_path = await orchestrator.run_fio(
+                    device=request.device,
+                    **request.options,
+                )
+            elif request.tool == "badblocks":
+                output_path = await orchestrator.run_badblocks(
+                    device=request.device,
+                    **request.options,
+                )
+            else:
+                raise ValueError(f"Unknown tool: {request.tool}")
+            return {
+                "job_id": job_id,
+                "status": "completed",
+                "output_path": str(output_path),
+            }
+        except Exception as e:
+            return {"job_id": job_id, "status": "failed", "error": str(e)}
+
+    request.app.state.jobs[job_id] = {
+        "status": "running",
+        "task": asyncio.create_task(run_job()),
+    }
+
+    return JobStatusResponse(job_id=job_id, status="running")
+
+
+@router.get("/jobs/{job_id}", response_model=JobStatusResponse)
+async def get_job_status(job_id: str, request: Request):
+    """
+    Check the status of a benchmark job.
+    """
+    jobs = request.app.state.jobs
+    if job_id not in jobs:
+        raise HTTPException(status_code=404, detail="Job not found")
+
+    job = jobs[job_id]
+    task = job["task"]
+
+    if task.done():
+        result = task.result()
+        return JobStatusResponse(**result)
+
+    return JobStatusResponse(job_id=job_id, status="running")
+
+
+@router.get("/jobs", response_model=List[str])
+async def list_jobs(request: Request):
+    """
+    List all benchmark jobs.
+    """
+    return list(request.app.state.jobs.keys())

src/disk_checker/web/server.py

@@ -0,0 +1,49 @@
+"""FastAPI application for disk-checker web API."""
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from contextlib import asynccontextmanager
+import logging
+
+from disk_checker.core.orchestrator import Orchestrator
+
+logger = logging.getLogger(__name__)
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """Application lifespan handler."""
+    # Startup: initialize orchestrator
+    app.state.orchestrator = Orchestrator(work_dir=app.state.work_dir)
+    app.state.jobs = {}
+    logger.info("Disk Checker API started")
+    yield
+    # Shutdown: cleanup
+    logger.info("Disk Checker API stopped")
+
+
+app = FastAPI(
+    title="Disk Checker API",
+    description="API for disk benchmarking and latency visualization",
+    version="0.1.0",
+    lifespan=lifespan,
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint."""
+    return {"status": "ok", "version": "0.1.0"}
+
+
+# Import and include routers
+from disk_checker.web.routes import router as api_router
+app.include_router(api_router, prefix="/api/v1")

tests/__init__.py

@@ -0,0 +1 @@
+"""Tests for disk-checker."""

tests/test_converter.py

@@ -0,0 +1,68 @@
+"""Tests for the unit conversion module."""
+
+import numpy as np
+import pytest
+
+from disk_checker.core.converter import to_unit, UNIT_FACTORS, UNIT_LABELS
+
+
+class TestToUnit:
+    """Tests for to_unit function."""
+
+    def test_nanoseconds_to_microseconds(self):
+        """Test conversion from ns to us."""
+        values = np.array([1000, 2000, 3000])
+        result = to_unit(values, "us")
+        expected = np.array([1.0, 2.0, 3.0])
+        np.testing.assert_array_equal(result, expected)
+
+    def test_nanoseconds_to_milliseconds(self):
+        """Test conversion from ns to ms."""
+        values = np.array([1000000, 2000000])
+        result = to_unit(values, "ms")
+        expected = np.array([1.0, 2.0])
+        np.testing.assert_array_equal(result, expected)
+
+    def test_nanoseconds_to_seconds(self):
+        """Test conversion from ns to s."""
+        values = np.array([1000000000, 2000000000])
+        result = to_unit(values, "s")
+        expected = np.array([1.0, 2.0])
+        np.testing.assert_array_equal(result, expected)
+
+    def test_same_unit_returns_same(self):
+        """Test conversion to same unit."""
+        values = np.array([100, 200, 300])
+        result = to_unit(values, "ns")
+        np.testing.assert_array_equal(result, values)
+
+    def test_empty_array(self):
+        """Test conversion with empty array."""
+        values = np.array([])
+        result = to_unit(values, "us")
+        assert len(result) == 0
+
+    def test_single_value(self):
+        """Test conversion with single value."""
+        result = to_unit(1000, "us")
+        assert result == 1.0
+
+
+class TestConstants:
+    """Tests for module constants."""
+
+    def test_unit_factors(self):
+        """Test UNIT_FACTORS contains all expected units."""
+        assert set(UNIT_FACTORS.keys()) == {"ns", "us", "ms", "s"}
+        assert UNIT_FACTORS["ns"] == 1.0
+        assert UNIT_FACTORS["us"] == 1e3
+        assert UNIT_FACTORS["ms"] == 1e6
+        assert UNIT_FACTORS["s"] == 1e9
+
+    def test_unit_labels(self):
+        """Test UNIT_LABELS contains all expected units."""
+        assert set(UNIT_LABELS.keys()) == {"ns", "us", "ms", "s"}
+        assert UNIT_LABELS["ns"] == "ns"
+        assert UNIT_LABELS["us"] == "µs"
+        assert UNIT_LABELS["ms"] == "ms"
+        assert UNIT_LABELS["s"] == "s"

tests/test_extractor.py

@@ -0,0 +1,72 @@
+"""Tests for the data extraction module."""
+
+import pytest
+import pandas as pd
+from pathlib import Path
+
+from disk_checker.core.extractor import load_latency_csv
+
+
+class TestLoadLatencyCsv:
+    """Tests for load_latency_csv function."""
+
+    def test_load_valid_csv(self, sample_csv_path):
+        """Test loading a valid fio CSV file."""
+        df = load_latency_csv(str(sample_csv_path))
+        assert not df.empty
+        assert "metric" in df.columns
+        assert "latency_ns" in df.columns
+        assert "count" in df.columns
+
+    def test_returns_long_format(self, sample_csv_path):
+        """Test that output is in long format with metric column."""
+        df = load_latency_csv(str(sample_csv_path))
+        metrics = df["metric"].unique()
+        assert "read_clat" in metrics
+
+    def test_empty_csv_raises(self, empty_csv_path):
+        """Test that empty CSV raises ValueError."""
+        with pytest.raises(ValueError):
+            load_latency_csv(str(empty_csv_path))
+
+    def test_invalid_format_raises(self, invalid_csv_path):
+        """Test that invalid CSV format raises ValueError."""
+        with pytest.raises(ValueError):
+            load_latency_csv(str(invalid_csv_path))
+
+    def test_missing_nsec_column_raises(self, tmp_path):
+        """Test that missing nsec column raises ValueError."""
+        csv_content = "col1,col2\n1,2\n"
+        path = tmp_path / "invalid.csv"
+        path.write_text(csv_content)
+        with pytest.raises(ValueError, match="expected first column to be 'nsec'"):
+            load_latency_csv(str(path))
+
+
+@pytest.fixture
+def sample_csv_path(tmp_path):
+    """Create a sample CSV file for testing."""
+    csv_content = """nsec,read_clat_ns_count,read_clat_ns_cumulative,read_clat_ns_percentile
+19791872,1,1,0.00016775708773695687
+22413312,4,5,0.0008387854386847844
+22675456,9,14,0.0023485992283173965
+"""
+    path = tmp_path / "test.csv"
+    path.write_text(csv_content)
+    return path
+
+
+@pytest.fixture
+def empty_csv_path(tmp_path):
+    """Create an empty CSV file for testing."""
+    path = tmp_path / "empty.csv"
+    path.write_text("nsec\n")
+    return path
+
+
+@pytest.fixture
+def invalid_csv_path(tmp_path):
+    """Create an invalid CSV file for testing."""
+    path = tmp_path / "invalid.csv"
+    path.write_text("col1,col2\n1,2\n")
+    return path

tests/test_helpers.py

@@ -0,0 +1,77 @@
+"""Tests for helper functions."""
+
+import pandas as pd
+import pytest
+
+from disk_checker.core.helpers import human_count, percentile_table
+
+
+class TestHumanCount:
+    """Tests for human_count function."""
+
+    def test_small_number(self):
+        """Test formatting of small numbers."""
+        assert human_count(100) == "100"
+        assert human_count(50) == "50"
+
+    def test_thousands(self):
+        """Test formatting of thousands."""
+        assert human_count(1500) == "2k"
+        assert human_count(2500) == "2k"
+        assert human_count(1000) == "1k"
+        assert human_count(999) == "999"
+
+    def test_millions(self):
+        """Test formatting of millions."""
+        assert human_count(1500000) == "1.5M"
+        assert human_count(2750000) == "2.8M"
+
+    def test_billions(self):
+        """Test formatting of billions."""
+        assert human_count(1500000000) == "1.5G"
+        assert human_count(2750000000) == "2.8G"
+
+    def test_zero(self):
+        """Test formatting of zero."""
+        assert human_count(0) == "0"
+
+    def test_position_argument_ignored(self):
+        """Test that _pos argument is ignored."""
+        assert human_count(1000, 0) == "1k"
+
+
+class TestPercentileTable:
+    """Tests for percentile_table function."""
+
+    def test_basic_percentiles(self):
+        """Test basic percentile table generation."""
+        df = pd.DataFrame({
+            "metric": ["read_clat"] * 3,
+            "latency_ns": [1000, 2000, 3000],
+            "count": [1, 2, 1],
+        })
+        result = percentile_table(df, "read_clat", "us", [50, 90])
+        assert "Metric: read_clat" in result
+        assert "total I/Os: 4" in result
+        assert "percentile" in result
+        assert "latency" in result
+
+    def test_missing_metric(self):
+        """Test percentile table with missing metric."""
+        df = pd.DataFrame({
+            "metric": ["read_clat"],
+            "latency_ns": [1000],
+            "count": [1],
+        })
+        result = percentile_table(df, "write_clat", "us", [50])
+        assert "(no data for metric write_clat)" in result
+
+    def test_unit_display(self):
+        """Test that correct unit is displayed."""
+        df = pd.DataFrame({
+            "metric": ["read_clat"],
+            "latency_ns": [1000000],  # 1ms in ns
+            "count": [1],
+        })
+        result = percentile_table(df, "read_clat", "ms", [50])
+        assert "ms" in result

tests/test_orchestrator.py

@@ -0,0 +1,53 @@
+"""Tests for the orchestrator module."""
+
+import asyncio
+import pytest
+from pathlib import Path
+from unittest.mock import AsyncMock, patch
+
+from disk_checker.core.orchestrator import Orchestrator, ToolStatus, JobResult
+
+
+class TestOrchestrator:
+    """Tests for Orchestrator class."""
+
+    @pytest.fixture
+    def orchestrator(self, tmp_path):
+        """Create an orchestrator instance."""
+        return Orchestrator(work_dir=tmp_path)
+
+    def test_initial_state(self, orchestrator):
+        """Test initial orchestrator state."""
+        assert orchestrator.list_jobs() == {}
+
+    def test_run_fio_creates_job(self, orchestrator, tmp_path):
+        """Test that run_fio creates a job entry."""
+        with patch("asyncio.create_subprocess_exec") as mock_exec:
+            mock_exec.return_value = AsyncMock()
+            result = asyncio.get_event_loop().run_until_complete(
+                orchestrator.run_fio("/dev/sda")
+            )
+
+        jobs = orchestrator.list_jobs()
+        assert len(jobs) == 1
+        job = list(jobs.values())[0]
+        assert job.status == ToolStatus.COMPLETED
+        # Note: output_path may not exist in test environment without actual fio
+
+    def test_get_job_status(self, orchestrator, tmp_path):
+        """Test retrieving job status."""
+        with patch("asyncio.create_subprocess_exec") as mock_exec:
+            mock_exec.return_value = AsyncMock()
+            result = asyncio.get_event_loop().run_until_complete(
+                orchestrator.run_fio("/dev/sda")
+            )
+            job_id = result.job_id
+
+        job = orchestrator.get_job_status(job_id)
+        assert job is not None
+        assert job.status == ToolStatus.COMPLETED
+
+    def test_get_nonexistent_job(self, orchestrator):
+        """Test getting status of non-existent job."""
+        job = orchestrator.get_job_status("nonexistent")
+        assert job is None

tests/test_plots.py

@@ -0,0 +1,134 @@
+"""Tests for the plotting module."""
+
+import pytest
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+
+from disk_checker.plotting.plots import draw_histogram, draw_cdf, generate_plot
+import pandas as pd
+
+
+class TestDrawHistogram:
+    """Tests for draw_histogram function."""
+
+    @pytest.fixture
+    def sample_df(self):
+        """Create a sample DataFrame for testing."""
+        return pd.DataFrame({
+            "metric": ["read_clat", "read_clat", "write_clat"],
+            "latency_ns": [1000, 2000, 1500],
+            "count": [1, 2, 1],
+        })
+
+    def test_draws_histogram(self, sample_df, tmp_path):
+        """Test that histogram is drawn without errors."""
+        fig, ax = plt.subplots()
+        draw_histogram(ax, sample_df, ["read_clat"])
+        assert ax.get_title() == "Completion latency distribution"
+        plt.close(fig)
+
+    def test_multiple_metrics(self, sample_df, tmp_path):
+        """Test drawing multiple metrics."""
+        fig, ax = plt.subplots()
+        draw_histogram(ax, sample_df, ["read_clat", "write_clat"])
+        assert len(ax.collections) > 0
+        plt.close(fig)
+
+    def test_log_scale(self, sample_df, tmp_path):
+        """Test logarithmic scale."""
+        fig, ax = plt.subplots()
+        draw_histogram(ax, sample_df, ["read_clat"], log_x=True, log_y=True)
+        assert ax.get_xscale() == "log"
+        assert ax.get_yscale() == "log"
+        plt.close(fig)
+
+
+class TestDrawCdf:
+    """Tests for draw_cdf function."""
+
+    @pytest.fixture
+    def sample_df(self):
+        """Create a sample DataFrame for testing."""
+        return pd.DataFrame({
+            "metric": ["read_clat", "read_clat"],
+            "latency_ns": [1000, 2000],
+            "count": [1, 3],
+        })
+
+    def test_draws_cdf(self, sample_df, tmp_path):
+        """Test that CDF is drawn without errors."""
+        fig, ax = plt.subplots()
+        draw_cdf(ax, sample_df, ["read_clat"])
+        assert ax.get_title() == "Cumulative latency distribution"
+        assert ax.get_ylim() == (0, 100)
+        plt.close(fig)
+
+    def test_log_scale(self, sample_df, tmp_path):
+        """Test logarithmic X scale."""
+        fig, ax = plt.subplots()
+        draw_cdf(ax, sample_df, ["read_clat"], log_x=True)
+        assert ax.get_xscale() == "log"
+        plt.close(fig)
+
+
+class TestGeneratePlot:
+    """Tests for generate_plot function."""
+
+    @pytest.fixture
+    def sample_df(self):
+        """Create a sample DataFrame for testing."""
+        return pd.DataFrame({
+            "metric": ["read_clat", "read_clat"],
+            "latency_ns": [1000, 2000],
+            "count": [1, 3],
+        })
+
+    def test_generates_histogram(self, sample_df, tmp_path):
+        """Test generating histogram plot."""
+        output = tmp_path / "test.png"
+        result = generate_plot(
+            df=sample_df,
+            metrics=["read_clat"],
+            output_path=output,
+        )
+        assert result == output
+        assert output.exists()
+
+    def test_generates_cdf_only(self, sample_df, tmp_path):
+        """Test generating CDF-only plot."""
+        output = tmp_path / "test_cdf.png"
+        result = generate_plot(
+            df=sample_df,
+            metrics=["read_clat"],
+            output_path=output,
+            cdf_only=True,
+        )
+        assert result == output
+        assert output.exists()
+
+    def test_generates_histogram_with_cdf(self, sample_df, tmp_path):
+        """Test generating histogram with CDF below."""
+        output = tmp_path / "test_both.png"
+        result = generate_plot(
+            df=sample_df,
+            metrics=["read_clat"],
+            output_path=output,
+            show_cdf=True,
+        )
+        assert result == output
+        assert output.exists()
+
+    def test_custom_dpi(self, sample_df, tmp_path):
+        """Test custom DPI setting."""
+        output = tmp_path / "test_dpi.png"
+        result = generate_plot(
+            df=sample_df,
+            metrics=["read_clat"],
+            output_path=output,
+            dpi=300,
+        )
+        assert result == output
+        assert output.exists()

tests/test_web.py

@@ -0,0 +1,88 @@
+"""Tests for the web backend."""
+
+import pytest
+from fastapi.testclient import TestClient
+from pathlib import Path
+from unittest.mock import AsyncMock, patch
+
+from disk_checker.web.server import app
+
+
+@pytest.fixture
+def client():
+    """Create test client."""
+    return TestClient(app)
+
+
+@pytest.fixture
+def sample_csv_content():
+    """Sample CSV content for testing."""
+    return """nsec,read_clat_ns_count,read_clat_ns_cumulative,read_clat_ns_percentile
+19791872,1,1,0.00016775708773695687
+22413312,4,5,0.0008387854386847844
+22675456,9,14,0.0023485992283173965
+"""
+
+
+@pytest.fixture
+def sample_csv_path(tmp_path, sample_csv_content):
+    """Create sample CSV file."""
+    path = tmp_path / "test.csv"
+    path.write_text(sample_csv_content)
+    return path
+
+
+def test_health_check(client):
+    """Test health check endpoint."""
+    response = client.get("/health")
+    assert response.status_code == 200
+    assert response.json()["status"] == "ok"
+
+
+def test_scan_csv(client, sample_csv_path):
+    """Test CSV scan endpoint."""
+    with open(sample_csv_path, "rb") as f:
+        response = client.post("/api/v1/scan", files={"file": f})
+    assert response.status_code == 200
+    data = response.json()
+    assert "metrics" in data
+    assert len(data["metrics"]) > 0
+
+
+def test_plot_endpoint(client, sample_csv_path):
+    """Test plot generation endpoint."""
+    with open(sample_csv_path, "rb") as f:
+        response = client.post(
+            "/api/v1/plot",
+            files={"file": (sample_csv_path.name, f, "text/csv")},
+            data={"unit": "us"},
+        )
+    assert response.status_code == 200
+    assert response.headers["content-type"] == "image/png"
+
+
+def test_plot_with_options(client, sample_csv_path):
+    """Test plot generation with options."""
+    with open(sample_csv_path, "rb") as f:
+        response = client.post(
+            "/api/v1/plot",
+            files={"file": (sample_csv_path.name, f, "text/csv")},
+            data={
+                "metric": "read_clat",
+                "unit": "ms",
+                "log_x": "true",
+                "cdf": "true",
+            },
+        )
+    assert response.status_code == 200
+
+
+def test_invalid_metric(client, sample_csv_path):
+    """Test invalid metric returns error."""
+    with open(sample_csv_path, "rb") as f:
+        response = client.post(
+            "/api/v1/plot",
+            files={"file": (sample_csv_path.name, f, "text/csv")},
+            data={"metric": "invalid_metric", "unit": "us"},
+        )
+    assert response.status_code == 400